“METHOD AND SYSTEM FOR DYNAMIC TRAFFIC CONTROL FOR ONE OR
MORE JUNCTIONS”

The present invention generally relates to traffic management, and more particularly to method and system for dynamic traffic control for one or more junctions with traffic signals thereat.

Traffic congestion is a major problem that is growing exponentially in metropolitan cities due to the increasing demand for private vehicles combined with limited land resources. Traffic results in longer travel time and the waste of billions of human resource hours, waste of fuel, degradation of the environment, growing accident rates, and largely reduced service efficiency of roads. Traffic congestion may also impose life-threatening scenarios due to psychological stress placed on the driver. The red light running (RLR) phenomenon that can cause an accident mainly results from the frustration caused by short or long signal cycle lengths that the driver feels to be unjustified. Sometimes, too short a signal cycle length is adopted by authorities to deal with high traffic density. However, a short signal cycle length often fails to manage traffic queues of different adjoining roads on an intersection and may lead to waiting for more than two signal cycles before crossing the road junction. With increase in number of vehicles especially in urban areas, there is a greater need to provide a more effective means to control traffic.

Traditional traffic management systems for networks function on a fixed signal cycle time model, whereby changes of the traffic signal times at a junction are based on a predetermined, cycle-based pattern. During peak traffic periods the signal cycle times are increased to allow a greater volume of traffic to clear while during off peak periods the signal cycle times are reduced to reduce the delay time (i.e. waiting time) at a junction when the roads are clear of vehicles. These manual and fixed solutions aim to sort out problems on road sections with low traffic flows, but, for the major sections, such solutions are not effective due to short temporal and spatial congestion changes. Also, this type of method introduces human evaluation errors and incorrect green signal time balancing.

Traffic congestion can be tackled by demand management of a given road intersection by adjusting a traffic light’ s cycle time according to the live congestion situation. Retiming traffic signals based on real-time traffic conditions can be one of the most cost-effective ways to improve traffic flow within the road network. Such systems consider real-time traffic conditions to adjust the cycle times of the traffic signals to minimize traffic congestions at various junctions in a road network. Optimized traffic signals can reduce traffic delays and stops considerably as motorists travel along a section of road. The benefits of optimized traffic signals experienced by motorists include improved safety, reduced fuel consumption and reduced emissions. Hence, real-time or near-real-time traffic data prediction is of prime importance.

For collecting such real-time or near-real-time traffic data, known solutions require different technologies of traffic density sensing such as traffic detection by Radar, magnetic loop, camerabased video analytics and the like. Herein, available conventional (micro controller based) solutions requires human intervention (traffic police) as the signal junctions does not communicate with each other in real time. Existing solutions have several limitations, such as coverage due to a sensor’s fixed location, and cable-based and/or wireless connections increase the initial cost of implementation and maintenance. That is, such traffic density sensing requires on field sensor/ hardware installation resulting in increased costs, and this also leads to considerable amount of maintenance and often results in frequent downtime. Furthermore, these solutions are financially feasible only for large number of signal junctions, typically 40 junctions or more, and is thus not scalable to smaller road networks.

In light of the above, it is an object of the present disclosure to provide a modular, scalable solution for dynamic traffic control which does not require on field sensors for capturing traffic density

data, thus resulting in cost effectiveness (thus reduced capital expenditure) and reduced maintenance and downtime (thus reduced operational expenditure).

The object of the present disclosure is achieved by a computer-implemented method for dynamic traffic control for one or more junctions with traffic signals thereat. The method comprises receiving traffic control data for the one or more junctions. Herein, the traffic control data comprises historical information about signal cycle phase times of the traffic signals. The method also comprises receiving traffic route data for the one or more junctions from a traffic route data platform. Herein, the traffic route data comprises current traffic information. The method further comprises determining optimum values for signal cycle phase times for a given time for the traffic signals at each of the one or more junctions based on the traffic control data and the traffic route data. The method further comprises controlling the traffic signals at each of the one or more junctions to operate with corresponding determined optimum value for signal cycle phase time.

In one or more embodiments, the method further comprises training a machine learning model based on historical information about at least one of traffic congestion information, vehicle count information and lane density information for each of the one or more junctions, and used signal cycle phase times for the traffic signals at each of the one or more junctions; and implementing the trained machine learning model for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times.

In one or more embodiments, the method further comprises implementing a rule-based engine for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times.

In one or more embodiments, the traffic control data further comprises historical information about at least one of traffic congestion information, vehicle count information and lane density information for each of the one or more junctions.

In one or more embodiments, the current traffic information comprises information about at least one of current traffic congestion information, current vehicle count information and current lane density information for each of the one or more junctions.

