Energy management method and device for high proportion photovoltaic power distribution area

Abstract

This invention relates to the field of power control technology, and more particularly to an energy management method and apparatus for high-proportion photovoltaic (PV) distribution substations. The invention constructs a cost objective function; the objective of which is to minimize the total construction cost of the high-proportion PV distribution substation while suppressing the impact of PV power output fluctuations and randomness on the power grid. Under the premise of satisfying the energy management constraints of the high-proportion PV distribution substation, a Markov decision model is used to iteratively solve the cost objective function to obtain the minimum operating cost of the high-proportion PV distribution substation. The energy management constraints of the high-proportion PV distribution substation include substation power constraints, energy storage operation constraints, and charging / discharging power constraints. Thus, this invention can maximize the comprehensive benefits of high-proportion PV distribution substations while suppressing the impact of PV power output fluctuations and randomness on the power grid.

Description

Technical Field

[0001] This invention relates to the field of power control technology, and in particular to an energy management method and apparatus for a high-proportion photovoltaic distribution area. Background Technology

[0002] Driven by the dual-carbon strategy, wind and solar power are rapidly replacing traditional fossil fuels. New distributed solar PV capacity reached 52.88 GW, while centralized solar PV power plants added 49.60 GW, with distributed PV accounting for over half and becoming the dominant force driving market growth. However, this high proportion of solar PV integration brings numerous challenges to distribution network operations. Firstly, distributed PV suffers from source-load mismatch, leading to frequent backfeeding of power from distribution areas to the grid. Secondly, the volatility and randomness of solar power generation result in significant fluctuations in the main grid's output. While energy storage devices offer bidirectional energy flow, storing energy when there is a power surplus and releasing it when there is a power shortage, energy storage alone may not be sufficient to handle large discrepancies when the gap between solar power generation and load demand is too large. In such cases, adjusting the power output of solar PV equipment is necessary to mitigate power fluctuations and ensure stable operation of the distribution area.

[0003] Based on this, the present invention proposes an energy management method and device for high-proportion photovoltaic distribution areas to solve the problem of maximizing the comprehensive benefits of high-proportion photovoltaic distribution areas while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid. Summary of the Invention

[0004] To address the challenge of maximizing the overall benefits of high-proportion photovoltaic (PV) distribution areas while mitigating the impact of PV power output fluctuations and randomness on the power grid, this invention provides an energy management method and apparatus for high-proportion PV distribution areas.

[0005] In a first aspect, embodiments of the present invention provide an energy management method for a high-proportion photovoltaic distribution area, comprising: Construct a cost objective function; wherein the objective function aims to minimize the total construction cost of high-proportion photovoltaic power generation areas while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid; Under the premise of meeting the energy management constraints of high-proportion photovoltaic distribution areas, the cost objective function is iteratively solved by calling the Markov decision model to obtain the minimum operating cost of high-proportion photovoltaic distribution areas. The energy management constraints of the high-proportion photovoltaic distribution area include distribution area power constraints, energy storage operation constraints, and charge / discharge power constraints.

[0006] Secondly, embodiments of the present invention provide an energy management device for a high-proportion photovoltaic distribution area, comprising: The first data processing module is used to construct a cost objective function; wherein the objective function aims to minimize the total construction cost of a high-proportion photovoltaic power generation area while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid. The second data processing module is used to call the Markov decision model to iteratively solve the cost objective function under the premise of meeting the energy management constraints of the high-proportion photovoltaic distribution area, so as to obtain the minimum operating cost of the high-proportion photovoltaic distribution area. The energy management constraints of the high-proportion photovoltaic distribution area include distribution area power constraints, energy storage operation constraints, and charge / discharge power constraints.

[0007] Thirdly, embodiments of the present invention also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method described in any embodiment of the present invention.

[0008] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the methods described in any embodiment of the present invention.

