Claims:1. A method for determining an optimal placement position foran antenna of a base station, said method comprising the steps of:
receiving, at a computing device, terrain information for the antenna; and
processing, at the computing device, the received terrain information with a trained neural network and an optimization algorithm to determine the optimal placement position for the antenna.
2. The method of claim 1, wherein the neural network is trained using a neural schema that is trained based on placement information and respective terrain/environment information of one or more already deployed antennas.
3. The method of claim 1, wherein the optimal placement position for the antenna comprises configuration of any or a combination of antenna height, longitude/latitude,antenna orientation, and antenna angle.
4. The method of claim 1, wherein the terrain information is any or a combination of 2D/3D/4D features of a given area/terrain.
5. The method of claim 1, wherein the terrain information is provided in real time to the trained neural network.
6. The method of claim 1, wherein the neural network is trained based on backpropagation, and wherein the optimization algorithm comprises any or a combination ofevolutionary methods, gene expression programming, simulated annealing, expectation-maximization, non-parametric methods, and particle swarm optimization.
7. A system for determining an optimal placement position for an antenna of a base station, said system comprising:
a non-transitory storage device having embodied therein one or more routines operable to facilitate determination of placement position for the antenna; and
one or more processors coupled to the non-transitory storage device and operable to execute the one or more routines, wherein the one or more routines include:
an optimal position determination module, which when executed by the one or more processors, receives terrain information for the antenna, and processes the received terrain information with a trained neural network and an optimization algorithm to determine the optimal placement position for the antenna.
8. The system of claim 7, said system further comprising:
an information receive module, which when executed by the one or more processors, receives placement information and respective terrain/environment information of one or more already deployed antennas in a given area;
a neural schema creation module, which when executed by the one or more processors, creates a neural schema based on the received placement information and respective terrain/environment information of the one or more already deployed antennas; and
a neural network training module, which when executed by the one or more processors, trains the neural network using the created neural schema based on back propagation.
9. The system of claim 7, wherein the optimal placement position for the antenna comprises configuration of any or a combination of antenna height, longitude/latitude, antenna orientation, and antenna angle.
10. The system of claim 7, wherein the terrain information is provided in real time to the trained neural network.
11. The system of claim 7, wherein the information receive module is further configured to receive power profile of the given area, and wherein the neural schema creation module is configured to create the neural schema based on the received power profile.
, Description:FIELD OF THE INVENTION
[0001] The present disclosure relates to antenna of a base station. In particular, present disclosure pertains to a system and method for optimally positioning one or more antennas of a base station for a particular terrain by using neural network(s).

BACKGROUND
[0002] The background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Base station is a stationary point that enables communication among cellular devices on a carrier network. The base station is operatively coupled with an array of antennas to transmit and receive signals between a cellular device and the base station, wherein base station antenna can be of several types e.g. active receiver antennas, directional antennas, omni-directional antennas, multiband antennas, etc. Generally, base station antenna is mounted at a certain height so as to overcome obstacles such as trees, buildings, hills that can stand in between the cellular device and the base station so as to provide maximum coverage to enableefficient communication among the cellular users who are normally at a ground level.
[0004] Installation of antennas is performed in such a way that maximum coverage can be achieved. To achieve this, before actual deployment of base station and antenna, tests are conducted to obtain the area covered by the base station, however, suchtests do not provide actual area coverage and involve extra cost overhead. The costing involves hardware cost, manpower cost, time, effort andother costs that are involved in placing antennas and base stations.
[0005] Withrapid pace of evolution of mobile devices and cellular communication, demand for optimal coverage by antennas of base stationsat lesser cost is increasing.Existing solutions for deploying antennas for base station are very expensive and not optimal. Such solutions also do not involve any sort of simulation or computer based methods to identify optimal placements and require considerable investment to implement.
[0006] FIG. 1illustrates an existing mechanism for antenna placement. As illustrated, drive tests conducted before emergence of 3G/Long-Term Evolution (LTE)102 andminimization of drive tests (MDT) primarily in 3G/LTE 104 provide different types of signal information 106, wherein the signal information 106 includes threshold power, reference signal received power, reference signal received quality, reference signal time difference, received interference power, angle of arrival and signal to noise ratio (SINR). The signal information 106 is eventually used toobtain antenna placementinformation 108. However, such mechanisms are not computer simulated and involve deployment of whole setup of base station and require trying of different permutations of antenna placement to achieve maximum coverage.
