Base station power optimization method, system, computer storage medium and electronic device

Abstract

The application provides a base station power optimization method, system, computer storage medium and electronic equipment, relates to the technical field of wireless communication optimization, and generates a signal coverage index by measuring the signal strength and receiving power of a receiving end in a target base station service area, and calculates a signal quality index in combination with the signal strength and channel quality indication of an interference area. Meanwhile, a device load index is generated by counting the base station resource utilization rate, the number of connected user equipment and the equipment operating power. A prediction model is constructed to predict the reference signal receiving power, the received signal strength, the inter-area interference ratio, the channel quality indication, the resource utilization rate, the number of user equipment and the base station equipment operating power based on the base station power; the target function value is calculated based on the signal comprehensive evaluation index and the device load index, and the maximum target function value is taken as the target, and the base station power is optimized by using the simulated annealing algorithm, so that the device load is balanced while the signal coverage and quality are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication optimization, in particular to a base station power optimization method, system, computer storage medium and electronic device. BACKGROUND

[0002] In a mobile communication network, base station power control is one of the important factors affecting network performance. The transmission power of the base station directly affects the signal coverage, signal quality and interference between users. Traditional power control methods usually rely on fixed parameter settings or simple power gain adjustments, lacking the ability to adapt to real-time dynamic changes in the network, resulting in problems such as insufficient signal coverage, significant signal interference and low resource utilization, which in turn affect user experience and overall network performance. In addition, with the rapid growth of mobile devices, the load and energy consumption of base stations are gradually increasing. Therefore, it is an important research direction to reduce energy consumption while ensuring network performance. Therefore, it is urgent to propose a dynamic base station power optimization method based on real-time network state, which balances the load and energy consumption of the base station while improving the signal range and quality.

[0003] In the prior art, the publication number CN117349993A discloses a base station power optimization method, device, computer storage medium and electronic device. The base station transmission power is input to the wireless signal distribution model to generate corresponding regional signal strength data. The base station transmission power, regional signal strength data and other communication scenario parameters are input into a multi-objective optimization algorithm. According to the optimization target of the maximum regional signal strength data and the minimum base station transmission power, a plurality of Pareto solutions are obtained. A most suitable Pareto solution is selected as a result and sent to the base station. The base station adjusts the current power according to the result.

[0004] The main problem of the above method is that only the strength of the regional signal is considered, and other parameters such as signal interference and device load are ignored. The optimization target is relatively single, resulting in insufficient comprehensive consideration of the final base station power optimization

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] The purpose of the present application is to provide a base station power optimization method, system, computer storage medium and electronic device to solve the problems raised in the background technology.

[0007] To achieve the above purpose, the present application provides the following technical solutions:

[0008] A base station power optimization method, the specific steps include:

[0009] Step 1: Select multiple measurement time periods, for each measurement time period, select a target receiving area served by a target base station, obtain the reference signal receiving power and the received signal strength according to the reporting information of the receiving end in the target receiving area, the receiving end being a user equipment connected to the target base station in the target receiving area, and generate a signal coverage index based on the reference signal receiving power and the received signal strength.

[0010] Step 2: Select other areas that reuse the same frequency as the target receiving area within the service range of the target base station, set as interference areas, obtain the received signal strength of all interference areas to generate interference strength, generate an inter-area interference ratio based on the interference strength and the received signal strength of the target area, obtain a channel quality indicator based on the reporting information of the receiving end of the target area, and generate a signal quality index based on the inter-area interference ratio and the channel quality indicator.

[0011] Step 3: Count the total number of physical resource blocks of the target base station, and collect the number of allocated physical resource blocks in the base station within the measurement time period to generate a resource utilization rate, and simultaneously obtain the number of user equipments using the base station resources for data transmission and the running power of the base station equipment within the measurement time period, and generate an equipment load index based on the resource utilization rate, the number of user equipments and the running power of the base station equipment.

