Communication base station power management method and system, electronic equipment and product

Abstract

The invention belongs to the technical field of power management, and aims to provide a communication base station power management method and system, electronic equipment and a product. The method comprises the following steps: collecting power supply state parameters of a base station power supply assembly in real time; carrying out load power prediction and generation power prediction on a future specified period according to the historically collected power state parameters to obtain a load power prediction value and a generation power prediction value of the future specified period; taking minimization of energy cost and battery loss as targets, constructing a power supply energy efficiency optimization model according to a load power prediction value and a power generation power prediction value, and solving the power supply energy efficiency optimization model to obtain an optimal solving result so as to obtain a power supply scheduling strategy of a future specified period; and controlling a power supply driving assembly matched with the base station power supply assembly to execute the power supply scheduling strategy so as to realize power supply scheduling of the base station power supply assembly. According to the invention, unified intelligent scheduling of various power supplies in the power supply assembly of the base station can be realized, and the energy distribution and utilization efficiency can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power management, and particularly relates to a power management method, system, electronic device and product for a communication base station. Background Art

[0002] With the full deployment of 5G communication networks and the large-scale access of Internet of Things devices, the number and power consumption load of communication base stations continue to grow, and the stability, intelligence and energy efficiency level of the base station power supply system have increasingly become the focus of attention of operators. At present, most communication base stations adopt a multi-power structure such as commercial power, storage batteries and standby diesel generators to build a power supply system to ensure the continuity of communication services and emergency capabilities. To implement functions such as power switching, battery maintenance and energy consumption monitoring, a power management system is usually configured inside the base station to schedule and control various power sources.

[0003] In the prior art, for example, a base station energy intelligent sharing method, system and control method disclosed in a Chinese patent application with the publication number of CN113258605A controls the switching between the battery pack and commercial power by judging the state of commercial power. When it detects that the commercial power is abnormal, it automatically switches to battery power supply to maintain the operation of the base station, thereby ensuring power supply continuity. However, at least the following problems exist in the above prior art: First, traditional power management systems mostly use threshold values such as voltage, current, and power quantity thresholds for power switching, and cannot adapt to the real-time fluctuations of communication loads and changes in the external environment (such as electricity prices), resulting in low energy distribution efficiency; in addition, in the scenario where multiple heterogeneous power sources such as commercial power, storage batteries and renewable energy are simultaneously connected, the existing scheduling strategies are not intelligent enough, and it is difficult to balance energy consumption costs and battery protection while ensuring communication reliability. Summary of the Invention

[0004] The present invention aims to solve at least to some extent the above technical problems, and provides a power management method, system, electronic device and product for a communication base station.

[0005] To achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a power management method for a communication base station, including: Real-time collecting power status parameters of base station power components; wherein, the base station power components include commercial power, storage batteries and power generation modules; Predicting the load power and power generation power for a future specified period according to the historically collected power status parameters, and obtaining the predicted load power value and predicted power generation power value for the future specified period; Constructing a power energy efficiency optimization model with the goal of minimizing energy cost and battery loss according to the predicted load power value and the predicted power generation power value; Solve the power energy efficiency optimization model to obtain the optimal solution result, and obtain the power scheduling strategy for the future specified period according to the optimal solution result; Control the power drive component matching the base station power component to execute the power scheduling strategy, so as to realize the power scheduling of the base station power component.

[0006] In a possible design, the power state parameters include the power generation power and the communication load power; correspondingly, within the future specified period t +1, t + T , the predicted value of the load power at the future moment t +1 is:

[0007] In the formula, f LSTM1 ( ) represents the load power prediction function, is the communication load power at the historical moment t 、 t -1、…、 t-n , n is the length of the historical time window, T is the length of the future time window; Within the future specified period t +1, t + T , the predicted value of the power generation power at the future moment t +1 is:

[0008] In the formula, f LSTM2 ( ) represents the power generation power prediction function, is the power generation power at the historical moment t 、 t -1、…、 t-n .