[0007] There is therefore a need in the art to use a simulation model (neural network) to determine most optimal position of an antenna of a base station. Also, there is a need to identify optimal antenna placement position in a cost effective way without actual deployment of antenna and base station at a particular site.There is further a need for a model that can identify an optimal position and placement of an antenna by using a neural schema and optimization mechanism, which have been trained on existing terrain and antenna placement.The optimal antenna placement position should be identified in a cost effective way without actual deployment of antenna and base station at a particular site.
[0008] All publications herein are incorporated by reference to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies and the definition of that term in the reference does not apply.
[0009] In some embodiments, the numbers expressing quantities of ingredients, properties such as concentration, reaction conditions, and so forth, used to describe and claim certain embodiments of the invention are to be understood as being modified in some instances by the term “about.” Accordingly, in some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the invention are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements.
[0010] As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.
[0011] The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g. “such as”) provided with respect to certain embodiments herein is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention.
[0012] Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience and/or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all Markush groups used in the appended claims.

OBJECTS OF THE INVENTION
[0013] An object of the present disclosure is to overcome one or more disadvantages associated with conventional systems and methods for optimal placement of antenna of a base station.
[0014] Another object of the present disclosure is to enable reduction of components to be used for placing antenna of a base station.
[0015] Another object of the present disclosure is to reduce cost and time spent by network operators to determine placement of base stations and associated antenna.
[0016] Another object of the present disclosure is to reduce cost to network operators by minimizing number of base stations required to cover a given terrain.
[0017] Another object of the present disclosure is to provide greater coverage of area with a given number of antennas and base stations.
[0018] Another object of the present disclosure is to determine optimum angle and height at which antenna is to be positioned in order to obtain maximum coverage for a particular terrain.
[0019] Another object of the present disclosure is to analyze antenna coverage without actually configuring an antenna at a particular site.
[0020] Another object of the present disclosure is to train a neural network for antenna deployment in complex urban areas.
[0021] Another object of the present disclosure is to maximize coverage and minimizing infrastructuralcosts.

SUMMARY
[0022] The present disclosure relates to an antenna of a base station. In particular, present disclosure pertains to a system and method fordetermining the power plot of an antenna by using a neural network in a given terrain and optimally positioning one or more antennas of a base station for the same terrain by using an optimization algorithm in conjunction with the neural network.
[0023] In an aspect, the present disclosure relates to determination of optimal position for antenna placement of a desired antenna byreceivingantenna placement and terrain/environment information of existing (already configured) one or more antennas of a particular area along with receiving power profile for the given area and for the antenna placement; creating a neural schema to take antenna placement information and terrain information as input and give a power plot for the area as output; training a neural network based on the created neural schema using the antenna placement information, terrain information, and the power plot for the area; and using the trained neural network along with an optimization algorithm to determine optimal position for the desired antenna of a base station based on its respective terrain information. The proposed trained neural network can further be configured to enable determination of power profile for a new configuration of antenna placement in the same terrain or in a new terrain. The proposed method can further include the step of executing the neural network for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0024] In an exemplary aspect, placement information of existing antennas can include any or a combination of antenna height, longitude/latitude, and antenna angle. Terrain information, on the other hand, can include any or a combination of 2D/3D/4D features of a given area, wherein, in an exemplary aspect, the terrain information for the desired antenna can be provided in real time to adjust the optimal height, vertical and azimuthal angles of the antenna.
[0025] In an aspect, neural network can be trained based on backpropagation to generate a power plot andbased on any or a combination ofoptimization methods including, but not limited to, gene expression programming,simulated annealing, expectation-maximization, non-parametric methods and particle swarm optimizationthat could be used to obtain an optimal position for the antenna.In an aspect, the proposed system comprises of a neural network and an optimization algorithm, wherein the trained neural network provides power plot for a given antenna position and terrain data, while the optimization algorithm can use output from the neural network for various positions of the antenna to obtain an optimal position to maximize area coverage, population coverage, or any other parameter for a given terrain.
[0026] The present disclosure therefore creates a neural schema based on antenna placement information of already configured/deployed antennas along with their respective environment/terrain information, and using the created neural schema, trains a neural network using existing information such that the trained neural network can be used in conjunction with an optimization algorithm for a new antenna, process terrain information for the new antenna and output optimal placement configuration (such as height, angle, orientation, location) for the new antenna within the terrain.