In one or more embodiments, the optimum values for signal cycle phase times for the traffic signals at each of the one or more junctions provide at least one of reduced traffic congestion at the one or more junctions, reduced vehicle count at the one or more junctions and reduced lane density for the given time at the one or more junctions.

In one or more embodiments, the traffic route data for the one or more junctions is based on satellite map information as obtained and processed using geographic information system (GIS) framework by the traffic route data platform.

The object of the present disclosure is also achieved by a system for dynamic traffic control for one or more junctions with traffic signals thereat. The system comprises one or more processing units. The system also comprises a traffic control database comprising historical information about signal cycle phase times of the traffic signals. The system further comprises a memory communicatively coupled to the one or more processing units. The memory comprises a dynamic traffic control module configured to perform the method steps described above.

The object of the present disclosure is further achieved by a computer-program product, having computer-readable instructions stored therein, that when executed by a processing unit, cause the processing unit to perform the method steps described above.

The object of the present disclosure is further achieved by a computer readable medium on which program code sections of a computer program are saved, the program code sections being loadable into and/or executable in a system to make the system execute the method steps described above when the program code sections are executed in the system.

Still other aspects, features, and advantages of the invention are readily apparent from the following detailed description, simply by illustrating a number of particular embodiments and implementations, including the best mode contemplated for carrying out the invention. The invention is also capable of other and different embodiments, and its several details can be modified in various obvious respects, all without departing from the scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

A more complete appreciation of the present disclosure and many of the attendant aspects thereof will be readily obtained as the same becomes better understood by reference to the following description when considered in connection with the accompanying drawings:

FIG 1 is a schematic representation of a system for dynamic traffic control for one or more junctions, in accordance with an embodiment of the present invention;

FIG 2 is a schematic diagram of a computing system that can be implemented for dynamic traffic control for one or more junctions, in accordance with an embodiment of the present invention;

FIG 3 is a schematic diagram of a database, in accordance with an embodiment of the present invention; and

FIG 4 is a flowchart illustrating a method for dynamic traffic control for one or more junctions, in accordance with an embodiment of the present invention.

Various embodiments are described with reference to the drawings, wherein like reference numerals are used to refer the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for the purpose of explanation, numerous specific details are set forth in order to provide thorough understanding of one or more

embodiments. It may be evident that such embodiments may be practiced without these specific details.

Examples of a method, a system, a computer-program product and a computer readable medium for dynamic traffic control for one or more junctions with traffic signals thereat are disclosed herein. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It is apparent, however, to one skilled in the art that the embodiments of the invention may be practiced without these specific details or with an equivalent arrangement. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the embodiments of the invention.

FIG 1 is a schematic representation of system 100 to be implemented for dynamic traffic control for one or more junctions with traffic signals thereat, in accordance with one or more embodiments of the present invention. The system 100 utilizes a network 102 to communicate with a traffic control database 104, a traffic route data platform 106 and a local server 108. The system 100 includes programable logic controllers 110, a message-broker application 112, a database 114, and an analytics application 116 including a rule -based engine 118 and/or a machine learning model 120.

The term “junction,” as used herein, includes any defined traffic area in a road network where two or more roads may intersect (not including turns), and includes defined zones, an approach to another defined traffic area, and the interior of an intersection, among others. Typically, in the road network, each junction is provided with at least one traffic signal. The term “traffic signal” as used herein refers to an apparatus that provide different signals and/or signs that regulate road traffic, to be observed by all participants of road traffic, vehicles, passengers and pedestrians. For purposes of this application, the term “traffic signal” means an apparatus having at least one light source and capable of exhibiting at least a red and a green light, and/or a timer display to display remaining time in the current cycle of the traffic signal, in order to direct an operator of a motor vehicle to stop or to proceed.

The present system 100 may be implemented for changing signal cycle phase time of traffic signals at one or more junctions in a road network. The invention described herein automates the processes of retiming of traffic signals, and proposes a more convenient and cost-effective solution to known methods being employed which are inconvenient and costly to implement as a result of manual processes required and/or requirement of hardware components. It has been recognized that the underlying framework discussed herein can be used to both monitor and control aspects of any observed area, e.g. a traffic intersection or other physical environment. As such, the invention described herein can not only aid in automating traffic signal re-timing, but also in more generally modeling and optimizing the performance of transportation networks.

In the exemplary illustration of FIG 1, the system 100 has been embodied as a cloud-based service. As illustrated in FIG 1, the system 100 utilizes a network 102. The term “network” refers to computer networks, such as the Internet, that allow computers to exchange data. In the present system 100, the network 102 may be, but not limited to, a cellular network or an OFC (Optical Fiber Cable) based network. As may be contemplated, the network 102 may utilize an existing communication network, which is particularly advantageous in implementing the system 100 described herein due to inherent coverage and ubiquity and thus ability to effectively connect various components of the system 100 for operations, as discussed below.