[0012] Step 4: Based on the deep learning network construction model, taking the base station power as the input, the reference signal receiving power and the received signal strength as the label, a signal coverage prediction model is constructed, taking the base station power as the input, the inter-area interference ratio and the channel quality indicator as the label, a signal quality prediction model is constructed, taking the base station power as the input, the resource utilization rate, the number of user equipments and the running power of the base station equipment as the label, a load prediction model is constructed.

[0013] Step 5: Based on the signal coverage index, the signal quality index and the equipment load index, the target function value of the base station power is calculated, and the maximum of the target function value is taken as the optimization target, and the current power of the target base station is optimized combined with the simulated annealing algorithm and the prediction model.

[0014] Further, the formula for generating the signal coverage index is

[0015]

[0016] wherein, represents the signal coverage index, represents the weight coefficient of the reference signal receiving power, represents the proportion factor, represents the reference signal power, represents the normalization of by the hyperbolic tangent function, a weight coefficient representing received signal strength, a scaling factor, received signal strength, logarithmic smoothing of received signal strength, , and .

[0017] Further, the principle for generating the signal quality index is:

[0018] The formula for generating the inter-zone interference ratio is:

[0019]

[0020]

[0021] wherein, inter-zone interference ratio, interference strength, the inter-zone interference ratio of the interference zone, the received signal strength of the interference zone, an index of the interference zone, and , the number of interference zones;

[0022] The formula for generating the signal quality index is:

[0023]

[0024] wherein, signal quality index, weight coefficient of the inter-zone interference ratio, the maximum inter-zone interference ratio among all interference zones within the service range of the target base station, weight coefficient of the channel quality indicator, channel quality indicator, , and .

[0025] Further, the principle for generating the device load index is:

[0026]

[0027] wherein, device load index, the number of allocated physical resource blocks, total number of physical resource blocks, a number of user equipments using base station resources for data transmission in a measurement time period, a maximum number of user equipments that the base station can support, a running power of the base station equipment in the measurement time period, a maximum running power of the base station equipment, weight coefficients of the number of physical resource blocks, the number of user equipments and the running power of the base station equipment, respectively, and .

[0028] Further, the principle for generating the target function value is that:

[0029] The formula for generating the signal comprehensive evaluation index is:

[0030]

[0031] wherein, the signal comprehensive evaluation index, the signal coverage index, the signal quality index, weight coefficients of the signal coverage index, the signal quality index and the interaction term of the signal coverage index and the signal quality index, respectively, , and ;

[0032] The formula for generating the target function value is:

[0033]

[0034] wherein, the target function value, the equipment load index.

[0035] Further, the principle for optimizing the base station power is that:

[0036] the range of the base station power is taken as a constraint condition to optimize the base station power, wherein, the minimum base station power, the maximum base station power, when a round of optimization of the base station power is performed based on the simulated annealing algorithm, the base station power before optimization is calibrated as , the corresponding annealing temperature is , the target function value is The formula for optimizing the base station power is:

[0037]

[0038] wherein, Popt represents the optimized base station power, represents an adjustment coefficient, and , represents an adjustment step;

[0039] Pnew represents a new solution, Popt represents the corresponding , when , directly accept ;

[0040] when , accept the new solution with a probability ;

[0041] After each calculation of a new solution, the annealing temperature is reduced, and the formula for reducing the annealing temperature is:

[0042]

[0043] wherein, Popt represents the reduced annealing temperature after optimization, represents a decay coefficient, and ;

[0044] When the annealing temperature is reduced to or less, the calculation is stopped, and the current solution is output, and the corresponding base station power is the optimized base station power.

[0045] The application also provides a base station power optimization system, which is used to execute the above-mentioned base station power optimization method, and specifically comprises:

[0046] A signal measurement module is configured to select a plurality of measurement time periods, select a target receiving area served by a target base station for each measurement time period, obtain reference signal received power and received signal strength according to the reporting information of the receiving end of the target receiving area, generate a signal coverage index based on the reference signal received power and the received signal strength, and the receiving end is a user equipment connected to the target base station in the target receiving area;

[0047] An interference calculation module is configured to select other areas that reuse the same frequency as the target receiving area within the service range of the target base station, set the other areas as interference areas, obtain the received signal strength of all the interference areas to generate interference strength, generate an inter-area interference ratio based on the interference strength and the received signal strength of the target area, obtain a channel quality indicator based on the reporting information of the receiving end of the target area, and generate a signal quality index based on the inter-area interference ratio and the channel quality indicator;

[0048] The load measurement module is used for counting the total number of physical resource blocks of the target base station, collecting the number of allocated physical resource blocks in the base station in a measurement time period, generating resource utilization, simultaneously acquiring the number of user equipment using the base station resource for data transmission in the measurement time period and the running power of the base station equipment, and generating the equipment load index based on the resource utilization, the number of user equipment and the running power of the base station equipment.