[0009] In a possible design, the power energy efficiency optimization model includes an energy efficiency optimization objective function and a constraint function, and the energy efficiency optimization objective function is:

[0010] In the formula, C is the total cost, α is the preset weight of the mains power cost, β is the preset weight of the battery aging cost, γ is the preset loss weight, C g ( t’ ) is the future momentt’ The unit price of the mains power supply P g ( t’ ) is the mains power supply power at the future moment to be solved t’ D bat ( t’ ) is the battery aging loss cost at the future moment t’ , P bat ( t’ ) is the battery power supply power at the future moment to be solved t’ is the coefficient of the unit power on the battery health loss preset H bat ( t’ ) is the battery health state at the future moment t’ L loss ( t’ ) is the power loss at the future moment t’ The constraint function includes a power balance constraint function, a power generation utilization power constraint function, and a battery discharge constraint function. Among them, the power balance constraint function is:

[0011] In the formula, P g ( t’ ) is the mains power supply power at the future moment to be solved t’ P pv ( t’ ) is the power supply power of the power generation module at the future moment to be solved t’ P bat ( t’ ) is the battery power supply power at the future moment to be solved t’ is the predicted value of the load power at the future moment t’ The power generation utilization power constraint function is:

[0012] In the formula, is the predicted value of the power generation power at the future moment t’ The battery discharge constraint function is:

[0013] In the formula, ​​​​​​​​​​is the maximum charge and discharge power of the preset storage battery.

[0014] In a possible design, the power loss is:

[0015] where is the energy conversion efficiency of the preset storage battery, is the energy conversion efficiency of the preset commercial power.

[0016] In a possible design, a mixed integer linear programming algorithm or a reinforcement learning algorithm is used to solve the power supply energy efficiency optimization model.

[0017] In a possible design, the load power prediction and the power generation power prediction are carried out at specified time intervals, and the power supply scheduling strategy for the current prediction period is optimized according to the scheduling execution status of the previous prediction period, so as to realize the closed-loop dynamic scheduling of the base station power supply components.

[0018] In a second aspect, the present invention provides a communication base station power management system, including: A data acquisition module, configured to collect the power status parameters of the base station power supply components in real time; wherein, the base station power supply components include commercial power, a storage battery, and a power generation module; A data prediction module, communicatively connected to the data acquisition module, configured to perform load power prediction and power generation power prediction for a future specified period according to the historically collected power status parameters, and obtain the load power prediction value and the power generation power prediction value for the future specified period; An optimization model construction module, communicatively connected to the data prediction module, configured to construct a power supply energy efficiency optimization model with the goal of minimizing the energy cost and battery loss according to the load power prediction value and the power generation power prediction value; An optimization model solving module, communicatively connected to the optimization model construction module, configured to solve the power supply energy efficiency optimization model, obtain the optimal solution result, and obtain the power supply scheduling strategy for the future specified period according to the optimal solution result; A strategy execution module, communicatively connected to the optimization model solving module, configured to control a power drive component matching the base station power supply components to execute the power supply scheduling strategy, so as to realize the power supply scheduling of the base station power supply components.

[0019] In a third aspect, the present invention provides an electronic device, including: A memory, configured to store computer program instructions; and A processor, configured to execute the computer program instructions to complete the operations of a communication base station power management method as described in any one of the above.

[0020] In a fourth aspect, the present invention provides a computer program product, including a computer program or instructions, and when the computer program or the instructions are executed by a computer, they implement a communication base station power management method as described in any one of the above.

[0021] In a fifth aspect, the present invention provides a computer-readable storage product, on which instructions are stored, and when the instructions run on a computer, they execute a communication base station power management method as described in any one of the above.

[0022] The beneficial effects of the present invention are as follows: The present invention discloses a communication base station power management method, system, electronic device and product, which can realize the unified intelligent scheduling of various power supplies in the base station power supply components, and is conducive to improving the energy distribution and utilization efficiency. In the implementation process of the present invention, the power state parameters of the base station power supply components are collected in real time, and the load power prediction and power generation power prediction are carried out for a future specified period according to the power state parameters collected historically, so as to obtain the load power prediction value and power generation power prediction value for the future specified period; subsequently, with the goal of minimizing the energy cost and battery loss, a power efficiency optimization model is constructed according to the load power prediction value and the power generation power prediction value, and then the power efficiency optimization model is solved to obtain the optimal solution result, and the power scheduling strategy for the future specified period is obtained according to the optimal solution result; finally, the power drive component matching the base station power supply component is controlled to execute the power scheduling strategy, so as to realize the power scheduling of the base station power supply component. Based on this, the present invention is applicable to a communication base station power supply system with commercial power, storage batteries and power generation capabilities. In the implementation process, through load power prediction and power generation power prediction, the power scheduling is converted from passive "responsive" to active "predictive", with high intelligence and higher energy distribution efficiency, which is conducive to improving the stability of subsequent energy distribution, especially significantly improving the system robustness in scenarios with strong load fluctuations and uncertainty of photovoltaic power generation.

