Description:FIELD OF THE INVENTION
The present invention is related, generally to a system and method for predicting auxiliary power consumption in a power plant and more particularly, but not exclusively to a system and method for predicting auxiliary power consumption in a power plant and providing insights on maintaining one or more auxiliary units in case of deviation from predicted performance.
BACKGROUND
Auxiliary power consumption (APC) in a power plant refers to the electrical energy that is consumed by various auxiliary systems and components necessary for the operation of the power plant itself. These systems do not directly contribute to the generation of electricity but are essential for the overall functioning of the plant. The auxiliary power consumption is typically expressed as a percentage of the total gross power output of the plant. Some components and systems such as cooling systems, pumps and fans, air and fuel gas systems, ash handling systems etc. contribute to auxiliary power consumption in a power plant. High auxiliary power consumption in a power plant can lead to various issues and challenges, impacting the overall efficiency and economic performance of the plant. The auxiliary power consumption represents a portion of the total energy produced by the power plant that is not delivered to the grid. High auxiliary power consumption lowers the plant's overall efficiency, as a significant portion of the generated power is used to meet internal needs rather than being sent to consumers. Power plants with high auxiliary power consumption may face a competitive disadvantage compared to more efficient plants, especially in regions with deregulated energy markets. Plants with lower operational costs can offer electricity at more competitive prices, potentially impacting the market position of less efficient facilities. Further, higher auxiliary power consumption often leads to increased emissions per unit of electricity generated. This can have environmental implications, especially in terms of greenhouse gas emissions if the power plant relies on fossil fuels. Reducing auxiliary power consumption is often aligned with environmental goals by improving the overall efficiency of power generation. Consequently, reduction in auxiliary power consumption has become a goal in power plant design and operation because it directly impacts the overall efficiency of the plant. A lower auxiliary power consumption means a higher net power output for a given amount of fuel input. Improved technologies, better design practices, and regular maintenance can contribute to minimizing auxiliary power losses in a power plant.
Therefore, there is a need for a system and method for predicting auxiliary power consumption in a power plant so that the auxiliary power consumption in a power plant can be predicted accurately and insights on maintaining one or more auxiliary units cane be provided in case of deviation from predicted performance.
SUMMARY
One or more shortcomings of the prior art are overcome, and additional advantages are provided through the present disclosure. Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.
The present invention is directed to a system for predicting auxiliary power consumption in a power plant. The system comprises one or more auxiliary units, one or more energy meters associated with the one or more auxiliary units. Each energy meter is associated with one auxiliary unit. The system further comprises one or more user devices and a processor communicably coupled with the energy meters and a memory. The system receives total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day as input from a user via a user device, and retrieves historical power consumption information of the one or more auxiliary units from a data repository. The system further predicts benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units on daily basis based on the received input and the retrieved historical power consumption information by using a pre-trained prediction model, and dynamically represents the predicted benchmark information in the user device for enabling a user to retrieve desired information related to auxiliary power consumption of the power plant.
In another embodiment, the present invention is directed to a method for predicting auxiliary power consumption in a power plant. The method comprises receiving total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day as input from a user via a user device; retrieving historical power consumption information of the one or more auxiliary units from a data repository. The method includes predicting benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units on daily basis based on the received input and the retrieved historical power consumption information by using a pre-trained prediction model, and dynamically representing the predicted benchmark information in the user device for enabling a user to retrieve desired information related to auxiliary power consumption of the power plant.