[0027] In an aspect, the present disclosure relates to a method for determining an optimal placement position for an antenna of a base station, said method comprising the steps of: receiving, at a computing device, terrain information for the antenna; andprocessing, at the computing device, the received terrain information with a trained neural network and an optimization algorithm to determine the optimal placement position for the antenna.
[0028] In an aspect, the neural network can be trained using a neural schema that is constructed based on placement information and respective terrain/environment information of one or more already deployed antennas. In another aspect, optimal placement position for the antenna comprises configuration of any or a combination of antenna height, longitude/latitude,antenna orientation, and antenna angle. In another aspect, the terrain information can be any or a combination of 2D/3D/4D features of a given area/terrain. In another aspect, the terrain information can be provided in real time to the trained neural network. The neural network can be trained using backpropagation and optimal position for the antenna can be determined by any or a combination of optimization methods, including but not limited to, gene expression programming,simulated annealing, expectation-maximization, non-parametric methods, and particle swarm optimization.
[0029] The present disclosure further relates to a system for determining an optimal placement position for an antenna of a base station, said system comprising:a non-transitory storage device having embodied therein one or more routines operable to facilitate determination of placement position for the antenna; andone or more processors coupled to the non-transitory storage device and operable to execute the one or more routines, wherein the one or more routines include: an optimal position determination module, which when executed by the one or more processors, receives terrain information for the antenna, and processes the received terrain information with a trained neural network to determine the optimal placement position for the antenna.
[0030] In an aspect, the system further comprises: an information receive module, which when executed by the one or more processors, receives placement information and respective terrain/environment information of one or more already deployed antennas for a given area along with receiving power profile for the area and for the antenna placement information; a neural schema creation module, which when executed by the one or more processors, creates a neural schema to take antenna placement information and terrain information as input and give a power plot for the area as output; and a neural network training module, which when executed by the one or more processors, trains the neural network based on the neural schema, the antenna placement information, the terrain information, and the power plot for the area; an optimization module which can run the trained neural network for various positions of the antenna in a given terrain and determine the optimal position of the antenna. In an aspect, the optimization module can be configured to use the trained neural network to determine power profile for a new configuration of antenna placement in the same terrain or in a new terrain, and execute the neural network for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0031] Various objects, features, aspects and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF DRAWINGS
[0032] FIG. 1 illustratesan existing mechanism for antenna placement.
[0033] FIG. 2 illustrates an exemplary block diagram for determining an optimal position for an antenna placementin accordance with embodiments of the present disclosure.
[0034] FIG. 3 illustrates exemplary functional modules of a system for determining an optimal position for antenna placement in accordance with embodiments of the present disclosure.
[0035] FIG. 4 illustrates an exemplary flow diagram depicting steps involved indetermining an optimal position for antenna placementin accordance with an embodiment of the present disclosure.
[0036] FIG. 5 illustrates expected and predicted antenna positions from the trained neural network in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION OF THE INVENTION
[0037] One should appreciate that the disclosed techniques provide many advantages including, but not limited to, efficient communication between local users.
[0038] The following discussion provides many exemplary embodiments of the inventive subject matter. Although each embodiment represents a single combination of inventive elements, the inventive subject matter is considered to include all possible combinations of the disclosed elements. Thus if one embodiment comprises elements A, B, and C, and a second embodiment comprises elements B and D, then the inventive subject matter is also considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed.
[0039] The present disclosure relates to an antenna of a base station. In particular, present disclosure pertains to a system and method for determining the power plot of an antenna by using a neural network in a given terrain and optimally positioning one or more antennas of a base station for the same terrain by using an optimization algorithm in conjunction with the neural network.
[0040] In an aspect, the present disclosure relates to determination of optimal position for antenna placement of a desired antenna byreceiving antenna placement and terrain/environment information of existing (already configured) one or more antennas of a particular area along with receiving power profile for the given area and for the antenna placement; creating a neural schema to take antenna placement information and terrain information as input and give a power plot for the area as output; training a neural network based on the created neural schema, the antenna placement information, terrain information, and the power plot for the area; and using the trained neural network along with an optimization algorithm to determine optimal position for the desired antenna of a base station based on its respective terrain information. The proposed trained neural network can further be configured to enable determination of power profile for a new configuration of antenna placement in the same terrain or in a new terrain. The proposed method can further include the step of executing the neural network for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0041] In an exemplary aspect, placement information of existing antennas can include any or a combination of antenna height, longitude/latitude, and antenna angle. Terrain information, on the other hand, can include any or a combination of 2D/3D/4D features of a given area, wherein, in an exemplary aspect, the terrain information for the desired antenna can be provided in real time to adjust the optimal height, vertical and azimuthal angles of the antenna.