The network 102 provides a platform on which multiple applications may run, that provides traffic management services. In the network 102, application program interfaces (APIs) that are used to communicate between different components of a network. Such APIs can be open source or proprietary. OpenFlow™ is an example of an open source API. An example of a proprietary API is onePK™ from Cisco Systems®. All trademarks and registered trademarks used herein are the property of their respective owners. APIs, typically representational state transfer (REST) APIs, enable basic network functions, such as path computation, loop avoidance, routing, and security.

API presents a network abstraction interface to the applications and management systems in the network 102, and thus enable applications in the system 100 to program the network 102 and request services from it.

In one or more embodiments, the network 102 of the present system 100 includes one or more networks such as a data network, a wireless network, a telephony network, or any combination thereof. It is contemplated that the data network may be any local area network (LAN), metropolitan area network (MAN), wide area network (WAN), a public data network (e.g., the Internet), short range wireless network, or any other suitable packet- switched network, such as a commercially owned, proprietary packet-switched network, e.g., a proprietary cable or fiber-optic network, and the like, or any combination thereof. In addition, the wireless network may be, for example, a cellular network and may employ various technologies including enhanced data rates for global evolution (EDGE), general packet radio service (GPRS), global system for mobile communications (GSM), Internet protocol multimedia subsystem (IMS), universal mobile telecommunications system (UMTS), etc., as well as any other suitable wireless medium, e.g., worldwide interoperability for microwave access (WiMAX), Long Term Evolution (LTE) networks, code division multiple access (CDMA), wideband code division multiple access (WCDMA), wireless fidelity (Wi-Fi), wireless LAN (WLAN), Bluetooth®, Internet Protocol (IP) data casting, satellite, mobile ad-hoc network (MANET), and the like, or any combination thereof.

By way of example, the components of the system 100 communicate with each other and other applications (like third-party applications) outside of the system 100 using well known, new or still developing protocols. In this context, a protocol includes a set of rules defining how the network nodes within the communication network 102 interact with each other based on information sent over the communication links. The protocols are effective at different layers of operation within each node, from generating and receiving physical signals of various types, to selecting a link for transferring those signals, to the format of information indicated by those signals, to identifying which software application executing on a computer system sends or receives the information. The conceptually different layers of protocols for exchanging

information over a network are described in the Open Systems Interconnection (OSI) Reference Model.

Communications between components of the network 102 are typically affected by exchanging discrete packets of data. Each packet typically comprises ( 1 ) header information associated with a particular protocol, and (2) payload information that follows the header information and contains information that may be processed independently of that particular protocol. In some protocols, the packet includes (3) trailer information following the payload and indicating the end of the payload information. The header includes information such as the source of the packet, its destination, the length of the payload, and other properties used by the protocol. Often, the data in the payload for the particular protocol includes a header and payload for a different protocol associated with a different, higher layer of the OSI Reference Model. The header for a particular protocol typically indicates a type for the next protocol contained in its payload. The higher layer protocol is said to be encapsulated in the lower layer protocol. The headers included in a packet traversing multiple heterogeneous networks, such as the Internet, typically include a physical (layer 1) header, a data-link (layer 2) header, an internetwork (layer 3) header and a transport (layer 4) header, and various application (layer 5, layer 6 and layer 7) headers as defined by the OSI Reference Model.

FIG 2 illustrates schematic diagram of a computing system 200 for dynamic traffic control for one or more junctions with traffic signals thereat, in accordance with an embodiment of the present invention. In an example, the computing system 200 may be a computer -program product 200 programmed for performing the said purpose. In another example, the computing system 200 may be a computer readable medium on which program code sections of a computer program are saved, the program code sections being loadable into and/or executable in a system to make the system execute the steps for performing the said purpose. The computing system 200 may be incorporated in one or more physical packages (e.g., chips). By way of example, a physical package includes an arrangement of one or more materials, components, and/or wires on a structural assembly (e.g., a baseboard) to provide one or more characteristics such as physical strength, conservation of size, and/or limitation of electrical interaction. It is contemplated that in certain embodiments the computing system can be implemented in a single chip. The system 100 of the present invention as discussed in the preceding paragraphs may include or be embodied in the computing system 200. It may be appreciated that the two systems 100 and 200 (and the corresponding components/elements) may be equivalent for the purposes of the present invention.