The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
BRIEF DESCRIPTION OF DRAWINGS
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which:
Figure 1 illustrates an exemplary architecture of a system for predicting auxiliary power consumption in a power plant, in accordance with some embodiments of the present disclosure;
Figure 2 illustrates a block diagram of the system of Figure 1 in accordance with some embodiments of the present disclosure;
Figure 3 illustrates a flowchart showing a method of predicting auxiliary power consumption in a power plant in accordance with some embodiments of present disclosure;
Figure 4 is a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure;
Figure 5 illustrates an exemplary input interface for implementing embodiments consistent with the present disclosure;
Figure 6 illustrates an exemplary interface for representing predicted APC information for implementing embodiments consistent with the present disclosure;
Figure 7 illustrates an exemplary APC correlation heatmap for representing predicted information for implementing embodiments consistent with the present disclosure;
Figure 8 illustrates an exemplary interface for block-wise APC analysis for implementing embodiments consistent with the present disclosure;
Figure 9 illustrates an exemplary graphical representation indicating historical station APC at same dates of previous years for implementing embodiments consistent with the present disclosure;
Figure 10 illustrates an exemplary interface for indicating station APC with Minimum and historical average of different dates at similar input conditions for implementing embodiments consistent with the present disclosure;
Figure 11 illustrates an exemplary representation of auxiliary power distribution percentage for implementing embodiments consistent with the present disclosure; and
Figure 12 illustrates an exemplary daily post facto deviation report for implementing embodiments consistent with the present disclosure.
The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION
In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.
The terms “comprises”, “comprising”, “includes”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
The present disclosure relates to a system for predicting auxiliary power consumption in a power plant. The system comprises one or more auxiliary units, one or more energy meters associated with the one or more auxiliary units. Each energy meter is associated with one auxiliary unit. The system further comprises one or more user devices and a processor communicably coupled with the energy meters and a memory. The system receives total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day as input from a user via a user device, and retrieves historical power consumption information of the one or more auxiliary units from a data repository. The system further predicts benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units on daily basis based on the received input and the retrieved historical power consumption information by using a pre-trained prediction model, and dynamically represents the predicted benchmark information in the user device for enabling a user to retrieve desired information related to auxiliary power consumption of the power plant.
In one embodiment, the system provides benchmark optimal APC values for all plant equipment for the next day, which, if achieved leads to cost savings. If the values are not achieved, then performing post-facto analysis leads to action steps for taking corrective action and running maintenance on low-performing assets. The system performs future prediction and benchmarking on a daily basis while the system performs block-wise prediction on a 15-minute interval basis.
In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.
Figure 1 illustrates an exemplary architecture of a system for optimizing auxiliary power consumption in a power plant, in accordance with some embodiments of the present disclosure.
As shown in Figure 1, the exemplary system (100) comprises one or more components configured for predicting auxiliary power consumption in a power plant and providing insights on maintenance of one or more auxiliary units in case of deviation from predicted performance. The exemplary system (100) discloses an auxiliary power prediction system (102) (hereinafter referred to as APPS), a plurality of auxiliary units (106-1,…, 106-6), a plurality of energy meters (108-1,…, 108-6) associated with the auxiliary units (106-1,….106-6), one or more user devices (104), and a data repository (110) communicatively coupled via a communication network (112). The communication network (112) may include, without limitation, a direct interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, etc.
The plurality of auxiliary units (106-1,…, 106-6) may include auxiliary units such as draft fans, fuel combustion fans, boiler feed pumps, cooling systems, compressors, ash handling plant, AC, ventilation systems, illumination, plant water systems, coal handling plant, miscellaneous low tension loads etc. The draft fans include induced-draft (ID) fans and forced-draft (FD) fans, wherein the ID fans pull the products of combustion in a boiler and direct them to the chimney for atmospheric discharge, and the FD fans supply air for combustion in steam boilers and create air pressure mechanically in the combustion chamber of a boiler. The fuel combustion fans include mill and primary air (PA) fans. The boiler feed pump is a specific type of pump used to pump feedwater in high pressure and temperature into a steam boiler. The cooling system includes circulating water (CW) pumps, auxiliary cooling water (ACW) pumps, cooling tower fans etc. An exemplary auxiliary power distribution percentage in different groups of auxiliary units of a power plant is illustrated in Figure 11.