[0023] Other beneficial effects of the present invention will be further described in the specific implementation manner. Description of the Drawings

[0024] Figure 1 is a flowchart of a communication base station power management method in an embodiment; Figure 2 is a block diagram of a communication base station power management system in an embodiment; Figure 3 is a block diagram of an electronic device in an embodiment. Specific Implementation Manner

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the present invention in combination with the accompanying drawings and the descriptions of the embodiments or the prior art. Obviously, the following descriptions of the structures of the accompanying drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts. It should be noted here that the descriptions of these embodiments are used to help understand the present invention, but do not constitute a limitation to the present invention.

[0026] Embodiment 1: This embodiment discloses a power management method for a communication base station, which can be, but is not limited to, executed by a computer device or virtual machine with certain computing resources, such as an electronic device like a personal computer, a smart phone, a personal digital assistant, or a wearable device, or executed by a virtual machine.

[0027] As Figure 1 shown, a power management method for a communication base station can, but is not limited to, include the following steps: S1. Real-time collect the power status parameters of the base station power components; wherein, the base station power components include commercial power, storage batteries, and power generation modules.

[0028] S2. Based on the historically collected power status parameters, predict the load power and power generation power for a future specified period (such as the next 1 hour) to obtain the predicted values of the load power and power generation power for the future specified period.

[0029] In this embodiment, the power status parameters include power generation power and communication load power; correspondingly, in step S2, within the future specified period t +1, t + T , the predicted value of the load power at the future time t +1 is:

[0030] In the formula, f LSTM1 ( ) represents the load power prediction function, is the communication load power at historical times t , t -1,..., t-n , n is the length of the historical time window, T is the length of the future time window; Within the future specified period t +1, t + T , the predicted value of the power generation power at the future time t +1 is:

[0031] Wherein, f LSTM2 ( ) represents the power generation power prediction function, is the historical moment t 、 t -1, …, t-n is the power generation power at.

[0032] It should be noted that when performing load power prediction and power generation power prediction, a preset Long Short-Term Memory (LSTM) network is used to construct a load power prediction model and a power generation power prediction function respectively. The prediction model is trained through its corresponding historical data to achieve long-term load power prediction and power generation power prediction.

[0033] S3. With the goal of minimizing energy cost and battery loss, construct a power supply energy efficiency optimization model according to the predicted load power value and the predicted power generation power value.

[0034] In step S3, the power supply energy efficiency optimization model includes an energy efficiency optimization objective function and a constraint function. The energy efficiency optimization objective function is:

[0035] Wherein, C is the total cost, α is the preset weight of the utility cost, β is the preset weight of the battery aging cost, γ is the preset loss weight, C g ( t’ ) is the unit price of the utility at the future moment t’ , provided by the power company, P g ( t’ ) is the power supply power of the utility to be solved at the future moment t’ , D bat ( t’ ) is the battery aging loss cost at the future moment t’ , , P bat ( t’ ) is the battery supply power to be solved at the future moment t’ , is the coefficient of the unit power on the battery health loss, H bat ( t’ ) is the future moment t’The state of health of the battery, which can be set to the latest state of health of the power state parameters collected historically, L loss ( t’ ) is the power loss at a future time t’ ; Specifically, in this embodiment, the power loss is:

[0036] Wherein, is the preset energy conversion efficiency of the storage battery, is the preset energy conversion efficiency of the commercial power.