[0042] In an aspect, neural network can be trained based on back propagation to generate a power plot and/or based on any or a combination ofoptimization methods including, but not limited to, gene expression programming,simulated annealing, expectation-maximization, non-parametric methods and particle swarm optimization that could be used to obtain an optimal position for the antenna. In an aspect, the proposed system comprises of a neural network and an optimization algorithm, wherein the trained neural network provides power plot for a given antenna position and terrain data, while the optimization algorithm can use output from the neural network for various positions of the antenna to obtain an optimal position to maximize area coverage, population coverage, or any other parameter for a given terrain.
[0043] The present disclosure therefore creates a neural schema based on antenna placement information of already configured/deployed antennas along with their respective environment/terrain information, and using the created neural schema, trains a neural network using existing information such that the trained neural network can be used in conjunction with an optimization algorithm for a new antenna, process terrain information for the new antenna and output optimal placement configuration (such as height, angle, orientation, location) for the new antenna within the terrain.
[0044] In an aspect, the present disclosure relates to a method for determining an optimal placement position for an antenna of a base station, said method comprising the steps of: receiving, at a computing device, terrain information for the antenna; andprocessing, at the computing device, the received terrain information with a trained neural network and an optimization algorithm to determine the optimal placement position for the antenna.
[0045] In an aspect, the neural network can be trained using a neural schema that is constructed based on placement information and respective terrain/environment information of one or more already deployed antennas. In another aspect, optimal placement position for the antenna comprises configuration of any or a combination of antenna height, longitude/latitude, antenna orientation, and antenna angle. In another aspect, the terrain information can be any or a combination of 2D/3D/4D features of a given area/terrain. In another aspect, the terrain information can be provided in real time to the trained neural network. The neural network can be trained using back propagation and optimal position for the antenna can be determined by any or a combination of optimization methods, including but not limited to, gene expression programming,simulated annealing, expectation-maximization, non-parametric methods, and particle swarm optimization.
[0046] The present disclosure further relates to a system for determining an optimal placement position for an antenna of a base station, said system comprising:a non-transitory storage device having embodied therein one or more routines operable to facilitate determination of placement position for the antenna; andone or more processors coupled to the non-transitory storage device and operable to execute the one or more routines, wherein the one or more routines include: an optimal position determination module, which when executed by the one or more processors, receives terrain information for the antenna, and processes the received terrain information with a trained neural network to determine the optimal placement position for the antenna.
[0047] In an aspect, the system further comprises: an information receive module, which when executed by the one or more processors, receives placement information and respective terrain/environment information of one or more already deployed antennas for a given area along with receiving power profile for the area and for the antenna placement information; a neural schema creation module, which when executed by the one or more processors, creates a neural schema to take antenna placement information and terrain information as input and give a power plot for the area as output; and a neural network training module, which when executed by the one or more processors, trains the neural network based on the neural schema, the antenna placement information, the terrain information, and the power plot for the area; an optimization module which can run the trained neural network for various positions of the antenna in a given terrain and determine the optimal position of the antenna. In an aspect, the optimization module can be configured to use the trained neural network to determine power profile for a new configuration of antenna placement in the same terrain or in a new terrain, and execute the neural network for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0048] FIG. 2 illustrates an exemplary block diagram for determining an optimal position for an antenna placement in accordance with embodiments of the present disclosure. FIG. 2 illustrates an exemplary process for determining an optimal position for antenna placement by using a simulation and/or a neural network. Block 202illustrates obtaining placement information of existing antennas,wherein antenna placement information can include longitude/latitude where one or more existing antennas are configured, height of the one or more antennas, angleof the one or more antennas, and the like, as would be known to people having ordinary skill in the art.
[0049] Block 204 illustrates extracting terrain and/or environment details of the already deployed/existing antennas, wherein the terrain detailscan includesurrounding datasuch as landscape where the existing antennas are configured, and attributes of surrounding area such as of hills/buildings where the existing antennasare deployed. In an aspect, at block 204, terrain details of surrounding area can be extracted along with power profile for a given configuration of antenna in the area.
[0050] Block 206 illustrates that the placement information of existing (already configured/deployed) antennas and therespective terrain/environment information (details) can be used to create a neural schema. In an aspect, the neural schema can be created so as to take antenna placement information and terrain information as input, and give a power plot for the area as output.