In one embodiment, the computing system 200 includes a communication mechanism such as a bus 202 for passing information among the components of the computing system 200. The computing system 200 includes one or more processing units 204 and a memory unit 206. Generally, the memory unit 206 is communicatively coupled to the one or more processing units 204. Hereinafter, the one or more processing units 204 are simply referred to as processor 204 and the memory unit 206 is simply referred to as memory 206. Herein, in particular, the processor 204 has connectivity to the bus 202 to execute instructions and process information stored in the memory 206. The processor 204 may include one or more processing cores with each core configured to perform independently. A multi-core processor enables multiprocessing within a single physical package. Examples of a multi-core processor include two, four, eight, or greater numbers of processing cores. Alternatively, or in addition, the processor 204 may include one or more microprocessors configured in tandem via the bus 202 to enable independent execution of instructions, pipelining, and multithreading. The processor 204 may also be accompanied with one or more specialized components to perform certain processing functions and tasks such as one or more digital signal processors (DSP) 208, or one or more application-specific integrated circuits (ASIC) 210. A DSP 208 typically is configured to process real-world signals (e.g., sound) in real time independently of the processor 204. Similarly, an ASIC 210 can be configured to performed specialized functions not easily performed by a general purposed processor. Other specialized components to aid in performing the inventive functions described herein include one or more field programmable gate arrays (FPGA) (not shown), one or more controllers (not shown), or one or more other special-purpose computer chips.

As used herein, the term "processor" refers to a computational element that is operable to respond to and processes instructions that drive the system. Optionally, the processor includes, but is not limited to, a microprocessor, a microcontroller, a complex instruction set computing (CISC) microprocessor, a reduced instruction set (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or any other type of processing circuit. Furthermore, the term "processor" may refer to one or more individual processors, processing devices and various elements associated with a processing device that may be shared by other processing devices. Additionally, the one or more individual processors, processing devices and elements are arranged in various architectures for responding to and processing the instructions that drive the system.

The processor 204 and accompanying components have connectivity to the memory 206 via the bus 202. The memory 206 includes both dynamic memory (e.g., RAM, magnetic disk, writable optical disk, etc.) and static memory (e.g., ROM, CD-ROM, etc.) for storing executable instructions that when executed perform the method steps described herein for dynamic traffic control for one or more junctions with traffic signals. In particular, the memory 206 includes a dynamic traffic control module 212 to perform steps for dynamic traffic control for one or more junctions with traffic signals. The memory 206 also stores the data associated with or generated by the execution of the inventive steps.

Herein, the memory 206 may be volatile memory and/or non-volatile memory. The memory 206 may be coupled for communication with the processing unit 204. The processing unit 204 may execute instructions and/or code stored in the memory 206. A variety of computer-readable storage media may be stored in and accessed from the memory 206. The memory 206 may include any suitable elements for storing data and machine -readable instructions, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, a hard drive, a removable media drive for handling compact disks, digital video disks, diskettes, magnetic tape cartridges, memory cards, and the like.

FIG 3 is a schematic diagram of the database 114, in accordance with one or more embodiments of the present disclosure. In one embodiment, the database 114 includes geographic data 302 used for (or configured to be compiled to be used for) mapping and/or traffic management services. As shown, the database 114 includes node data records 304, link data records 306, points-of-interest (POI) data records 308, obstacle records 310, other records 312, and indexes 314, for example. More, fewer or different data records can be provided. In one embodiment, additional data records (not shown) can include cartographic (“carto”) data records, routing data, and maneuver data. In one embodiment, the indexes 314 may improve the speed of data retrieval operations in the database 114. In one embodiment, the indexes 314 may be used to quickly locate data without having to search every row in the database 114 every time it is accessed. The obstacle records 310 store predicted/validated obstacles and other related road characteristics. The predicted data, for instance, can be stored as attributes or data records of an obstacle overlay, which fuses with the predicted attributes with map attributes or features.

In exemplary embodiments, the link data records 306 are links or segments representing paths, as can be used in the calculated route or recorded route information for determination of signal cycle phase times of traffic signals. The node data records 304 are end points corresponding to the respective links or segments of the road segment data records 306. The link data records 306 and the node data records 304 represent a road network, such as used by vehicles, cars, and/or other entities. Alternatively, the database 114 can contain path segment and node data records or other data that represent pedestrian paths or areas in addition to or instead of the vehicle road record data, for example.

In one embodiment, the database 114 can be maintained by the content provider in association with the third-party services platform (e.g., a map developer). The map developer can collect geographic data to generate and enhance the database 114. There can be different ways used by the map developer to collect data. These ways can include remote sensing, such as aerial or satellite photography, obtaining data from other sources, such as municipalities or respective geographic authorities, and the like.