The user device (104) is electronic equipment designed to serve particular purpose according to the requirement of the end user such as authorized operator of the power plant in order to access a plurality of information as provided by the APPS (102). The user device (110) may be a mobile device generally a portable computer or a computing device including the functionality for communicating over the communication network (112). For example, the mobile device can be a conventional web-enabled personal computer in the home, mobile computer (laptop, notebook, or subnotebook), Smart Phone (iPhone, Android), tablet computer or another device capable of communicating over the Internet or other appropriate communications network. In one embodiment, the user device (104) can comprise user application to receive prediction data from the APPS (102). The user application is further configured to display details of different APC information, prediction information, real time consumption information, information related to deviation from the predicted APC, insights on different APC components etc.
The data repository (110) stores plurality of information related to historical auxiliary power consumption, auxiliary units, coal quality, historical ambient weather etc. In one embodiment, the data repository (110) is configured to store information of correlation between different auxiliary units of the power plant. In one embodiment, the data repository (110) is configured to store one or more information received as input from the user. In an example, the data repository can be configured in one or more database platforms such as mongodb, amazon rds etc. In one embodiment, the data repository (110) may be configured as a standalone device independent from the APPS (102). In another embodiment, the data repository (110) may be integrated with the APPS (102).
The APPS (102) comprises at least a processor (114) and a memory (116) coupled with the processor (114). The processor (114) may be for example, any processing unit capable of processing the input data. The APPS (102) further comprises a data acquisition module (118), a data processing module (120), an auxiliary power prediction module (122) and a report generation module (124). The data acquisition module (118) is configured to accumulate user input, information related to historical auxiliary power consumption, auxiliary units, coal quality, historical ambient weather etc. The data processing module (120) is configured to analyze historical information related to plurality of auxiliary units and determine correlation between the auxiliary units. The auxiliary power prediction module (122) is configured to analyze user input and predict auxiliary power consumption of a power plant based on the historical information. The report generation module (124) is configured to dynamically generate a plurality of statistical information related to the auxiliary power consumption and insights on the probable cause of under performance of one or more auxiliary units.
In an embodiment, the APPS (102) may be a typical APPS as illustrated in Figure 2. The APPS (102) comprises the processor (114), and the memory (116) communicatively coupled with the processor (114). The APPS (102) further includes data (204) and modules (206). In one implementation, the data (204) may be stored within the memory (116). In some embodiments, the data (204) may be stored within the memory in the form of various data structures. Additionally, the data (204) may be organized using data models, such as relational or hierarchical or unstructured data models. In one example, the data (204) may include historical data (208), input data (210), prediction data (212), and other data (214). In one example, the historical data (208) defines a plurality of information of historical data on auxiliary power consumption and relevant parameters. Such information includes data on ambient conditions, plant load, equipment status, and any other variables that may impact auxiliary power consumption. The other data (214) may store data, including temporary data and temporary files, generated by the modules (206) for performing the various functions of the APPS (102).
The modules (206) may include, for example, the data acquisition module (118), the data processing module (120), the auxiliary power prediction module (122), the report generation module (124), and a machine learning module (220). The modules (206) may also comprise other modules (222) to perform various miscellaneous functionalities of the APPS (102). It will be appreciated that such aforementioned modules may be represented as a single module or a combination of different modules. The modules (206) may be implemented in the form of software executed by a processor, hardware and/or firmware.
In one embodiment, the data acquisition module (118) receives user input, information related to historical auxiliary power consumption, auxiliary units, coal quality, historical ambient weather etc. The generation schedule can be one of daily and block-wise. In case of daily prediction, the user input includes total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day. Wherein, in case of block-wise prediction, the user input includes date, block number, block load schedule, block average temperature, block relative humidity, plant load factor, amount of coal consumption. The station for coal consumption indicates the type and quality of the coal that will be used for power generation in next day. The data acquisition module (118) stores the information received as user input in the input data (210) of the data repository (110). The data acquisition module (118) further receives the historical APC information of the auxiliary units (106) from the user and further stores the received information as historical data (208) of the data repository (110).