[0009] This invention provides an energy management method and apparatus for high-proportion photovoltaic (PV) distribution substations. First, a cost objective function is constructed. This function aims to minimize the total construction cost of the high-proportion PV substation while effectively suppressing the impact of PV power output fluctuations and randomness on the power grid, thus balancing grid stability and economic efficiency. Simultaneously, to ensure the feasibility and security of the energy management scheme, energy management constraints for high-proportion PV distribution substations must be followed. These constraints include substation power constraints, energy storage operation constraints, and charging / discharging power constraints. The substation power constraints regulate power exchange between the substation and the distribution network, preventing excessive backfeeding and voltage exceeding limits. The energy storage operation constraints define parameters such as the charging / discharging state and SOC (State of Charge) range of the energy storage equipment, ensuring stable and reliable operation. The energy storage charging / discharging power constraints limit the upper and lower limits of the energy storage equipment's charging / discharging power, preventing power surges from damaging the equipment and the power grid. Based on satisfying all the above constraints, a Markov decision model is invoked to iteratively solve the cost objective function. Through multiple rounds of iterative optimization, the optimal solution is gradually approximated, ultimately yielding the minimum operating cost of the high-proportion photovoltaic distribution area. Thus, this invention can maximize the comprehensive benefits of high-proportion photovoltaic distribution areas while effectively suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid, ensuring both the safe and stable operation of the power grid and reducing the construction and operating costs of the distribution areas. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart of an energy management method for a high-proportion photovoltaic distribution area according to one embodiment is shown; Figure 2 This is a hardware architecture diagram of an electronic device provided in an embodiment of the present invention; Figure 3 A structural diagram of an energy management device for a high-proportion photovoltaic distribution area according to one embodiment is shown. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0013] Please refer to Figure 1 This invention provides an energy management method for a high-proportion photovoltaic distribution area, comprising: Step 100: Construct a cost objective function; whereby the objective function aims to minimize the total construction cost of high-proportion photovoltaic power generation areas while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid. Step 102: Under the premise of meeting the energy management constraints of the high-proportion photovoltaic distribution area, the Markov decision model is called to iteratively solve the cost objective function to obtain the minimum operating cost of the high-proportion photovoltaic distribution area. Among them, the energy management constraints of high-proportion photovoltaic distribution areas include distribution area power constraints, energy storage operation constraints, and charging and discharging power constraints.

[0014] In this embodiment, a cost objective function is first constructed. The goal of this function is to minimize the total construction cost of high-proportion photovoltaic (PV) distribution areas while effectively suppressing the impact of PV power output fluctuations and randomness on the power grid, thus balancing grid stability and economic efficiency. Simultaneously, to ensure the feasibility and security of the energy management scheme, energy management constraints for high-proportion PV distribution areas must be followed. These constraints include distribution area power constraints, energy storage operation constraints, and charging / discharging power constraints. The distribution area power constraints regulate power exchange between the distribution area and the distribution network, preventing excessive backfeeding and voltage exceeding limits. The energy storage operation constraints define parameters such as the charging / discharging state and SOC (State of Charge) range of the energy storage devices, ensuring stable and reliable operation. The energy storage charging / discharging power constraints limit the upper and lower limits of the energy storage devices' charging / discharging power, preventing power surges from damaging the equipment and the power grid. Based on satisfying all the above constraints, a Markov decision model is invoked to iteratively solve the cost objective function. Through multiple rounds of iterative optimization, the optimal solution is gradually approximated, ultimately yielding the minimum operating cost of the high-proportion photovoltaic distribution area. Thus, this invention can maximize the comprehensive benefits of high-proportion photovoltaic distribution areas while effectively suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid, ensuring both the safe and stable operation of the power grid and reducing the construction and operating costs of the distribution areas.

[0015] In one embodiment of the present invention, the cost objective function is constructed using the following formula: In the formula, To minimize the operating costs of high-proportion photovoltaic distribution areas, Let t be the cost of buying and selling electricity from the grid. Let t be the cost of power fluctuation in the distribution area. Let t be the lifetime loss cost of energy storage. Let t be the dispatch compensation cost incurred by photovoltaic power generation reduction due to curtailment at time t. The cost is the peak-valley difference in net load for the transformer area, where T is the preset number of points.

[0016] In this embodiment, to maximize the overall benefits of a high-proportion photovoltaic (PV) distribution area while suppressing the impact of PV power output fluctuations and randomness on the power grid, the multi-objective optimization economic cost of the distribution area includes the power interaction cost between the distribution area and the power grid, the distribution transformer area power (DTAP) fluctuation cost, the lifetime loss cost of energy storage, the dispatch compensation cost of PV, and the peak-valley difference cost of the distribution area's net load. With the goal of minimizing the total cost, T=96 represents a 1-day cycle with power allocation performed every 15 minutes.