[0049] The model construction module is used for constructing a model based on a deep learning network, taking the base station power as the input, the reference signal receiving power and the received signal strength as the label, constructing a signal coverage prediction model, taking the base station power as the input, the inter-area interference ratio and the channel quality indicator as the label, constructing a signal quality prediction model, taking the base station power as the input, the resource utilization, the number of user equipment and the running power of the base station equipment as the label, and constructing a load prediction model.

[0050] The comprehensive optimization module is used for calculating the target function value of the base station power based on the signal coverage index, the signal quality index and the equipment load index, taking the maximization of the target function value as the optimization target, combining the simulated annealing algorithm and the prediction model, and optimizing the current power of the target base station.

[0051] The application further provides a computer storage medium, which stores a computer program, and controls the computer storage medium to execute the base station power optimization method when the computer program runs.

[0052] The application further provides an electronic device, which comprises at least one processor and a memory connected with the processor, the memory is used for storing a computer program or instructions, and the processor is used for executing the computer program or instructions, so that the electronic device realizes the base station power optimization method.

[0053] Compared with the prior art, the application has the following beneficial effects:

[0054] The application evaluates the signal coverage of the target base station by using the reference signal received power and the received signal strength reported by the user equipment in the target receiving area, and evaluates the current signal effect from the signal coverage; selects the interference area, and quantifies the influence of the interference on the signal quality of the target area based on the signal strength of the target area and the inter-area interference ratio, generates the signal quality index from two dimensions of interference strength and channel quality, evaluates the current signal effect from the signal strength, comprehensively considers the physical layer condition of the link and the actual perception of the user, is more comprehensive compared with a single index, generates the signal comprehensive evaluation index based on the signal coverage index and the signal quality index, reflects the signal coverage on one hand and the quality and strength of the signal on the other hand, avoids one-sidedness of a single index, balances the coverage and the signal strength, more accurately reflects the overall performance of the signal, and makes the optimization result closer to the real situation.

[0055] The application also generates the target function value by combining the signal comprehensive evaluation index and the device load, realizes the global balance between the signal performance and the network load, avoids resource waste or performance decline caused by separate optimization of a certain aspect, and quickly optimizes the base station power configuration by means of the simulated annealing algorithm, balances the multi-dimensional performance index, and is more significant and comprehensive in optimization effect, and is more suitable for complex actual communication environment. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 The figure is a flowchart of the embodiment method of the application;

[0057] Figure 2 The figure is a schematic diagram of the system module of the embodiment of the application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the application clearer and more apparent, the application is further described in detail below with reference to specific embodiments.

[0059] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the application should be understood as the general meaning understood by those skilled in the art to which the application belongs. The "first", "second" and similar words used in the application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the words cover the elements or objects listed after the words and their equivalents, and do not exclude other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationship, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0060] Embodiment:

[0061] Please refer to Figure 1 , the present application provides a technical solution:

[0062] A base station power optimization method, the specific steps include:

[0063] Step 1: select a plurality of measurement time period, for each measurement time period, select the target receiving area served by the target base station, according to the receiving end of the target receiving area report information, get reference signal received power and received signal strength, based on reference signal received power and received signal strength to generate signal coverage index, the receiving end is connected to the target base station in the target receiving area user equipment;

[0064] In this embodiment, the formula for generating signal coverage index is

[0065]

[0066] Among them, indicates the signal coverage index, indicates the weight coefficient of reference signal received power, indicates the proportion factor, indicates the reference signal power, indicates the normalization of by hyperbolic tangent function, indicates the weight coefficient of received signal strength, indicates the scaling factor, indicates the received signal strength, indicates the logarithmic smoothing of received signal strength, , and .