The database 114 can be a master geographic database stored in a format that facilitates updating, maintenance, and development. For example, the master geographic database or data in the master geographic database can be in an Oracle spatial format or other spatial format, such as for development or production purposes. The Oracle spatial format or development/production database can be compiled into a delivery format, such as a geographic data files (GDF) format. The data in the production and/or delivery formats can be compiled or further compiled to form geographic database products or databases, which can be used in end user navigation devices or systems.

It is to be understood that the system and methods described herein may be implemented in various forms of hardware, software, firmware, special purpose processors, or a combination thereof. One or more of the present embodiments may take a form of a computer program product comprising program modules accessible from computer-usable or computer-readable medium storing program code for use by or in connection with one or more computers, processors, or instruction execution system. For the purpose of this description, a computer-usable or computer-readable medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation mediums in and of themselves as signal carriers are not included in the definition of physical computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, random access memory (RAM), a read only memory (ROM), a rigid magnetic disk and optical disk such as compact disk read-only memory (CD-ROM), compact disk read/write, and digital versatile disc (DVD). Both processors and program code for implementing each aspect of the technology can be centralized or distributed (or a combination thereof) as known to those skilled in the art.

FIG 4 is a flowchart of a computer-implemented method 400 for dynamic traffic control for one or more junctions with traffic signals thereat, in accordance with an embodiment of the present invention. In various embodiments, the various components of the system 100 may perform one or more steps (or portions of steps) of the method 400 and may be implemented in, for instance, a computing system including a processor and a memory. The method 400, for instance, describes the process for dynamic traffic control for one or more junctions with traffic signals.

At step 402, the traffic control data for the one or more junctions is received. The traffic control data comprises historical information about signal cycle phase times of the traffic signals. Such historical information may include signal cycle phase times with time stamps to indicate the timings used for each of the traffic signals in the past for particular time of a day. Such historical information may be for any suitable period, for example past one or more hours, past one or more days, past one or more weeks, past one or more months, or even past one or more weeks.

In one or more embodiments, the traffic control data further comprises historical information about at least one of traffic congestion information, vehicle count information and lane density information for each of the one or more junctions. The term “traffic congestion” as used herein refers to traffic jams, traffic slowdowns, traffic accidents, road works generated traffic problems etc., whether in urban areas, inter-urban areas or other areas. The term “vehicle count” refers to an estimated number of vehicles that may be present at a particular junction in a particular timeperiod. Herein, such “particular time-period” may usually be in the range of 1 to few minutes, typically corresponding to signal cycle phase time at that junction. Further, the term “lane density” refers to density of vehicles in a particular lane or area in the vicinity of a particular junction. It may be appreciated that the three listed factors herein, i.e. the traffic congestion information, the vehicle count information and the lane density information affect the signal cycle phase time to be used at any junction to ensure relatively smooth flow of traffic and for minimizing the traffic jams or the like. Such historical data points may have respective time stamps to indicate the time of prevailing conditions at the junctions, to make comparisons for analysis as discussed later in the description.

At step 402, the traffic route data for the one or more junctions is received. The traffic route data comprises current traffic information. The term “current traffic information” as used throughout this detailed description refers to any information related to real-time or near real-time information about number of vehicles at a particular junction, speed of vehicles, time duration of a traffic jam at a particular junction and the like. In one or more embodiments, the current traffic information comprises information about at least one of current traffic congestion information, current vehicle count information and current lane density information for each of the one or more junctions. In one or more examples, the current traffic information further comprises information about one or more of accident information and procession information for each of the one or more junctions. Therefore, in general, the current traffic information is indicative of a traffic accident, an unexpected accident, a public transportation status, and/or a road congestion status, etc., however, it is not limited to the above-mentioned meanings and can be applied to other similar meanings as necessary.

In an embodiment, the system 100 is in communication with the traffic control database 104, via the network 102. The traffic control database 104 provides the traffic control data for the one or more junctions to the system 100. In other words, the system 100 receives the traffic control data for the one or more junctions from the traffic control database 104. Herein, in an example, the traffic control database 104 may be a part of a data warehouse managed by a traffic control center of, say, a city responsible for managing the road networks therein.

In an embodiment, the system 100 is in communication with the traffic route data platform 106, via the network 102. The traffic route data 106 provides the traffic route data for the one or more junctions to the system 100. In other words, the system 100 receives the traffic route data for the one or more junctions from the traffic route data platform 106. In a further embodiment, the traffic route data 106 provides the traffic control data for the one or more junctions to the system 100. That is, the system 100 also receives the traffic route data for the one or more junctions from the traffic route data platform 106. In an embodiment, the traffic route data for the one or more junctions is based on satellite map information as obtained and processed using geographic

information system (GIS) framework by the traffic route data platform. Herein, in an example, the traffic route data platform 106 may be a third-party data source, such as crowd-sourced traffic data source, like Google, Bing, and other data sources which collect such crowdsourced traffic data and provide the result in their APIs.