[0017] In one embodiment of the present invention, the electricity purchase and sale cost from the grid at time t, the power fluctuation cost of the distribution area at time t, the lifespan loss cost of energy storage at time t, the dispatch compensation cost of photovoltaic power generation reduced due to curtailment at time t, and the peak-valley difference cost of the net load of the distribution area are determined by the following formula: In the formula, Let t be the grid electricity price. Let t represent the electricity sales and purchases between the distribution area and the power grid at time t. This is the discount factor for electricity sales prices. The power fluctuation coefficient of the distribution area. The cost coefficient is the primary energy storage safety indicator. Let be the change in charging and discharging power of the stored energy at time t. The cost coefficient is the second energy storage safety indicator. The state of charge, which stores energy at all times. This is the photovoltaic dispatch cost coefficient. Let t be the amount of solar power curtailed in the distribution area. This is the cost coefficient for the peak-to-valley difference in net load. Let t be the net load of the transformer area. This represents the average net load over the day.

[0018] In this embodiment, when the distribution area is in a state of low load or excess renewable energy supply, it can sell electricity to the grid; however, when the load demand exceeds its own supply capacity, it needs to purchase electricity from the grid. Therefore, it is necessary to solve for the power sales and purchases between the distribution area and the grid. In order to reduce the impact on the grid caused by large power fluctuations due to imbalance between the load and photovoltaics, it is also necessary to solve for the power fluctuation cost of the distribution area. When the photovoltaic power generation exceeds the total load power of the distribution area, the excess power is absorbed by energy storage devices or the grid; if the absorbed power exceeds the energy storage charging capacity and the grid reverse transmission limit threshold, the excess part is converted into curtailed power by adjusting the photovoltaic inverter. It is also necessary to solve for the dispatch compensation cost caused by the reduction in photovoltaic power generation due to curtailment. When the photovoltaic capacity is too large, when the photovoltaic is at full capacity at noon and the local load demand cannot be absorbed, it will cause the transformer to be reverse overloaded; while when the load is almost zero during the evening peak period, it will cause the transformer to be forward overloaded. This will increase the peak-valley difference of the net load of the distribution area and increase the peak-shaving pressure, affecting the stability of the distribution area operation. Therefore, the cost of the net load peak-to-valley difference needs to be considered.

[0019] In one embodiment of the present invention, a Markov decision model is invoked to iteratively solve the cost objective function to obtain the minimum operating cost of a high-proportion photovoltaic distribution area; Based on the cost objective function, the state space and action space are determined. The process involves iterating through the state space, action space, and an improved DDQN model to obtain the minimum operating cost for high-proportion photovoltaic distribution areas.

[0020] In this embodiment, the state space and action space required by the model are clearly defined, guided by the cost objective function. Subsequently, the improved DDQN model is combined to leverage its advantages and compensate for the shortcomings of the traditional model. Based on the determined state space and action space, further iterative optimization is performed. Through multiple rounds of training and adjustment, the minimum operating cost of the high-proportion photovoltaic distribution area is finally obtained.

[0021] In one embodiment of the present invention, the state space and action space are constructed using the following formulas: In the formula, For state space, Let be the power generation of the photovoltaic system during time period t. The load of the transformer area during time period t. The time-of-use electricity price for period t. The state of charge of the energy stored during time period t. For the time of day, Let t represent the charging power of the electric vehicle during time period t. For the action space, This represents the amount of solar power that has been curtailed over a given time period. This refers to the charging and discharging power of energy storage during a given period.

[0022] In this embodiment, to comprehensively describe the operational characteristics of the distribution substation under different scheduling cycles, the state space construction of the distribution substation model needs to integrate multi-dimensional environmental variables. Based on the MDP theoretical framework, the state space can be composed of six-dimensional variables: photovoltaic output, load demand, time-of-use pricing, energy storage state of charge, time characteristic parameters, and electric vehicle load. The action space, based on the regulation requirements of the substation's power bus energy flow, designs actions to select photovoltaic curtailment power and energy storage charging / discharging power. After selecting and executing these actions, the photovoltaic power generation for the next time period is calculated based on the magnitude of photovoltaic curtailment power, and the active power relative to the grid is determined using a formula. Subsequently, the environmental state variables are updated as the input state for the next time step.