[0037] The constraint function includes a power balance constraint function, a power utilization constraint function for power generation, and a battery discharge constraint function. Among them, the power balance constraint function is:

[0038] In the formula, P g ( t’ ) is the commercial power supply power to be solved at a future time t’ ; P pv ( t’ ) is the power supply power of the power generation module to be solved at a future time t’ ; P bat ( t’ ) is the battery supply power to be solved at a future time t’ ; is the predicted value of the load power at a future time t’ ; The power utilization constraint function for power generation is:

[0039] In the formula, is the predicted value of the power generation power at a future time t’ ; The battery discharge constraint function is:

[0040] In the formula, is the maximum charge and discharge power of the preset storage battery.

[0041] In this embodiment, the battery discharge constraint function is used to prevent high-power operations when the battery health is low.

[0042] In this embodiment, the energy efficiency optimization objective function is based on the cost of commercial power, battery loss, and power conversion loss. The variables include the commercial power supply power and the battery power supply power, which are used to minimize the comprehensive energy consumption cost. The constraint function is used to limit the actual feasible power range of each power supply path, based on which the physical feasibility and safety of the scheduling strategy can be ensured. Based on this, the power supply energy efficiency optimization model fully considers three objectives: economy, equipment life, and system loss, and can realize the joint scheduling of the three, ensuring power supply and demand balance, giving priority to the utilization of the power generation module, and enabling the battery to operate within the allowable range. During the implementation process, the weights can be flexibly adjusted to adapt to different base station operation strategies, thereby achieving the optimal strategy of power supply control.

[0043] S4. Solve the power supply energy efficiency optimization model to obtain the optimal solution result, and obtain the power supply scheduling strategy for the future specified period according to the optimal solution result.

[0044] The optimization problem in step S3 is a non-linear programming problem with integer constraints. Based on this, in step S4, a mixed integer linear programming (MILP) algorithm or a reinforcement learning algorithm is used to solve the power supply energy efficiency optimization model, which can reduce the need for human intervention and improve the intelligent level of the system.

[0045] Correspondingly, in this embodiment, the optimal solution result obtained by solving the power supply energy efficiency optimization model can be expressed as:

[0046] where, is the optimal commercial power supply power at the future time t’ , P pv ( t’ ) is the optimal power supply power of the power generation module at the future time t’ , P bat ( t’ ) is the optimal battery power supply power at the future time t’ .

[0047] S5. Control the power supply drive component matching the base station power supply component to execute the power supply scheduling strategy, so as to realize the power supply scheduling of the base station power supply component. It should be understood that in this embodiment, the power supply drive component is, for example, a relay or a converter, depending on the type of the base station power supply component.

[0048] In this embodiment, the load power prediction and the power generation power prediction are carried out at specified intervals (such as every 15 minutes), and the power supply scheduling strategy is optimized for the current prediction period according to the scheduling execution status of the previous prediction period, so as to realize the closed-loop dynamic scheduling of the base station power supply component.

[0049] Based on this, in this embodiment, the power supply scheduling strategy can be dynamically adjusted according to multi-dimensional factors such as communication load, electricity price fluctuations, and battery health status, as well as the scheduling execution status in the previous prediction period. If a deviation occurs, the prediction model is dynamically adjusted or the scheduling is re-planned.

[0050] This embodiment provides a communication base station power management solution based on a dynamic load prediction and optimization scheduling mechanism, which can achieve unified intelligent scheduling of various power supplies in the base station power supply components, and is conducive to improving the energy distribution and utilization efficiency. During the implementation of this embodiment, the power status parameters of the base station power supply components are collected in real time, and the load power prediction and power generation power prediction for a future specified period are performed based on the historically collected power status parameters to obtain the load power prediction value and power generation power prediction value for the future specified period; subsequently, with the goal of minimizing energy cost and battery loss, a power supply energy efficiency optimization model is constructed according to the load power prediction value and the power generation power prediction value, and then the power supply energy efficiency optimization model is solved to obtain the optimal solution result, and the power supply scheduling strategy for the future specified period is obtained according to the optimal solution result; finally, the power supply drive component matching the base station power supply component is controlled to execute the power supply scheduling strategy, so as to achieve the power supply scheduling of the base station power supply component. Based on this, this embodiment is applicable to a communication base station power supply system with the capabilities of commercial power, storage battery, and power generation (such as photovoltaic power generation). During the implementation process, through load power prediction and power generation power prediction, the power supply scheduling is converted from passive "responsive" to active "predictive", with high intelligence and higher energy distribution efficiency, which is conducive to improving the stability of subsequent energy distribution, especially significantly improving the system robustness in scenarios with strong load fluctuations and high uncertainty of photovoltaic power generation.