For instance, in an example, the traffic route data platform 106 may be Google Maps® which uses various sources for traffic data, depending on the availability of hardware-intensive sensors, personalized network availability and anonymized traffic data, local road sensors, car/taxi fleets’ private monitoring network, etc. Crowdsourced, anonymized traffic data are collected from people using the Google Maps application or other Google services on certain smartphones, including Android and personal digital assistant (PDA) devices. Initially, the GPS functionality is set to ‘applied’ by default to relay location data back to the Google server. GPS -determined locations are analyzed and transmitted by a large number of cellphone users. Using the data, the traffic status information along a stretch of road are calculated by Google to generate a live traffic map through the use of various techniques including machine learning methods. For example, Google Maps provides numerous JavaScript APIs, which have a vast variety of API functionalities for map editing, some of which are traffic route API, traffic layer API, Google Roots API, etc. which gives the option to observe live traffic. With the help of the such APIs of Google Maps, Google JavaScript API response data can be leveraged to extract congestion information by removing clutter and being left with current traffic information.

Herein, the traffic control data including the historical information about signal cycle phase times for a particular junction can aid in determining how to retime a particular traffic light at other intersections in the traffic network. For example, there may be historical information of traffic jams at one or more junctions along with corresponding historical information about signal cycle phase times for those one or more junctions at the same time periods. Thus, the system 100 can utilize such historical information to estimate optimal values for the signal cycle phase times for those one or more junctions (e.g., at the same time periods) by considering different scenarios which may end up leading to reduced traffic jams. Such optimization techniques may be contemplated by a person skilled in the art and thus have not been discussed herein.

In some implementations, the system 100 is also in communication with the local server 108 which may include information about predefined signal cycle phase times of the traffic signals for each of the one or more junctions. Herein, the local server 108 may also include access details for controlling of the traffic signals at the one or more junctions in consideration for implementation of the present system 100. The local server 108 may further provide information about different protocols to be executed, as necessary for controlling of the signal cycle phase times of the said traffic signals. Herein, the present system 100 may receive such information from the local server 108, via the network 102. In an implementation, the local server 108 may perform signal metadata export, taken from SCAD A server (for example, at the control room), and to be sent to the system 100.

In one or more embodiments of the present disclosure, the system 100 includes the message -broker application 112 configured to generate API calls to receive the traffic control data for the one or more junctions, the traffic control data comprising historical information about signal cycle phase times of the traffic signals with time stamps along with at least one of corresponding traffic congestion information, vehicle count information and lane density information at respective times in the time stamps for each of the one or more junctions, and the traffic route data for the one or more junctions from a traffic route data platform, the traffic route data comprising at least one of current traffic congestion information, current vehicle count information and current lane density information for each of the one or more junctions. Herein, the message -broker application 112 acts as an intermediary platform when it comes to processing communication between two applications, for example in the network 102. RabbitMQ is one such open-source enterprise messaging system modeled on the Advanced Message Queuing Protocol (AMQP) standard.

In some implementations, the system 100 may include the database 114 to store the received data via the message-broker application 112, including the traffic control data for the one or more junctions with historical information about signal cycle phase times of the traffic signals with time stamps along with at least one of corresponding traffic congestion information, vehicle count information and lane density information at respective times in the time stamps for each of the one or more junctions, and the traffic route data for the one or more junctions with at least one of current traffic congestion information, current vehicle count information and current lane density information for each of the one or more junctions.

Further, at step 406, optimum values for signal cycle phase times is determined for a given time for the traffic signals at each of the one or more junctions based on the traffic control data and the traffic route data. Herein, as illustrated in FIG 1, the system 100 includes the analytics application 116 configured to analyze the traffic control data and the traffic route data to determine optimum values for signal cycle phase times for the given time for the traffic signals at each of the one or more junctions, such that the optimum values for signal cycle phase times for the traffic signals at each of the one or more junctions provide at least one of reduced traffic congestion at the one or more junctions, reduced vehicle count at the one or more junctions and reduced lane density at the given time at the one or more junctions. In an example, the optimum values for signal cycle phase times are determined for next signal cycle of the traffic signals. Herein, in an example, the determined optimum values for signal cycle phase times for the traffic signals are further stored back in the database 114 for future reference or the like.