[0023] In one embodiment of the present invention, the improved DDQN model includes an exploration phase and an exploitation phase during the training process of the exploration strategy; The exploration phase is iterated using the following formula: In the formula, This represents the greedy factor at the corresponding moment. This represents the current iteration number. This represents the total number of global iterations. To explore control coefficients; In this embodiment, to effectively balance exploration and exploitation, the training process of the exploration strategy is divided into two phases: exploration and exploitation. During the exploration phase, the agent's main task is to interact with the environment to collect as many state-action samples as possible, thereby accumulating cognitive information about environmental characteristics, dynamic change patterns, and other aspects.

[0024] In one embodiment of the present invention, the utilization phase is iterated using the following formula: In the formula, This is the final value of the greed factor after the exploration phase ends. This represents the minimum greed factor value. To control the rate of exploration to a minimum, Adjust the size of the greed factor.

[0025] In this embodiment, as the number of iterations increases, the algorithm transitions from the exploration phase to the utilization phase when a preset iteration threshold is reached or exceeded. During the utilization phase, having accumulated sufficient environmental information through previous exploration, the algorithm's primary goal shifts to efficiently utilizing this prior information. If the decrease in the exploration rate is linear, it may lead to excessively frequent random exploration, resulting in low learning efficiency, slow convergence, and an inability to effectively learn from known experiences. Therefore, an exponential annealing function is used in the utilization phase. As training progresses, the algorithm gradually transitions from a broad search state to a local fine-tuning search state, which helps the network fine-tune near the optimal solution, improving the model's accuracy and generalization ability.

[0026] In one embodiment of the present invention, the power constraints of the distribution area, the operational constraints of energy storage, and the charging and discharging power constraints are constructed by the following formula: In the formula, This refers to the maximum power limit that the distribution area can sell to the grid. This represents the maximum power capacity that the distribution area can purchase from the power grid. To determine the real-time electricity purchase and sales volume, This is the lower limit threshold for the charged state of energy storage. This is the upper limit threshold for the state of charge of energy storage. For real-time energy storage state of charge, The maximum active power for charging energy storage. To store the maximum active power of discharge, This refers to the active power of real-time energy storage.

[0027] like Figure 2 , Figure 3 As shown, this embodiment of the invention provides an energy management device for a high-proportion photovoltaic distribution area. The device embodiment can be implemented through software, hardware, or a combination of both. From a hardware perspective, as... Figure 2 The diagram shown is a hardware architecture diagram of an electronic device for an energy management system in a high-proportion photovoltaic distribution area, according to an embodiment of the present invention. (Except for...) Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, the electronic device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 3 As shown, a device in a logical sense is formed by the CPU of the electronic device in which it is located reading the corresponding computer program from the non-volatile memory into the memory for execution.

[0028] like Figure 3 As shown in the figure, this embodiment provides an energy management device for a high-proportion photovoltaic distribution area, comprising: The first data processing module 300 is used to construct a cost objective function; wherein the objective function aims to minimize the total construction cost of a high-proportion photovoltaic power generation area while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid. The second data processing module 302 is used to call the Markov decision model to iteratively solve the cost objective function under the premise of meeting the energy management constraints of the high-proportion photovoltaic distribution area, so as to obtain the minimum operating cost of the high-proportion photovoltaic distribution area. The energy management constraints of the high-proportion photovoltaic distribution area include distribution area power constraints, energy storage operation constraints, and charge / discharge power constraints.

[0029] In one embodiment of the present invention, the cost objective function is constructed by the following formula: In the formula, To minimize the operating costs of high-proportion photovoltaic distribution areas, Let t be the cost of buying and selling electricity from the grid. Let t be the cost of power fluctuation in the distribution area. Let t be the lifetime loss cost of energy storage. Let t be the dispatch compensation cost incurred by photovoltaic power generation reduction due to curtailment at time t. The cost is the peak-valley difference in net load for the transformer area, where T is the preset number of points.