[0051] Embodiment 2: This embodiment discloses a communication base station power management system for implementing the communication base station power management method in Embodiment 1; as Figure 2 shown, the communication base station power management system includes: A data acquisition module, which is used to collect the power status parameters of the base station power supply components in real time; wherein, the base station power supply components include commercial power, storage battery, and power generation module; A data prediction module, which is communicatively connected to the data acquisition module and is used to perform load power prediction and power generation power prediction for a future specified period based on the historically collected power status parameters to obtain the load power prediction value and power generation power prediction value for the future specified period; An optimization model construction module, which is communicatively connected to the data prediction module and is used to construct a power supply energy efficiency optimization model with the goal of minimizing energy cost and battery loss according to the load power prediction value and the power generation power prediction value; An optimization model solving module, communicatively connected to the optimization model building module, is configured to solve the power efficiency optimization model to obtain an optimal solution result, and obtain a power scheduling strategy for the specified future period according to the optimal solution result; A strategy execution module, communicatively connected to the optimization model solving module, is configured to control a power driving component matching the base station power supply component to execute the power scheduling strategy, so as to implement power scheduling for the base station power supply component.

[0052] It should be noted that for the working process, working details and technical effects of the communication base station power management system provided in Embodiment 2, reference can be made to Embodiment 1, which will not be elaborated here.

[0053] Embodiment 3: Based on Embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc. The electronic device may be referred to as a user terminal, a portable terminal, a desktop terminal, etc. As Figure 3 shown, the electronic device includes: A memory, configured to store computer program instructions; and, A processor, configured to execute the computer program instructions to complete the operations of any one of the communication base station power management methods described in Embodiment 1.

[0054] Specifically, the processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen.

[0055] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory, as well as non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 302 is used to store at least one instruction for being executed by the processor 301 to implement the communication base station power management method provided in Embodiment 1 of the present application.

[0056] In some embodiments, the terminal may further optionally include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302, and the communication interface 303 may be connected through a bus or signal lines. Each peripheral device may be connected to the communication interface 303 through a bus, signal lines, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 304, a display screen 305, and a power supply 306.

[0057] The communication interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 may be implemented on a separate chip or circuit board, and the present embodiment does not limit this.

[0058] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with a communication network and other communication devices through electromagnetic signals.

[0059] The display screen 305 is used to display a UI (User Interface). The UI may include any combination of graphics, text, icons, and videos.

[0060] The power supply 306 is used to supply power to each component in the electronic device.

[0061] Embodiment 4: Based on any one of Embodiments 1 to 3, the present embodiment discloses a computer program product, including a computer program or instruction, and the computer program or the instruction, when executed by a computer, implements a communication base station power management method as described in any one of Embodiment 1. Wherein, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0062] Embodiment 5: Based on any one of Embodiments 1 to 3, this embodiment discloses a computer-readable storage product. Instructions are stored on the computer-readable storage product. When the instructions run on a computer, they execute a communication base station power management method as described in any one of Embodiments 1. Among them, the computer-readable storage product refers to a carrier for storing data, and may include, but is not limited to, computer-readable storage media such as floppy disks, optical discs, hard disks, flash memories, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0063] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to be implemented. In this way, the present invention is not limited to any specific combination of hardware and software.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A power management method for a communication base station, characterized in that, Including: Real-time collection of power status parameters of the base station power supply components; wherein, the base station power supply components include commercial power, storage batteries, and power generation modules; Based on the power status parameters collected historically, perform load power prediction and power generation power prediction for a future specified period to obtain the load power prediction value and power generation power prediction value for the future specified period; Taking minimizing energy cost and battery loss as the goal, construct a power efficiency optimization model according to the load power prediction value and the power generation power prediction value; Solve the power efficiency optimization model to obtain the optimal solution result, and obtain the power scheduling strategy for the future specified period according to the optimal solution result; Control the power drive components matching the base station power supply components to execute the power scheduling strategy, so as to realize the power scheduling of the base station power supply components.