[0067] The signal coverage index reflects the performance of the signal sent by the base station in the coverage range, the higher the signal coverage index, the wider the signal coverage range, and the higher the signal quality, wherein the reference signal received power is the main index of the signal coverage index, which is the power of the signal received by the receiving end user equipment, and the reference signal power received by different receiving end user equipment is different, the average value of the reference signal power received by all user equipment in the target receiving area is taken as , which is obtained by extracting the report information of the receiving end, reflecting the coverage range of the base station signal strength; the reference signal received power is nonlinearly transformed, and the range is normalized to interval, to avoid the great influence of extreme data on the result, and the formula for normalization by hyperbolic tangent function is:

[0068]

[0069] wherein, represents a scaling factor, ranging from to , the greater the value of , the more sensitive to the change of , the smaller the value of , the more smooth to the change of , here ;

[0070] The received signal strength is taken as the secondary index, reflecting all the signal strength received by the user equipment at the receiving end, including the signal sent by the base station and the noise, and the signal strength received by different user equipment at the receiving end is different. The average value of the received signal strength of all user equipment in the target receiving area is taken as , which reflects the coverage of the signal and indirectly reflects the environmental factors such as noise interference, and is a supplement to the reference signal received power. The data range of the received signal strength is wide, so the logarithmic transformation is used for compression to avoid the high value area covering the low value area, and the scaling factor is used to adjust the influence range of the received signal strength, and is taken to avoid too flat data gradient. The weight coefficients of the reference signal received power and the received signal strength are respectively: , .

[0071] Step 2: Select other areas with the same frequency as the target receiving area in the service range of the target base station, set as interference areas, obtain the received signal strength of all interference areas to generate interference strength, generate inter-area interference ratio based on the interference strength and the received signal strength of the target area, obtain channel quality indicator based on the reporting information of the receiving end of the target area, and generate signal quality index based on the inter-area interference ratio and the channel quality indicator;

[0072] In this embodiment, the principle for generating the signal quality index is:

[0073] The formula for generating the inter-area interference ratio is:

[0074]

[0075]

[0076] wherein, represents the inter-area interference ratio, represents the interference strength, represents the inter-area interference ratio of the th interference area, represents the inter-area interference ratio of the reception signal strength of the interference region, an index representing the interference region, and , a number representing the interference region;

[0077] When two regions reuse the same frequency, their signals will superimpose at the receiving end, causing interference, which is specifically embodied in that the receiving end cannot distinguish the signals of the target receiving region and the interference region and cannot correctly decode the signals. When the regions use different frequencies, their signals are isolated from each other in frequency and do not directly cause interference. At this time, the interference is embodied as noise. The sum of the reception signal strengths of the interference regions is the total interference strength caused to the target region. The inter-region interference ratio is directly proportional to the reception signal strength of the interference region and inversely proportional to the reception signal strength of the target region.

[0078] The formula on which the signal quality index is generated is:

[0079]

[0080] Among them, the signal quality index, a weight coefficient of the inter-region interference ratio, the maximum inter-region interference ratio in all interference regions served by the target base station, i.e., the maximum , a weight coefficient of the channel quality indication, the channel quality indication, , and .

[0081] The signal quality index reflects the transmission quality of the signal under the influence of noise and channel quality. The higher the signal quality index, the better the signal transmission effect. The inter-region interference ratio reflects the influence of interference on signal quality and is used to measure the relative strength between the signal in the target receiving region and the signals in the surrounding interference regions. The smaller the inter-region interference ratio, the smaller the negative impact on the signal. When the inter-region interference ratio approaches the maximum inter-region interference ratio, the negative impact on the signal approaches the maximum value. The channel quality indication is used to reflect the communication quality of the channel and is reported by the user equipment to the base station according to the current channel condition. The higher the channel quality indication, the stronger the communication ability of the current channel and the better the transmission quality of the signal. When the channel quality is poor, a small amount of improvement in the channel quality will significantly improve the signal quality. When the channel quality is good, the impact of improving the channel quality on the signal quality gradually decreases. Therefore, the logarithmic function is used to represent the relationship between the channel quality and the signal quality. In the transmission process of the signal, the channel quality directly affects the signal quality. Therefore, the weight coefficient of the channel quality indication is high, , .