In an example embodiment, the method 400 implements the rule -based engine 118, in the analytics application 116, for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times. In other words, the analytics application 116 in the system 100 implements a rule-based engine for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times. Rule-based strategies rely on preset rules, such as those embedded in signal controllers at some isolated intersections and the generalized adaptive signal control algorithms at other specified intersections. Such rule -based approach may particularly be beneficial at initial stages of implementation of the system 100, when there is not much optimized dataset providing holistic view of end results of applied optimal values to the traffic signals. In an example implementation, the rule-based engine 118 may be Drools® engine, which is a business rule management system with a forward and backward chaining inference, more correctly known as a production rule system, using an enhanced implementation of the Rete algorithm.

As may be appreciated, such rule-based optimization strategies mainly deal with the computational process and performance, and may incur complexity and fail to guarantee holistic optimal control, as they consist of many short-term optimizations based on different models. In an example embodiment, the method 400 implements artificial intelligence approaches, like reinforcement learning and others, are under development in the machine-learning community, as they offer key advantages in this regard. Herein, the machine learning model 120, in the analytics application 116, is trained based on historical information about at least one of traffic congestion information, vehicle count information and lane density information for each of the one or more junctions, and used signal cycle phase times for the traffic signals at each of the one or more junctions. Further, the trained machine learning model 120 is implemented for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times.

Machine learning is a subset of artificial intelligence. Herein, the machine learning model is trained to perform tasks based on some predefined data sets without having to be programmed to do so. The predefined data sets are set of input and output according to which the machine learning model is trained. Typically, a machine learning model employs an artificial neural network (ANN). The artificial neural network (ANN) may have a single layer or multiple hidden layers between the input and output layers, with the output each layer serving as input to the successive layer. As discussed, for proper functioning, the machine learning model needs to be trained. The training is done by employing learning algorithms. The learning algorithms may be a supervised learning algorithm or an unsupervised learning algorithm or a reinforcement learning algorithm. The supervised learning algorithm is like a teacher-student learning. Herein, data sets consisting of a set of input data along with their respective output data are provided. The machine learning model considers them as examples and learns a rule that maps each input data to the respective output

data. Contrary to the supervised learning, in unsupervised learning, outputs for the input data is not provided and the machine learns without supervision. In reinforcement learning, no data sets are provided and the machine learns with “experience”.

At step 408, the traffic signals are controlled at each of the one or more junctions to operate with corresponding determined optimum value for signal cycle phase time. Herein, as illustrated in FIG 1, the system 100 includes the programable logic controllers 110. In the system 100, each of the programable logic controllers 110 is associated with one of the traffic signals at each of the one or more junctions. As employed herein, the term “programmable logic controller” (PLC) means a programmable controller, an intelligent relay, a control relay, or another intelligent or microprocessor-based device used for controlling, automating and/or monitoring a residential, commercial or industrial process. Typically, programmable controllers, intelligent relays and control relays are lower-cost, lower-end versions of a PLC. A PLC is usually real-time and can do relatively more complex math. Programmable controllers, intelligent relays and control relays are typically not real time and are typically more restricted in what they can do. For instance, some of the low-end control relays do not include math functions or have memory, while some of the high-end control relays have some math functions and may include counters. Herein, the programable logic controllers 110 are in communication with the network 102 to receive determined optimum value for signal cycle phase times. The programable logic controllers 110 are configured to control the traffic signals at each of the one or more junctions to operate with corresponding determined optimum value for signal cycle phase time. The implementation of the PLCs 110 for controlling the signal cycle phase times of the traffic signals may be contemplated by a person skilled in the art and thus has not been explained herein for the brevity of the present disclosure.

The system 100, the method 400 and the computing system 200 provide a modular, scalable solution for dynamic traffic control which does not require on field sensors for capturing traffic density data, thus resulting in cost effectiveness (thus reduced capital expenditure) and reduced maintenance and downtime (thus reduced operational expenditure). The present invention caters to the need of scalability for controlling traffic signals for 1 junction to 100 junctions or more, as required. The present invention allows the flexibility to capture the traffic density data of larger distance/demography with ease based on real time traffic congestion data as obtained from third-party traffic data providers, such as Google routes API (or equivalent APIs). Herein, on-field sensors are not required, hence reducing the hardware installation cost and maintenance cost, and further reduced downtime due to less hardware installed and thereby improved reliability. It may be appreciated that the present invention is flexible in terms of ease of capturing traffic data through Google/Equivalent routes API for any area/ distance without making any changes in the hardware configuration at field.