2. The power management method for a communication base station according to claim 1, characterized in that, The power state parameters include the power generation power and the communication load power; correspondingly, within the future specified period t +1, t + T , the predicted value of the load power at the future moment t +1 is: Wherein, f LSTM1 ( ) represents the load power prediction function, is the historical moment t 、 t -1, …, t-n the communication load power, n is the historical time window length, T is the future time window length; The future specified period t +1, t + T , the predicted power generation value at the future time t +1 is: In the formula, f LSTM2 ( ) represents the power generation prediction function, is the historical moment t 、 t -1, …, t-n is the power generation of 3. The power management method for a communication base station according to claim 2, characterized in that, The power efficiency optimization model includes an energy efficiency optimization objective function and constraint functions. The energy efficiency optimization objective function is: Wherein, C is the total cost, α is the preset weight of the utility cost, β is the preset weight of the battery aging cost, γ is the preset loss weight, C g ( t’ ) is the unit price of the utility at the future time t’ , P g ( t’ ) is the power supply of the utility to be solved at the future time t’ , D bat ( t’ ) is the battery aging loss cost at the future time t’ , , P bat ( t’ ) is the battery power supply to be solved at the future time t’ , is the coefficient of the unit power on the battery health loss, H bat ( t’ ) is the battery health state at the future time t’ , L loss ( t’ ) is the power loss at the future time t’ ; The constraint functions include a power balance constraint function, a power generation utilization power constraint function, and a battery discharge constraint function. Among them, the power balance constraint function is: Wherein, P g ( t’ ) is the mains power supply at the future time t’ to be solved, P pv ( t’ ) is the power supply of the power generation module at the future time t’ to be solved, P bat ( t’ ) is the battery power supply at the future time t’ to be solved, is the predicted value of the load power at the future time t’ ; The power generation utilization power constraint function is: In the formula, is the predicted power generation value at the future time t’ , The battery discharge constraint function is: In the formula, is the maximum charge-discharge power of the preset storage battery.

4. The power management method for a communication base station according to claim 3, characterized in that, The power loss is: Among them, is the preset energy conversion efficiency of the storage battery, is the preset energy conversion efficiency of the mains power.

5. The power management method for a communication base station according to claim 1, characterized in that, Use a mixed integer linear programming algorithm or a reinforcement learning algorithm to solve the power efficiency optimization model.

6. The power management method for a communication base station according to claim 1, characterized in that, Perform load power prediction and power generation power prediction at specified time intervals, and optimize the power scheduling strategy for the current prediction period according to the scheduling execution status of the previous prediction period, so as to realize the closed-loop dynamic scheduling of the base station power supply components.

7. A power management system for a communication base station, characterized in that, Including: A data collection module for real-time collection of power status parameters of the base station power supply components; wherein, the base station power supply components include commercial power, storage batteries, and power generation modules; A data prediction module, communicatively connected to the data collection module, for performing load power prediction and power generation power prediction for a future specified period based on the power status parameters collected historically, to obtain the load power prediction value and power generation power prediction value for the future specified period; An optimization model construction module, communicatively connected to the data prediction module, for constructing a power efficiency optimization model with the goal of minimizing energy cost and battery loss according to the load power prediction value and the power generation power prediction value; An optimization model solving module, communicatively connected to the optimization model construction module, for solving the power efficiency optimization model to obtain the optimal solution result, and obtaining the power scheduling strategy for the future specified period according to the optimal solution result; A strategy execution module, communicatively connected to the optimization model solving module, for controlling the power drive components matching the base station power supply components to execute the power scheduling strategy, so as to realize the power scheduling of the base station power supply components.

8. An electronic device, characterized in that, Including: A memory for storing computer program instructions; And, A processor for executing the computer program instructions to complete the operations of a communication base station power management method as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or the instructions, when executed by a computer, implement a communication base station power management method as described in any one of claims 1 to 6.

10. A computer-readable storage product, characterized in that, Instructions are stored on the computer-readable storage product, and when the instructions are run on a computer, a communication base station power management method according to any one of claims 1 to 6 is executed.

Images