[0082] Step 3: Count the total number of physical resource blocks of the target base station, collect the number of allocated physical resource blocks in the base station in the measurement time period, generate resource utilization, and at the same time obtain the number of user equipment using the base station resources for data transmission in the measurement time period and the running power of the base station equipment, generate the equipment load index based on the resource utilization, the number of user equipment and the running power of the base station equipment;

[0083] In this embodiment, the principle for generating the equipment load index is:

[0084]

[0085] wherein, represents the equipment load index, represents the number of allocated physical resource blocks, represents the total number of physical resource blocks, represents the number of user equipment using the base station resources for data transmission in the measurement time period, represents the maximum number of user equipment that the base station can support, represents the running power of the base station equipment in the measurement time period, represents the maximum running power of the base station equipment, respectively represent the weight coefficients of the number of physical resource blocks, the number of user equipment and the running power of the base station equipment, and .

[0086] The device load index reflects the load of the base station in a period of time, the higher the device load index, the higher the load of the current base station, the worse the overall performance, and the resource utilization reflects whether the spectrum resource of the base station is close to saturation, if the resource utilization is high, it means that the scheduling resource of the base station is close to the limit, and there is load pressure, and the resource utilization is proportional to the load pressure; the actual number of user equipment and the maximum number of user equipment that the base station can support reflect whether the base station is close to the upper limit of user access, close to the upper limit of user access, which leads to the decrease of the scheduling efficiency of the base station, and increases the device load; the running power of the base station equipment represents the total power of all devices of the base station in normal work, which is related to the resource used by the base station, and when the running power is close to the upper limit, it reflects that the base station bears a large running load; the physical resource block is the core capacity of the base station, and the base station completes the transmission and scheduling of user data by allocating physical resource blocks, and when the resource blocks are exhausted, the base station cannot provide services, therefore, the weight coefficient of the resource utilization is the highest; the base station needs to dynamically schedule resource blocks according to the number of user equipment, the more the users, the higher the complexity of scheduling, and the higher the load of the base station, the increase of the number of user equipment will not directly lead to the exhaustion of the base station resources, and the base station can alleviate the pressure brought by the increase of the number of users by taking appropriate scheduling measures, therefore, the weight coefficient is lower than that of the resource utilization; the increase of the running power of the base station equipment is usually indirectly caused by the resource occupation or the increase of the number of users, and the high or low of the running power of the base station equipment reflects the energy consumption pressure of the base station, although it will increase the operation cost, but it does not directly affect the service quality, therefore, the weight coefficient of the running power of the base station equipment is the lowest, in summary, , , .

[0087] Step 4: based on the deep learning network, a model is constructed, taking the base station power as the input, the reference signal receiving power and the received signal strength as the label, a signal coverage prediction model is generated, taking the base station power as the input, the inter-area interference ratio and the channel quality indicator as the label, a signal quality prediction model is generated, taking the base station power as the input, the resource utilization, the number of user equipment and the running power of the base station equipment as the label, a load prediction model is generated;

[0088] In this embodiment, the deep learning network structure for constructing the signal coverage prediction model is as follows:

[0089] The input layer includes 1 neuron for inputting the base station power;

[0090] The first hidden layer includes 64 neurons, which are activated by using the ReLU activation function;

[0091] The second hidden layer includes 32 neurons, which are activated by using the ReLU activation function;

[0092] Output layer: contains 2 neurons for outputting reference signal received power and received signal strength;

[0093] The deep learning network structure for constructing the signal quality prediction model is as follows:

[0094] Input layer: contains 1 neuron for inputting base station power;

[0095] First hidden layer: contains 64 neurons, activated by ReLU activation function;

[0096] Second hidden layer: contains 32 neurons, activated by ReLU activation function;

[0097] Output layer: contains 2 neurons for outputting inter-area interference ratio and channel quality indicator;

[0098] The deep learning network structure for constructing the load prediction model is as follows:

[0099] Input layer: contains 1 neuron for inputting base station power;

[0100] First hidden layer: contains 64 neurons, activated by ReLU activation function;

[0101] Second hidden layer: contains 32 neurons, activated by ReLU activation function;

[0102] Output layer: contains 3 neurons for outputting resource utilization, number of user equipment and base station equipment running power.