The present invention providing artificial intelligence based solution predicts the optimum signal cycle phase time intelligently based on the real time traffic congestion data (as obtained from google routes API, for example), without any on field sensors for capturing of traffic density/ vehicle count. The present invention is implemented for controlling traffic signals in one or more junctions, enabling the smooth traffic flow in the road network. Historical and real-time data from sources (such as, traffic data providers and/or SCADA systems at the central control room) and further real time traffic congestion data (from Google routes API/equivalent API) is utilized by the cloud based system 100 for data analytics and based on data analytics (considering multiple parameters and scenarios), dynamic traffic control system predicts the next signal cycle phase time intelligently and supersedes the predefined signal phase time of automation programming, thus enabling the intelligent and real-time control of traffic flow. The system 100 may, but not necessarily, use machine learning models (e.g., a supervised learning algorithm implementing Random Forest, Decision Tree, Neural Net, or equivalent techniques) to achieve the purpose.

The present invention can be utilized to provide a monthly subscription based service to a municipality or other entity without the large capital costs upfront since the hardware installation process is easier and more cost effective and the cluster computing resources provide economies of scale to service multiple customers. All of these benefits represent a significant cost savings and thus ability to more easily upgrade a traffic system to utilize adaptive signal control. Further, the present invention can be used to observe traffic flow and various other criteria to determine the environmental impact achieved (i.e. reduction in vehicle greenhouse gas emissions) by improving signal re-timing or other optimization techniques to obtain carbon credits or otherwise track such environmental statistics for later use.

While the present disclosure has been described in detail with reference to certain embodiments, it should be appreciated that the present disclosure is not limited to those embodiments. In view of the present disclosure, many modifications and variations would be present themselves, to those skilled in the art without departing from the scope of the various embodiments of the present disclosure, as described herein. The scope of the present disclosure is, therefore, indicated by the following claims rather than by the foregoing description. All changes, modifications, and variations coming within the meaning and range of equivalency of the claims are to be considered within their scope.

Reference Numerals

system 100 network 102 traffic control database 104 traffic route data platform 106 local server 108 programable logic controller 110 message-broker application 112 database 114 analytics application 116 rule-based engine 118 machine learning model 120 computing system 200 bus 202 processing unit 204 memory 206 digital signal processor (DSP) 208 application-specific integrated circuit (ASIC) 210 dynamic traffic control module 212 geographic data 302 data records 304 link data records 306 points-of-interest (POI) data records 308 obstacle records 310 other records 312 indexes 314 method flowchart 400
[EN ]
PATENT CLAIMS
1. A computer-implemented method for dynamic traffic control for one or more junctions with traffic signals thereat, the method comprising:

receiving traffic control data for the one or more junctions, wherein the traffic control data comprises historical information about signal cycle phase times of the traffic signals;

receiving traffic route data for the one or more junctions from a traffic route data platform, wherein the traffic route data comprises current traffic information;

determining optimum values for signal cycle phase times for a given time for the traffic signals at each of the one or more junctions based on the traffic control data and the traffic route data; and

controlling the traffic signals at each of the one or more junctions to operate with corresponding determined optimum value for signal cycle phase time.

2. The method according to claim 1 further comprising:

training a machine learning model (120) based on historical information about at least one of traffic congestion information, vehicle count information and lane density information for each of the one or more junctions, and used signal cycle phase times for the traffic signals at each of the one or more junctions; and

implementing the trained machine learning model (120) for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times.

3. The method according to claim 1 further comprising implementing a rule-based engine (118) for analyzing the traffic control data and the traffic route data to determine the optimum values for signal cycle phase times.

4. The method according to claim 1 , wherein the traffic control data further comprises historical information about at least one of traffic congestion information, vehicle count information and lane density information for each of the one or more junctions.

5. The method according to claim 1, wherein the current traffic information comprises

information about at least one of current traffic congestion information, current vehicle count information and current lane density information for each of the one or more junctions.

6. The method according to claim 1 , wherein the optimum values for signal cycle phase times for the traffic signals at each of the one or more junctions provide at least one of reduced traffic congestion at the one or more junctions, reduced vehicle count at the one or more junctions and reduced lane density for the given time at the one or more junctions.

7. The method according to claim 1 , wherein the traffic route data for the one or more junctions is based on satellite map information as obtained and processed using geographic information system (GIS) framework by the traffic route data platform.

8. A system (100) for dynamic traffic control for one or more junctions with traffic signals thereat, the system (100) comprising:

one or more processing units (204);

a memory (206) communicatively coupled to the one or more processing units (204), the memory (206) comprising a dynamic traffic control module (212) configured to perform the method steps as claimed in claims 1 to 7.

9. A computer-program product (200), having computer-readable instructions stored therein, that when executed by a processing unit (204), cause the processing unit (204) to perform method (400) steps according to any of the claims 1 to 7.

10. A computer readable medium on which program code sections of a computer program are saved, the program code sections being loadable into and/or executable in a system to make the system execute the method steps according to any of the claims 1 to 7 when the program code sections are executed in the system.