[0051] At block 208, a neural network can be trained based on the created neural schema.In an aspect, the neural network can be trained using back propagation. In an aspect, "backward propagation of errors", is configured to train artificial neural networks used in conjunction with an optimization method such as gradient descent, wherein the method calculates gradient of a loss function with respect to all the weights in the network. The gradient can be fed to the optimization method, which, in turn, uses it to update the weights in an attempt to minimize the loss function. Backpropagation requires a known, desired output for each input value in order to calculate the loss function gradient, and is therefore considered to be a supervised learning method, although it is also used in some unsupervised networks such as autoencoders. It is a generalization of the delta rule to multi-layered feedforward networks, made possible by using chain to iteratively compute gradients for each layer. Back propagation requires that the activation function used by the artificial neurons (or "nodes") be differentiable. In another aspect, the proposed neural network can be trained based on the antenna placement information, the terrain information, and the power plot for the area.
[0052] Block 210 is configured to validate the neural network using existing data (antenna placement information and terrain/environment information), wherein the trained neural network can be validated by performing multiple iterations by varying inputs of antenna placement information and/or varying terrain information.
[0053] Block 212 illustrates that the validatedneural network can run on a new/desired terrain to provide optimal position of an antenna to be configured in the new/desired terrain along with other information such as antenna height and vertical antenna angle (between 0 and 90 degrees) and azimuthal antenna angle (between 0 and 360 degrees).In an aspect, the trained neural network can be used to determine power profile for a new configuration of antenna placement in the same terrain or in a new terrain. Furthermore, the neural network can be executed for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0054] In an exemplary implementation, any or a combination of neural networks such as dynamic neural network, static neural network, neuro-fuzzy network, and the like, can be utilized to enable the aspects of the invention.In an embodiment, neural network and/or neural schema can be further used along with optimization mechanism (hybrid algorithm) that uses terrain information and antenna placement informationto learnprediction of height and/or angle (vertical and/or azimuthal) of one or more antennas on a base station, which are required to cover the desired/new terrain.
[0055] In an embodiment, optimization mechanism can include, but is not limited to, a genetic algorithm, simulated annealing, local optima, global optima seeker and the like that can enable aspects of the disclosure.
[0056] In an exemplary implementation, neural network can be trained by using any ora combination of mechanisms, including but not limited to, evolutionary methods, gene expression programming,simulated annealing, expectation-maximization, non-parametric methods, particle swarm optimization, and the like, that can enable aspects of the present disclosure.
[0057] In an exemplary implementation, more number of varying inputsof antenna placement information for a given terrain can be provided to validate neural network and hence make the determined antenna position more optimal. For example, inputs can be varied as increasing height but keeping terrain parameters constant and vice versa. In another example, height as well as terrain parameters can both be varied simultaneously.
[0058] In an exemplary embodiment, new terrain information where an antenna is to be placed can be provided in real time.
[0059] In an exemplary embodiment, 2D/3D/4D features of existing terrain(s) can be used to create neural schema.
[0060] In an exemplary embodiment, neural schema can be used to determine the power profile contour for the base station.
[0061] As one may appreciate, optimal position of antenna can be quantified on various parameters, including but not limited to, population covered, strength of signal over some region, Service Level Agreements, radiations that can be injurious for public health, signal to noise (SNR) ratio, reference signal received quality, received interference power, and the like.
[0062] FIG. 3 illustrates exemplary functional modules of a system for determining an optimal position for antenna placement in accordance with embodiments of the present disclosure.
[0063] In an aspect, the proposed system can include an information receive module 302 configured to receive placement information and terrain information of existing/already deployed antennas across one or more base stations, a neural schema creation module 304configured to create a neural schema based on received antenna placement information and respective terrain information, a neural network training module 306configured to train a neural network, and an optimal position determination module 308configured to determine optimal placement position for an antenna based on terrain/environment information for the antenna.
[0064] In an aspect, information receive module 302 can be configured to receive placement information and respective terrain/environment information of already deployed/existing antennas across one or more base stations and/or across one or more landscapes/terrains/locations. In an exemplary embodiment, terrain information can be extracted from anyterrain database, wherein, one exemplary database can be United States Geological Survey (USGS) and all such databases/sources that provide terrain information are completely in the scope of the present disclosure. In an aspect, a logical table can be generated based on the received information such that, for instance, each row can correspond to an existing antenna and columns can indicate placement information (such as location, orientation, strength, efficiency, among other parameters of the antenna across one or more columns), and terrain/environment information (across one or more columns) for the respective antenna.