[0103] Step 5: Based on the signal coverage index, signal quality index and device load index, the target function value of the base station power is calculated, and the current power of the target base station is optimized by maximizing the target function value as the optimization objective, combined with the simulated annealing algorithm and the prediction model.

[0104] In this embodiment, the principle for generating the target function value is as follows:

[0105] The formula for generating the signal comprehensive evaluation index is as follows:

[0106]

[0107] Wherein, represents the signal comprehensive evaluation index, represents the signal coverage index, represents the signal quality index, respectively represent the weight coefficients of the signal coverage index, the signal quality index and the interaction term of the signal coverage index and the signal quality index, , and ;

[0108] The signal comprehensive evaluation index reflects the comprehensive performance of the base station in two dimensions of signal coverage and signal quality, The higher the value is, the wider the coverage of the base station is, The higher the value is, the better the signal transmission quality of the base station is, and the interaction term reflects the synergistic effect of signal coverage and signal quality, and the purpose is to capture the case where signal coverage and signal quality are good at the same time. In the actual optimization process, the coverage and quality of the signal should be considered, and therefore , the interaction term is a supplement to the first two terms, and therefore the weight coefficient is relatively low, , .

[0109] The formula for generating the target function value is:

[0110]

[0111] wherein, represents the target function value, represents the device load index.

[0112] The principle for optimizing the base station power is:

[0113] The base station power range is taken as a constraint condition to optimize the base station power, wherein, represents the minimum power of the base station, represents the maximum power of the base station. When a round of optimization is performed on the base station power based on the simulated annealing algorithm, the base station power before optimization is calibrated as , the corresponding annealing temperature is , and the target function value is The formula for optimizing the base station power is:

[0114]

[0115] wherein, represents the optimized base station power, represents the adjustment coefficient, and , represents the adjustment step;

[0116] The corresponding is calculated, when , the is directly accepted;

[0117] when , the new solution is accepted with a probability ;

[0118] After each calculation of a new solution, the annealing temperature is reduced, and the formula for reducing the annealing temperature is:

[0119]

[0120] wherein, represents the reduced annealing temperature after optimization, represents the attenuation coefficient, and ;

[0121] When the annealing temperature is reduced to below, the calculation is stopped, and the current solution is output, and the corresponding base station power is the optimized base station power.

[0122] Referring to Figure 2 , the application also provides a base station power optimization system, which is used to implement the above-mentioned base station power optimization method, and specifically comprises:

[0123] a signal measurement module, configured to select a plurality of measurement time periods, for each measurement time period, select a target receiving area served by a target base station, obtain reference signal received power and received signal strength according to the reporting information of the receiving end of the target receiving area, generate a signal coverage index based on the reference signal received power and the received signal strength, and the receiving end is a user equipment connected to the target base station in the target receiving area;

[0124] an interference calculation module, configured to select other areas that reuse the same frequency as the target receiving area within the service range of the target base station, set the other areas as interference areas, obtain the received signal strength of all the interference areas to generate interference strength, generate an inter-area interference ratio based on the interference strength and the received signal strength of the target area, obtain a channel quality indicator based on the reporting information of the receiving end of the target area, and generate a signal quality index based on the inter-area interference ratio and the channel quality indicator;

[0125] a load measurement module, configured to count the total number of physical resource blocks of the target base station, and collect the number of allocated physical resource blocks in the base station within the measurement time period to generate a resource utilization rate, and simultaneously obtain the number of user equipments using the base station resources for data transmission and the running power of the base station equipment within the measurement time period, and generate an equipment load index based on the resource utilization rate, the number of user equipments and the running power of the base station equipment;