The data processing module (122) further analyzes analyze historical information related to plurality of auxiliary units and determine correlation between the auxiliary units. The data processing module further aids in grouping the auxiliary units based on the determined correlation between the auxiliary units. Such selection & grouping selection is done considering 88% of total power consumption. All loads are distributed based on significant energy use (SEUs) and Co-relation with input variables. Co-relation also exists between each group. The one or more auxiliary units (106) are clustered into groups, wherein each group comprises the auxiliary units (106) having maximum extent of interdependence. In an example, if PA header pressure increases PA fan power increases while Mill power decreases. Thus, both loads are considered in the same group. The data processing module (122) determines correlation of each group of auxiliary units (106) and each of the one or more input parameters as received from the user based on analysis of the historical power consumption information by a pre-trained prediction model of the analysis engine (220). The data processing module (122) represents the determined correlation in a format of heat map as illustrated in Figure 7.
In an example, the draft fans are assigned in a group for which the APC is impacted by the export load and coal quality. The boiler feed pumps are assigned in a group for which the APC is impacted by the export load, coal quality, and relative humidity. Further, the cooling systems are assigned in a group for which the APC is impacted by the export load, average temperature, and relative humidity.
The auxiliary power prediction module (122) analyzes user input and predict auxiliary power consumption of a power plant based on the historical information. The auxiliary power prediction module (122), upon receipt of the user input, analyses the historical APC information and computes a suitable data pattern corresponding to the user input by using the analysis engine (220). The auxiliary power prediction module (122) predicts the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) by the pre-trained prediction model based on the determined correlation between the respective auxiliary unit and the one or more input parameters. The auxiliary power prediction module (122) further computes a benchmark optimal auxiliary power to be consumed by the power plant based on aggregation of the predicted benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106). Such computed data pattern indicates a prediction of the APC for the next day.
In one embodiment, the auxiliary power prediction module (122) performs block-wise prediction of the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) in a predefined time interval of a day, wherein the block-wise prediction aids in executing immediate corrective action on the one or more auxiliary units (106) during the day. In an example, the block-wise prediction is computed in an interval of 15 minutes as for example as illustrated in Figure 8.
In one embodiment, the report generation module (124) is configured to process stored APC information and generate a plurality of statistical information such as group wise predicted APC, minimal APC for a group, filtered historical information etc. as illustrated in Figure 5 and Figure 6. The report generation module (124) retrieves information of minimum power consumed by each of the auxiliary units (106) in each group and respective date of such consumption upon receipt of a request from the user, and displays the retrieved information in the user device (104). The report generation module (124) can automatically generate a graphical representation with historical information of APC by the power plant, wherein the historical information includes auxiliary power consumed by the power plant in same day of the month of previous years like the day of the month of current prediction of APC. An exemplary snapshot has been illustrated in Figure 9.
Further, the report generation module (124) determines information indicating APC of the power plant with minimum and historical average of different dates having similar input conditions like the received input from the user. An exemplary snapshot has been illustrated in Figure 10. The report generation module (124) determines deviation in actual auxiliary power consumed by the auxiliary unit from the predicted benchmark optimal auxiliary power to be consumed by the respective auxiliary unit, and generates probable cause for such deviation based on the analysis of the stored historical information. Figure 12 illustrates an exemplary daily post facto deviation report as generated by the report generation module (124).
The report generation module (124) further generates insights to optimize energy efficiency and operational costs. Implementing such recommendations can contribute to improved overall performance and sustainability. The report generation module (124) generates long-term trends in auxiliary power consumption that provides insights for strategic planning and resource allocation.
In another embodiment, the APPS (102) comprises an optical character recognition module that retrieves information of APC every few seconds by taking video of a display of distributed control system during unavailability of Internet connectivity, and stores the retrieved APC information in the data repository (110).