[0030] In one embodiment of the present invention, the electricity purchase and sale cost from the grid at time t, the power fluctuation cost of the distribution area at time t, the lifespan loss cost of energy storage at time t, the dispatch compensation cost of photovoltaic power generation reduced due to curtailment at time t, and the peak-valley difference cost of the net load of the distribution area are determined by the following formula: In the formula, Let t be the grid electricity price. Let t represent the electricity sales and purchases between the distribution area and the power grid at time t. This is the discount factor for electricity sales prices. The power fluctuation coefficient of the distribution area. The cost coefficient is the primary energy storage safety indicator. Let be the change in charging and discharging power of the stored energy at time t. The cost coefficient is the second energy storage safety indicator. The state of charge, which stores energy at all times. This is the photovoltaic dispatch cost coefficient. Let t be the amount of solar power curtailed in the distribution area. This is the cost coefficient for the peak-to-valley difference in net load. Let t be the net load of the transformer area. This represents the average net load over the day.

[0031] In one embodiment of the present invention, the second data processing module 302 is configured to perform the following operations: Based on the aforementioned cost objective function, the state space and action space are determined; Based on the state space, the action space, and the improved DDQN model, iterative processes are performed to obtain the minimum operating cost of high-proportion photovoltaic distribution areas.

[0032] In one embodiment of the present invention, the state space and the action space are constructed using the following formula: In the formula, For state space, Let be the power generation of the photovoltaic system during time period t. The load of the transformer area during time period t. The time-of-use electricity price for period t. The state of charge of the energy stored during time period t. For the time of day, Let t represent the charging power of the electric vehicle during time period t. For the action space, This represents the amount of solar power that has been curtailed over a given time period. This refers to the charging and discharging power of energy storage during a given period.

[0033] In one embodiment of the present invention, the improved DDQN model includes an exploration phase and an exploitation phase during the training process of the exploration strategy; The exploration phase is iterated using the following formula: In the formula, This represents the greedy factor at the corresponding moment. This represents the current iteration number. This represents the total number of global iterations. To explore control coefficients; The utilization phase is iterated using the following formula: In the formula, This is the final value of the greed factor after the exploration phase ends. This represents the minimum greed factor value. To control the rate of exploration to a minimum, Adjust the size of the greed factor.

[0034] In one embodiment of the present invention, the power constraint of the distribution area, the operational constraint of the energy storage, and the charging / discharging power constraint are constructed by the following formula: In the formula, This refers to the maximum power limit that the distribution area can sell to the grid. This represents the maximum power capacity that the distribution area can purchase from the power grid. To determine the real-time electricity purchase and sales volume, This is the lower limit threshold for the charged state of energy storage. This is the upper limit threshold for the state of charge of energy storage. For real-time energy storage state of charge, The maximum active power for charging energy storage. To store the maximum active power of discharge, This refers to the active power of real-time energy storage.

[0035] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on an energy management device for a high-proportion photovoltaic distribution area. In other embodiments of the present invention, an energy management device for a high-proportion photovoltaic distribution area may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0036] The information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the method embodiment of the present invention, and the specific details can be found in the description of the method embodiment of the present invention, and will not be repeated here.

[0037] This invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements an energy management method for a high-proportion photovoltaic distribution area according to any embodiment of this invention.

[0038] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform an energy management method for a high-proportion photovoltaic distribution area according to any embodiment of this invention.

[0039] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or Mpu) of the system or apparatus may read and execute the program code stored in the storage medium.

[0040] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0041] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as Cd-ROM, Cd-R, Cd-Rw, DVD-ROM, DVD-Ram, DVD-Rw, DVD+Rw), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0042] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0043] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other device installed on the expansion board or expansion module executes some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0044] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0045] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An energy management method for a high-proportion photovoltaic distribution area, characterized in that, include: Construct a cost objective function; wherein the objective function aims to minimize the total construction cost of high-proportion photovoltaic power generation areas while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid; Under the premise of meeting the energy management constraints of high-proportion photovoltaic distribution areas, the cost objective function is iteratively solved by calling the Markov decision model to obtain the minimum operating cost of high-proportion photovoltaic distribution areas. The energy management constraints of the high-proportion photovoltaic distribution area include distribution area power constraints, energy storage operation constraints, and charge / discharge power constraints.

