A power distribution network power flow optimization method, system, device and medium

Abstract

This invention relates to the field of data processing technology, and discloses a method, system, device, and medium for power flow optimization in distribution networks. The method includes: acquiring power grid operating status data; randomly generating an optimization calculation population that meets preset capacity conditions; calculating the power grid losses corresponding to each set of operating commands based on the power grid operating status data and the power flow optimization calculation population; generating a new optimization calculation population based on the operating commands corresponding to some power grid losses that meet the loss conditions, and returning to the step of generating the optimization calculation population until the iteration stopping condition is met, obtaining the target optimization calculation population; and determining the target power parameters of each port in the power flow optimization router based on the optimal operating command of the target optimization calculation population. This invention controls the energy router according to a strategy, significantly reducing power grid operating losses and improving the power grid's absorption capacity and operating efficiency.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, system, device and medium for optimizing power flow in a distribution network. Background Technology

[0002] With the rapid development of new energy power generation technologies, energy storage systems, and diversified loads, medium- and low-voltage distribution networks are gradually evolving from traditional radial, AC-dominated grid structures to flexible distribution networks that are AC / DC hybrid and operate with multiple sources in a coordinated manner. Against this backdrop, energy routers, as key power distribution equipment, possess the ability to integrate different voltage levels and power types, providing crucial technical support for the intelligent operation of distribution networks.

[0003] However, current energy routers still have significant limitations in practical engineering applications. Energy routers are often designed using a customized approach, with their port capacity, control strategies, and energy management algorithms largely developed based on the specific needs of a single project. This results in insufficient versatility and scalability, making it difficult to adapt to the requirements of rapid deployment and flexible operation in different scenarios. Furthermore, existing energy router control strategies are typically limited to simple local power coordination or fixed power scheduling modes, failing to fully utilize the multi-port coordination and active control capabilities of energy routers, and unable to perform global optimization and control based on the real-time state of the power grid. These problems lead to high system losses during power grid operation, limited grid absorption capacity, and difficulty in improving overall operating efficiency, thus failing to fully realize the potential of new power distribution equipment in improving grid flexibility and economy.

[0004] Therefore, how to design a power flow optimization method for distribution networks that can fully utilize the control capabilities of energy routers and reduce the operating losses of distribution networks has become an urgent technical problem to be solved in the field of distribution networks. Summary of the Invention

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, this invention provides a distribution network power flow optimization method, system, device, and medium to solve the problem that the control strategies of energy routers in the prior art usually adopt customized fixed scheduling modes and lack global optimization capabilities based on the real-time status of the power grid, resulting in high operating losses and low operating efficiency of the distribution network.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a power flow optimization method for a distribution network, comprising: Acquire power grid operation status data; An optimized computing population that meets preset capacity conditions is randomly generated. The optimized computing population includes multiple sets of operating instructions, which include control instructions for each port of the energy router. Based on the power grid operation status data and the optimized calculation population, the power grid loss of the distribution network under each set of operation commands is calculated. Based on the power grid loss, select some operating instructions that meet the loss conditions from the optimized calculation population, generate a new optimized calculation population based on the selected operating instructions, perform loss calculation and population selection update on the new optimized calculation population, and obtain the target optimized calculation population. Based on the target optimization calculation population's optimal operating instructions, the target power parameters of each port in the energy router are determined.

[0008] As a preferred embodiment of the power flow optimization method for distribution networks according to the present invention, the step of selecting a portion of the operating instructions that meet the loss conditions from the optimization calculation population, and generating a new optimization calculation population based on the portion of the operating instructions, includes: Based on the aforementioned power grid losses, a portion of the first operating instructions are determined from multiple sets of operating instructions; Based on the independent control instructions of each port in the first running instructions, multiple second running instructions are generated in a cross-referenced manner; A new optimized computation population is generated based on multiple first execution instructions and multiple second execution instructions.

[0009] As a preferred embodiment of the power flow optimization method for distribution networks described in this invention, the step of generating a new optimization calculation population based on multiple first operating instructions and multiple second operating instructions includes: The population difference is determined based on the minimum population size of the optimized computation population, the number of the first running instructions, and the number of the second running instructions; A third running instruction is randomly generated in a quantity equal to the population difference, and the third running instruction satisfies a preset capacity condition; A new optimized computation population is constructed based on multiple first execution instructions, multiple second execution instructions, and multiple third execution instructions.

[0010] As a preferred embodiment of the power flow optimization method for a distribution network described in this invention, the step of determining the target power parameters of each port in the energy router includes: Extract the optimal operating instructions of the target optimization computation population, wherein the optimal operating instructions include the control instructions of each port of the energy router; Extract the control instructions corresponding to each port from the optimal running instructions; The control command is converted into a target power setting value for each port, the target power setting value including target active power and target reactive power; The power output of the corresponding port of the energy router is controlled according to the target power setting value to perform power flow optimization operation.

[0011] The beneficial effects of this preferred technical solution are: controlling the energy router according to the optimal operation strategy, thereby significantly reducing the operating losses of the distribution network and improving the grid absorption capacity and operating efficiency of the grid system.