In one embodiment, the APPS (102) performs the critical analysis of retrieved information by using the analysis engine (220). The analysis engine (220) is configured to analyze information retrieved from the historical information and APC information captured in real time. The pre-trained prediction model of the analysis engine is generated by creating a prediction model based on regression technique that estimates relationship between independent and dependent variables that are extracted upon analysis of the historical power consumption information by the auxiliary units. Further, the analysis engine (220) executes a gradient boosting technique over the regression technique in order to drive fast learning of the prediction model through parallel and distributed computing. The analysis engine (220) performs tuning of hyperparameters such as the Maximum Depth of each Decision Tree, Learning Rate, N Estimators, Minimum Child Weight, and Gamma values of the prediction model in order to further enhance the prediction model. Thereafter, the analysis engine (220) trains the prediction model with a set of training data including independent and dependent variables. The training data is retrieved from the data repository (110) and a process of training the AI model is performed by feeding the training data to the AI model. The training data is processed in one or more phases to prepare a training dataset and a testing dataset, wherein the one or more phases include but not limited to analysis of data, handling missing data, cleansing of data, deciding key factors related to data etc. The training dataset is further split into a plurality of mini batches so that the process of the training can be conducted in a plurality of iterations. Once the AI model receives each of the mini batches as input, the machine learning model initiates the learning from the information contained in each of the mini-batches, wherein the AI model can use one of plurality of learning mechanism such as supervised learning, unsupervised learning etc. The training of the AI model is completed upon processing all the mini-batches. Further, the processor performs testing of the trained AI model using the testing set to ensure desired performance of the AI model. In one embodiment, the AI model can be periodically retrained with an updated set of training data comprising new set of APC information so as to enhance the efficiency of the analysis engine to accurately predict most suitable APC information for the system users.
Figure 3 illustrates a flowchart showing a method of predicting auxiliary power consumption in a power plant in accordance with some embodiments of present disclosure.
As illustrated in Figure 3, the method (300) comprises one or more blocks implemented by the processor (114) for optimizing auxiliary power consumption in a power plant using APPS (102). The method (300) may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract data types.
The order in which the method (300) is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.
At block (302), total export in million units, coal consumption, average temperature, and average relative humidity are received as input from the user. In one embodiment, the data acquisition module (118) receives user input such as total export, coal consumption, average temperature, and average relative humidity. The generation schedule can be one of daily and block-wise. In case of daily prediction, the user input includes total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day. Wherein, in case of block-wise prediction, the user input includes date, block number, block load schedule, block average temperature, block relative humidity, plant load factor, amount of coal consumption. The station for coal consumption indicates the type and quality of the coal that will be used for power generation in next day.
At block (304), historical information with respect to the received input and auxiliary power consumption is retrieved. In one embodiment, the data acquisition module (118) further receives the historical APC information of the auxiliary units (106) from the user and further stores the received information as historical data (208) of the data repository (110). The data processing module (122) further analyzes analyze historical information related to plurality of auxiliary units and determine correlation between the auxiliary units. The data processing module further aids in grouping the auxiliary units based on the determined correlation between the auxiliary units. The one or more auxiliary units (106) are clustered into groups, wherein each group comprises the auxiliary units (106) having maximum extent of interdependence.
At block (306), benchmark optimal auxiliary power to be consumed by the plurality of auxiliary units is predicted. In an embodiment, the data processing module (122) determines correlation of each group of auxiliary units (106) and each of the one or more input parameters as received from the user based on analysis of the historical power consumption information by a pre-trained prediction model of the analysis engine (220). The auxiliary power prediction module (122) analyzes user input and predict auxiliary power consumption of a power plant based on the historical information. The auxiliary power prediction module (122), upon receipt of the user input, analyses the historical APC information and computes a suitable data pattern corresponding to the user input by using the analysis engine (220). The auxiliary power prediction module (122) predicts the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) by the pre-trained prediction model based on the determined correlation between the respective auxiliary unit and the one or more input parameters. The auxiliary power prediction module (122) further computes a benchmark optimal auxiliary power to be consumed by the power plant based on aggregation of the predicted benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106). Such computed data pattern indicates a prediction of the APC for the next day. In one embodiment, the auxiliary power prediction module (122) performs block-wise prediction of the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) in a predefined time interval of a day, wherein the block-wise prediction aids in executing immediate corrective action on the one or more auxiliary units (106) during the day.