[0065] In an aspect, neural schema creation module 304 can be configured to create a neural schema based on the received antenna placement information and terrain information, whereas neural network training module 306 can be configured to train a neural network based on the created neural schema, wherein such training can be performed by using any or a combination of mechanisms including, but not limited to, evolutionary methods, gene expression programming, simulated annealing, expectation-maximization, non-parametric methods, particle swarm optimization, and the like, that can enable the aspects of the present disclosure.
[0066] In an aspect, optimal position determination module 308 can be configured toprovide optimal position of a desired antenna along with other information such as antenna height, longitude/latitude, vertical antenna angle (between 0 and 90 degrees) and azimuthal antenna angle (between 0 and 360 degrees) based on processing of terrain information (for the desired antenna) that is provided as input through the trained neural network. In an aspect, module 308 can be configured to use the trained neural network to determine power profile for a new configuration of antenna placement in the same terrain or in a new terrain, and then execute the neural network for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0067] In an embodiment, optimal antenna position can be displayed in any or a combination of forms such as through graphical depiction, latitude/longitude/angle/orientation values, and chartwise details.
[0068] In an aspect, antenna of the present disclosure can be an RF antenna.
[0069] FIG. 4 illustrates an exemplary flow diagram depicting steps involved indetermining an optimal position for antenna placementin accordance with an embodiment of the present disclosure.In an aspect, the proposed method/flow diagram 400 can include the steps of, at step 402, receiving antenna placement and terrain information for a particular area, along with power profile for the given area and for the antenna placement. The method can further include, at step 404, creating a neural schema to take antenna placement information and terrain information as input and give a power plot for the area as output, and at step 406,training a neural network based on any or a combination of the neural schema, the antenna placement information, the terrain information, and the power plot for the area. The method can further include, at step 408, using the trained neural network to determine power profile for a new configuration of antenna placement in the same terrain or in a new terrain. The method further includes, at step 410, executing the neural network for various antenna configurations to determine optimal positioning of the antenna in the terrain with the help of an optimization algorithm.
[0070] FIG. 5 illustrates expected and predicted antenna positions from trained neural networkin accordance with an embodiment of the present disclosure. To substantiate the principle and working of optimal antenna position determination, after training on USGS terrain data from multiple locations in the United States, expected output (top) and predicted (below) output from the neural network is illustrated. The prediction of optimal antenna position can be further improved by reducing errors where different mechanisms can be employed for reducing errors such as using more varying training examples for neural network training, using different training mechanisms for neural network training,increasing size of input and output layer, and hence increasing resolution of data being parsed and processing generated neural network on a parallel computing unit and/or powerful computing chip such as powerful desktop GPU.
[0071] As used herein, and unless the context dictates otherwise, the term "coupled to" is intended to include both direct coupling (in which two elements that are coupled to each other contact each other) and indirect coupling (in which at least one additional element is located between the two elements). Therefore, the terms "coupled to" and "coupled with" are used synonymously. Within the context of this document terms "coupled to" and "coupled with" are also used euphemistically to mean “communicatively coupled with” over a network, where two or more devices are able to exchange data with each other over the network, possibly via one or more intermediary device.
[0072] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification claims refers to at least one of something selected from the group consisting of A, B, C ….and N, the text should be interpreted as requiring only one element from the group, not A plus N, or B plus N, etc.

ADVANTAGES OF THE INVENTION
[0073] The present disclosure overcomes one or more disadvantages associated with conventional systems and methods for optimal placement of antenna of a base station.
[0074] The present disclosure enables reduction of components to be used for optimal antenna placement.
[0075] The present disclosure reduces cost and time spent by network operators to determine optimal placement of base stations and associated antenna.
[0076] The present disclosure reduces cost to network operators by minimizing number of base stations required to cover a given terrain.
[0077] The present disclosure provides greater coverage of area with a given number of antennas and base stations.
[0078] The present disclosure determines optimum angle and height at which antennas should be positioned in order to obtain maximum coverage given the features of terrain.
[0079] The present disclosure analyzes antenna coverage without actually configuring antenna at a particular site.
[0080] The present disclosure trains a neural network for antenna deployment in complex urban areas.
[0081] The present disclosure enables maximum coverage and minimum infrastructural costs.