[0126] a model construction module, configured to construct a model based on a deep learning network, take the base station power as the input, take the reference signal received power and the received signal strength as the label, construct a signal coverage prediction model, take the base station power as the input, take the inter-area interference ratio and the channel quality indicator as the label, construct a signal quality prediction model, take the base station power as the input, take the resource utilization rate, the number of user equipments and the running power of the base station equipment as the label, and construct a load prediction model;

[0127] The comprehensive optimization module is configured to calculate a target function value of base station power based on a signal coverage index, a signal quality index and a device load index, to optimize a current power of a target base station with a maximum target function value as an optimization target, and to combine a simulated annealing algorithm and a prediction model.

[0128] The application further provides a computer storage medium storing a computer program, which controls the computer storage medium to execute the base station power optimization method when the computer program is run.

[0129] The application further provides an electronic device comprising at least one processor and a memory connected to the processor, wherein the memory is configured to store a computer program or instructions, and the processor is configured to execute the computer program or instructions, so that the electronic device implements the base station power optimization method.

[0130] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the most recent real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0131] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product wholly or partially. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0132] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0133] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for base station power optimization, the method comprising: The specific steps include: Step 1: Selecting a plurality of measurement time periods, for each measurement time period, selecting a target receiving area served by a target base station, obtaining reference signal receiving power and received signal strength according to the reporting information of the receiving end of the target receiving area, generating a signal coverage index based on the reference signal receiving power and the received signal strength, and the receiving end is a user equipment connected to the target base station in the target receiving area; Step 2: Selecting other areas that reuse the same frequency as the target receiving area within the service range of the target base station as interference areas, obtaining the received signal strength of all interference areas to generate interference strength, generating an inter-area interference ratio based on the interference strength and the received signal strength of the target area, obtaining a channel quality indicator based on the reporting information of the receiving end of the target area, and generating a signal quality index based on the inter-area interference ratio and the channel quality indicator; Step 3: Counting the total number of physical resource blocks of the target base station, and collecting the number of physical resource blocks allocated in the base station within the measurement time period to generate resource utilization, and simultaneously obtaining the number of user equipment using base station resources for data transmission and the running power of the base station equipment within the measurement time period, generating an equipment load index based on resource utilization, the number of user equipment and the running power of the base station equipment; Step 4: Based on the deep learning network construction model, taking the base station power as the input, the reference signal receiving power and the received signal strength as the label, constructing a signal coverage prediction model, taking the base station power as the input, the inter-area interference ratio and the channel quality indicator as the label, constructing a signal quality prediction model, and taking the base station power as the input, the resource utilization, the number of user equipment and the running power of the base station equipment as the label, constructing a load prediction model; Step 5: Based on the signal coverage index, the signal quality index and the equipment load index, calculate the target function value of the base station power, maximize the target function value as the optimization goal, combine the simulated annealing algorithm and the prediction model, and optimize the current power of the target base station; The principle for generating the target function value is: The formula for generating the signal comprehensive evaluation index is: ； wherein, represents a signal comprehensive evaluation index, represents a signal coverage index, represents a signal quality index, respectively represent a weight coefficient of the signal coverage index, the signal quality index, and an interaction term of the signal coverage index and the signal quality index, , and ; The formula for generating the target function value is: ； wherein denotes the objective function value, denotes the device load index.

2. The method of claim 1, wherein: The formula for generating the signal coverage index in step 1 is ； wherein denotes a signal coverage index, denotes a weight coefficient for reference signal received power, denotes a scaling factor, denotes a reference signal power, denotes a normalization of by a hyperbolic tangent function, denotes a weight coefficient for received signal strength, denotes a scaling factor, denotes a received signal strength, denotes a logarithmic smoothing of received signal strength, , and .