At block (308), predicted benchmark information is dynamically represented. In one embodiment, the report generation module (124) is configured to process stored APC information and generate a plurality of statistical information such as group wise predicted APC, minimal APC for a group, filtered historical information etc. The report generation module (124) retrieves information of minimum power consumed by each of the auxiliary units (106) in each group and respective date of such consumption upon receipt of a request from the user, and displays the retrieved information in the user device (104). The report generation module (124) can automatically generate a graphical representation with historical information of APC by the power plant, wherein the historical information includes auxiliary power consumed by the power plant in same day of the month of previous years like the day of the month of current prediction of APC.
Further, the report generation module (124) determines information indicating APC of the power plant with minimum and historical average of different dates having similar input conditions like the received input from the user. The report generation module (124) determines deviation in actual auxiliary power consumed by the auxiliary unit from the predicted benchmark optimal auxiliary power to be consumed by the respective auxiliary unit, and generates probable cause for such deviation based on the analysis of the stored historical information. The report generation module (124) further generates insights to optimize energy efficiency and operational costs. Implementing such recommendations can contribute to improved overall performance and sustainability. The report generation module (124) generates long-term trends in auxiliary power consumption that provides insights for strategic planning and resource allocation. The report generation module (124) further generates insights to optimize energy efficiency and operational costs.
Figure 4 is a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.
The operating environment (400) illustrates various components of an example computing system (402) that can be implemented for managing electronic wallet associated with at least two or more user device such as debit card for one customer.
The computing system (402) includes a processing system (404) (e.g., any of microprocessors, controllers, or other controllers) that can process various computer-executable instructions to control the operation of the computing system (402) and to enable techniques for, or in which can be implemented, procurement management. Alternatively or additionally, the computing system (402) can be implemented with any one or combination of hardware elements (406), firmware, or fixed logic circuitry that is implemented in connection with processing and control circuits. Although not shown, the computing system (402) can include a system bus or data transfer system that couples the various components within the device. A system bus can include any one or combination of different bus structures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and/or a processor or local bus that utilizes any of a variety of bus architectures.
The computing system (402) also includes a communication module (408) that enables wired and/or wireless communication of data (e.g., external data). The communication module (408) can be implemented as one or more of a serial and/or parallel interface, a wireless interface, any type of network interface, a modem, or as any other type of communication interface. The communication module (408) provides a connection and/or communication links between the computing system (402) and a communication network by which other electronic, computing, and communication devices communicate data with the computing system (402).
The computing system (402) includes I/O interfaces (410) for receiving and providing data. For example, the I/O interfaces (410) may include one or more of a touch-sensitive input, a capacitive button, a microphone, a keyboard, a mouse, an accelerometer, a display, an LED indicator, a speaker, or a haptic feedback device.
The computing system (402) also includes computer-readable media (412), such as one or more memory devices that enable persistent and/or non-transitory data storage (i.e., in contrast to mere signal transmission), examples of which include random access memory (RAM), non-volatile memory (e.g., any one or more of a read-only memory (ROM), flash memory, EPROM, EEPROM, etc.), and a disk storage device. A disk storage device may be implemented as any type of magnetic or optical storage device, such as a hard disk drive, a recordable and/or rewritable compact disc (CD), any type of a digital versatile disc (DVD).
The computer-readable media (412) provides data storage mechanisms to store various device applications (414), an operating system (416), and memory/storage (418) and any other types of information and/or data related to operational aspects of the computing system (402). For example, an operating system (416) can be maintained as a computer application within the computer-readable media (412) and executed on the processing system (404). The device applications (414) may include a device manager, such as any form of a control application, software application, or signal-processing and control modules. The device applications (414) may also include system components, engines, or managers to implement real time prediction of accurate business lead, such as the APPS (102), the data repository (110). The computing system (402) may also include, or have access to, one or more machine learning systems.