2. The method according to claim 1, characterized in that, The cost objective function is constructed using the following formula: In the formula, To minimize the operating costs of high-proportion photovoltaic distribution areas, Let t be the cost of buying and selling electricity from the grid. Let t be the cost of power fluctuation in the distribution area. Let t be the lifetime loss cost of energy storage. Let t be the dispatch compensation cost incurred by photovoltaic power generation reduction due to curtailment at time t. The cost is the peak-valley difference in net load for the transformer area, where T is the preset number of points.

3. The method according to claim 2, characterized in that, The costs of purchasing and selling electricity from the grid at time t, the power fluctuation costs of the distribution area at time t, the lifespan loss costs of energy storage at time t, the dispatch compensation costs of photovoltaic power generation reduced due to curtailment at time t, and the peak-valley difference costs of the net load of the distribution area are determined by the following formulas: In the formula, Let t be the grid electricity price. Let t represent the electricity sales and purchases between the distribution area and the power grid at time t. This is the discount factor for electricity sales prices. The power fluctuation coefficient of the distribution area. The cost coefficient is the primary energy storage safety indicator. Let be the change in charging and discharging power of the stored energy at time t. The cost coefficient is the second energy storage safety indicator. The state of charge, which stores energy at all times. This is the photovoltaic dispatch cost coefficient. Let t be the amount of solar power curtailed in the distribution area. This is the cost coefficient for the peak-to-valley difference in net load. Let t be the net load of the transformer area. This represents the average net load over the day.

4. The method according to claim 1, characterized in that, The step of iteratively solving the cost objective function using a Markov decision model to obtain the minimum operating cost of a high-proportion photovoltaic distribution area includes: Based on the aforementioned cost objective function, the state space and action space are determined; The process iterates based on the state space, the action space, and the improved DDQN model to obtain the minimum operating cost of a high-proportion photovoltaic distribution area.

5. The method according to claim 4, characterized in that, The state space and the action space are constructed using the following formulas: In the formula, For state space, Let be the power generation of the photovoltaic system during time period t. The load of the transformer area during time period t. The time-of-use electricity price for period t. The state of charge of the energy stored during time period t. For the time of day, Let t represent the charging power of the electric vehicle during time period t. For the action space, This represents the amount of solar power that has been curtailed over a given time period. This refers to the charging and discharging power of energy storage during a given period.

6. The method according to claim 4, characterized in that, The improved DDQN model includes an exploration phase and an exploitation phase in the training process of the exploration strategy; The exploration phase is iterated using the following formula: In the formula, This represents the greedy factor at the corresponding moment. This represents the current iteration number. This represents the total number of global iterations. To explore control coefficients; The utilization phase is iterated using the following formula: In the formula, This is the final value of the greed factor after the exploration phase ends. This represents the minimum greed factor value. To control the rate of exploration to a minimum, Adjust the size of the greed factor.

7. The method according to claim 1, characterized in that, The power constraints of the distribution area, the operational constraints of the energy storage, and the charging / discharging power constraints are constructed using the following formulas: In the formula, This refers to the maximum power limit that the distribution area can sell to the grid. This represents the maximum power capacity that the distribution area can purchase from the power grid. To determine the real-time electricity purchase and sales volume, This is the lower limit threshold for the charged state of energy storage. This is the upper limit threshold for the state of charge of energy storage. For real-time energy storage state of charge, The maximum active power for charging energy storage. To store the maximum active power of discharge, This refers to the active power of real-time energy storage.

8. An energy management device for a high-proportion photovoltaic distribution area, characterized in that, include: The first data processing module is used to construct a cost objective function; wherein the objective function aims to minimize the total construction cost of a high-proportion photovoltaic power generation area while suppressing the impact of photovoltaic power output fluctuations and randomness on the power grid. The second data processing module is used to call the Markov decision model to iteratively solve the cost objective function under the premise of meeting the energy management constraints of the high-proportion photovoltaic distribution area, so as to obtain the minimum operating cost of the high-proportion photovoltaic distribution area. The energy management constraints of the high-proportion photovoltaic distribution area include distribution area power constraints, energy storage operation constraints, and charge / discharge power constraints.

9. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed in a computer, causes the computer to perform the method described in any one of claims 1-7.

Images