3. The method of claim 2, wherein: The principle for generating the signal quality index in step 2 is: The formula for generating the inter-area interference ratio is: ； ； wherein, represents an inter-zone interference ratio, represents an interference strength, represents an inter-zone interference ratio of the zone, represents a received signal strength of the zone, represents an index of the interference zone, and , represents a number of interference zones; The formula for generating the signal quality index is: ； wherein denotes a signal quality index, denotes a weight coefficient of an inter-cell interference ratio, denotes a maximum inter-cell interference ratio among all interference areas within a service range of a target base station, denotes a weight coefficient of a channel quality indicator, denotes a channel quality indicator, , and .

4. The method of claim 1, wherein: The principle for generating the equipment load index in step 3 is: ； wherein, denotes a device load index, denotes a number of allocated physical resource blocks, denotes a total number of physical resource blocks, denotes a number of user equipments using base station resources for data transmission within a measurement time period, denotes a maximum number of user equipments supportable by the base station, denotes a running power of the base station device within the measurement time period, denotes a maximum running power of the base station device, denote weight coefficients for the number of physical resource blocks, the number of user equipments and the running power of the base station device, respectively, and .

5. The method of claim 1, wherein: The principle for optimizing the base station power in step 5 is: The base station power range is divided into a plurality of sub-ranges As a constraint condition, the base station power is optimized, wherein, The base station minimum power is represented as Pmin, The base station maximum power is represented as Pmax, and when a round of optimization is performed on the base station power based on a simulated annealing algorithm, the base station power before optimization is calibrated as The corresponding annealing temperature is The objective function value is The formula for optimizing the base station power is: ； wherein, represents the optimized base station power, represents an adjustment coefficient, and , represents an adjustment step. Computing Corresponding When Directly accept ; When the probability accept the new solution; After each calculation of a new solution, the annealing temperature is reduced, and the formula for reducing the annealing temperature is: ； wherein denotes the reduced annealing temperature after optimization, denotes the decay coefficient, and ; When the annealing temperature is reduced to When the following time, stop the calculation, output the current solution, the corresponding base station power is the optimized base station power.

6. A base station power optimization system, characterized by: The system is used to execute the base station power optimization method of any one of claims 1-5, and specifically includes: A signal measurement module is configured to select a plurality of measurement time periods, for each measurement time period, select a target receiving area served by a target base station, obtain reference signal receiving power and received signal strength according to the reporting information of the receiving end of the target receiving area, generate a signal coverage index based on the reference signal receiving power and the received signal strength, and the receiving end is a user equipment connected to the target base station in the target receiving area; The interference calculation module is configured to select other areas that use the same frequency as the target receiving area in the service range of the target base station, set the selected areas as interference areas, obtain the received signal strength of all the interference areas to generate interference strength, generate an inter-area interference ratio based on the interference strength and the received signal strength of the target area, obtain a channel quality indicator based on the reporting information of the receiving end of the target area, and generate a signal quality index based on the inter-area interference ratio and the channel quality indicator; The load measurement module is configured to count the total number of physical resource blocks of the target base station, collect the number of allocated physical resource blocks in the base station within a measurement time period to generate resource utilization, and simultaneously obtain the number of user equipment using the base station resources for data transmission and the operating power of the base station equipment within the measurement time period, and generate an equipment load index based on the resource utilization, the number of user equipment, and the operating power of the base station equipment; The model construction module is configured to construct a signal coverage prediction model based on a deep learning network, with the base station power as the input and the reference signal received power and the received signal strength as the label, construct a signal quality prediction model with the base station power as the input and the inter-area interference ratio and the channel quality indicator as the label, and construct a load prediction model with the base station power as the input and the resource utilization, the number of user equipment, and the operating power of the base station equipment as the label. The comprehensive optimization module is configured to calculate the target function value of the base station power based on the signal coverage index, the signal quality index, and the equipment load index, maximize the target function value as the optimization objective, and combine the simulated annealing algorithm and the prediction model to optimize the current power of the target base station.

7. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which controls the computer storage medium to execute the base station power optimization method of any one of claims 1-5 when the computer program is running.

8. An electronic device, comprising: The electronic device includes at least one processor and a memory connected to the processor, wherein the memory is configured to store a computer program or instructions, and the processor is configured to execute the computer program or instructions to enable the electronic device to implement the base station power optimization method of any one of claims 1-5.

Images