Using the communication module (408), the computing system (402) may communicate via a cloud computing service (cloud) (420) to access a platform (422) having resources (424). In some implementations, the APPS (102), the data repository (110), are located at the resources (424) and are accessed by the computing system (402) via the cloud (420).
The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words "comprising," "having," "containing," and "including," and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.
With respect to the use of substantially any plural and/or singular terms herein, those having skill in the art can translate from the plural to the singular and/or from the singular to the plural as is appropriate to the context and/or application. The various singular/plural permutations may be expressly set forth herein for sake of clarity.
While various aspects and embodiments have been disclosed herein, other aspects and embodiment will be apparent to those skilled in the art.

, Claims:We Claim:
1) A system (100) for predicting auxiliary power consumption (APC) in a power plant, the system comprising:
one or more auxiliary units (106);
one or more energy meters (108) associated with the one or more auxiliary units (106), each energy meter is associated with one auxiliary unit;
one or more user devices (104); and
a processor (114) communicably coupled with the energy meters and a memory, wherein the processor (114) is configured to:
receive total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day as input from a user via a user device (104);
retrieve historical power consumption information of the one or more auxiliary units (106) from a data repository (110);
predict benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units (106) on daily basis based on the received input and the retrieved historical power consumption information by using a pre-trained prediction model; and
dynamically represent the predicted benchmark information in the user device (104) for enabling a user to retrieve desired information related to APC of the power plant.
2) The system (100) as claimed in claim 1, the processor (114) is configured to:
receive historical power consumption information of the auxiliary units (106) from the user via the user device (104); and
store the received historical power consumption information in the data repository (110).
3) The system (100) as claimed in claim 1, wherein the one or more auxiliary units (106) are clustered into groups, wherein each group comprises the auxiliary units (106) having maximum extent of interdependence.
4) The system (100) as claimed in claim 1, wherein the processor (114) is further configured to receive date, block number, block load schedule, block average temperature, block relative humidity, plant load factor, amount of coal consumption as input from the user via the user device (104) in order to perform block-wise prediction of the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) in a predefined time interval of a day, wherein the block-wise prediction aids in executing immediate corrective action on the one or more auxiliary units (106) during the day.
5) The system (100) as claimed in claim 1, wherein the processor (114) is configured to predict the benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units (106) by:
determining correlation of each group of auxiliary units (106) and each of the one or more input parameters as received from the user based on analysis of the historical power consumption information by the pre-trained prediction model;
predicting the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) by the pre-trained prediction model based on the determined correlation between the respective auxiliary unit and the one or more input parameters; and
computing a benchmark optimal auxiliary power to be consumed by the power plant based on aggregation of the predicted benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106).
6) The system (100) as claimed in claim 1, wherein the processor (114) is configured to generate pre-trained prediction model by:
creating a prediction model based on regression technique that estimates relationship between independent and dependent variables that are extracted upon analysis of the historical power consumption information by the auxiliary units (106);
executing a gradient boosting technique over the regression technique in order to drive fast learning of the prediction model through parallel and distributed computing;
performing tuning of hyperparameters such as the Maximum Depth of each Decision Tree, Learning Rate, N Estimators, Minimum Child Weight, and Gamma values of the prediction model in order to further enhance the prediction model; and
training the prediction model with a set of training data including independent and dependent variables.
7) The system (100) as claimed in claim 1, wherein the processor (114) is configured to dynamically represent the predicted benchmark information in the user device (104) by:
retrieving information of minimum power consumed by each of the auxiliary units (106) in each group and respective date of such consumption upon receipt of a request from the user, and displaying the retrieved information in the user device (104);
automatically generating a graphical representation with historical information of APC by the power plant, wherein the historical information includes auxiliary power consumed by the power plant in same day of the month of previous years like the day of the month of current prediction of APC; and
determining information indicating APC of the power plant with minimum and historical average of different dates having similar input conditions like the received input from the user.
8) The system (100) as claimed in claim 1, wherein the processor (114) is configured to determine deviation in actual auxiliary power consumed by the auxiliary unit from the predicted benchmark optimal auxiliary power to be consumed by the respective auxiliary unit, and generate probable cause for such deviation based on the analysis of the stored historical information.
9) The system (100) as claimed in claim 1, wherein the system (100) further comprises an optical character recognition module that retrieves information of APC every few seconds by taking video of a display of distributed control system during unavailability of Internet connectivity, and stores the retrieved APC information in the data repository (110).
10) A method (300) for predicting auxiliary power consumption (APC) in a power plant, the method comprising:
receiving, by a processor (114), total export, projected coal consumption, projected average temperature, and projected relative humidity of the power plant for a particular day as input from a user via a user device (104);
retrieving, by the processor (114), historical power consumption information of the one or more auxiliary units (106) from a data repository (110);
predicting, by the processor (114), benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units (106) on daily basis based on the received input and the retrieved historical power consumption information by using a pre-trained prediction model; and
dynamically representing, by the processor (114), the predicted benchmark information in the user device (104) for enabling a user to retrieve desired information related to APC of the power plant.
11) The method (300) as claimed in claim 9, wherein the method further comprises the steps of:
receiving historical power consumption information of the auxiliary units (106) from the user via the user device (104); and
storing the received historical power consumption information in the data repository (110).
12) The method (300) as claimed in claim 9, wherein the one or more auxiliary units (106) are clustered into groups, wherein each group comprises the auxiliary units (106) having maximum extent of interdependence.
13) The method (300) as claimed in claim 9, wherein the method comprises the step of:
receiving date, block number, block load schedule, block average temperature, block relative humidity, plant load factor, amount of coal consumption as input from the user via the user device (104) in order to perform block-wise prediction of the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) in a predefined time interval of a day, wherein the block-wise prediction aids in executing immediate corrective action on the one or more auxiliary units (106) during the day.
14) The method (300) as claimed in claim 9, wherein the benchmark optimal auxiliary power to be consumed by each of the one or more auxiliary units (106) is predicted by:
determining correlation of each group of auxiliary units (106) and each of the one or more input parameters as received from the user based on analysis of the historical power consumption information by the pre-trained prediction model;
predicting the benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106) by the pre-trained prediction model based on the determined correlation between the respective auxiliary unit and the one or more input parameters; and
computing a benchmark optimal auxiliary power to be consumed by the power plant based on aggregation of the predicted benchmark optimal auxiliary power to be consumed by each of the auxiliary units (106).
15) The method (300) as claimed in claim 9, wherein the pre-trained prediction model is generated by:
creating a prediction model based on regression technique that estimates relationship between independent and dependent variables that are extracted upon analysis of the historical power consumption information by the auxiliary units (106);
executing a gradient boosting technique over the regression technique in order to drive fast learning of the prediction model through parallel and distributed computing;
performing tuning of hyperparameters such as the Maximum Depth of each Decision Tree, Learning Rate, N Estimators, Minimum Child Weight, and Gamma values of the prediction model in order to further enhance the prediction model; and
training the prediction model with a set of training data including independent and dependent variables.
16) The method (300) as claimed in claim 9, wherein the predicted benchmark information is dynamically represented in the user device (104) upon:
retrieving information of minimum power consumed by each of the auxiliary units (106) in each group and respective date of such consumption upon receipt of a request from the user, and displaying the retrieved information in the user device (104);
automatically generating a graphical representation with historical information of APC by the power plant, wherein the historical information includes auxiliary power consumed by the power plant in same day of the month of previous years like the day of the month of current prediction of APC; and
determining information indicating APC of the power plant with minimum and historical average of different dates having similar input conditions like the received input from the user.
17) The method (300) as claimed in claim 9, wherein deviation in actual auxiliary power consumed by the auxiliary unit from the predicted benchmark optimal auxiliary power to be consumed by the respective auxiliary unit is determined, and probable cause for such deviation is generated based on the analysis of the stored historical information.