[0012] As a preferred embodiment of the power flow optimization method for distribution networks described in this invention, the power grid operating status data includes the real-time voltage of each node in the distribution network, the real-time load of each load, the real-time power of each power source, the real-time power of each energy storage, the current storage capacity of each energy storage, and the predicted power of each power source.

[0013] As a preferred embodiment of the power flow optimization method for distribution networks described in this invention, the random generation of the optimization calculation population that satisfies the preset capacity conditions includes: Based on the capacity range of each port of the energy router, the port power control target of each port is randomly generated to obtain a single set of operating instructions; Based on the acquired multiple sets of running instructions, the optimized computing population is formed, and the number of running instructions in the optimized computing population reaches the minimum population size.

[0014] As a preferred embodiment of the power flow optimization method for distribution networks described in this invention, the calculation of the power network losses corresponding to each set of operating commands includes: Based on the power grid operation status data and each set of operation instructions in the optimization calculation population, the power flow distribution of the power grid is calculated when each port of the energy router executes each set of operation instructions; If the calculation of the power flow distribution fails, the corresponding running instruction is removed from the optimization calculation population; If the power flow distribution calculation is successful, the grid loss corresponding to the operation command is determined based on the power flow distribution.

[0015] The beneficial effects of this preferred technical solution are: it can effectively evaluate and optimize the power control targets of each port in the power system, so as to improve the operating efficiency of the power grid.

[0016] Secondly, the present invention provides a power flow optimization system for a distribution network, comprising: The acquisition module is used to acquire power grid operating status data; The generation module is used to randomly generate an optimized computing population that meets preset capacity conditions. The optimized computing population includes multiple sets of running instructions, which include control instructions for each port of the energy router. The calculation module is used to calculate the power grid loss of the distribution network under each set of operating commands based on the power grid operation status data and the optimized calculation population. An iterative module is used to select a portion of the operating instructions that meet the loss conditions from the optimized calculation population based on the power grid loss, generate a new optimized calculation population based on the portion of the operating instructions, perform loss calculation and population selection and update on the new optimized calculation population, and obtain the target optimized calculation population. The determination module is used to determine the target power parameters of each port in the energy router based on the optimal operating instructions of the target optimization calculation population.

[0017] Thirdly, the present invention provides an electronic device, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions to implement the steps of a power flow optimization method for a power distribution network.

[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of a power flow optimization method for a power distribution network.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention acquires grid operation status data reflecting the electrical state of various parts of the grid, randomly generates multiple sets of energy router operation commands, determines the possible corresponding grid losses based on the grid operation status data and energy router operation commands, calculates the grid losses under different commands and iteratively filters them, and can automatically and accurately find the optimal operation strategy that minimizes the total grid loss of the system. Finally, the energy router is controlled according to the optimal operation strategy, thereby significantly reducing the distribution network operation losses and improving the grid absorption capacity and the operating efficiency of the grid system. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the overall process logic of the power flow optimization method for power distribution networks provided in an embodiment of the present invention.

[0022] Figure 2The flowchart illustrates the population iterative optimization process of the power flow optimization method for distribution networks provided in this embodiment of the invention.

[0023] Figure 3 This is a schematic diagram of the population composition during the population iteration process of the power flow optimization method for distribution networks provided in this embodiment of the invention. Detailed Implementation

[0024] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0025] Example 1, referring to Figure 1 As one embodiment of the present invention, a power flow optimization method for a distribution network is provided, such as... Figure 1 The specific steps shown are as follows: S100: Acquire power grid operation status data; S200: Randomly generates an optimized computing population that meets preset capacity conditions. The optimized computing population includes multiple sets of running instructions, which include control instructions for each port of the energy router. S300: Based on grid operation status data and optimized computing population, calculate the grid loss of the distribution network under each set of operation commands; S400: Based on grid losses, select some operating instructions that meet the loss conditions from the optimization calculation population, generate a new optimization calculation population based on the partial operating instructions, perform loss calculation and population screening and update on the new optimization calculation population, and obtain the target optimization calculation population. S500: Determines the target power parameters of each port in the energy router based on the optimal operating instructions of the target optimization calculation population.

[0026] It should be noted that this invention acquires grid operation status data reflecting the electrical state of various parts of the grid, randomly generates multiple sets of energy router operation commands, determines possible corresponding grid losses based on grid operation status data and energy router operation commands, and automatically and accurately finds the optimal operation strategy that minimizes the total grid loss of the system by calculating grid losses under different commands and iteratively filtering them. Finally, the energy router is controlled according to the optimal operation strategy, thereby significantly reducing distribution network operation losses and improving grid absorption capacity and grid system operation efficiency.

[0027] Example 2, refer to Figure 2 and Figure 3Based on the previous embodiment, this embodiment provides a specific implementation method for power flow optimization in a distribution network, which will be used to illustrate the technical means employed in this method.

[0028] S100: Acquire power grid operation status data.

[0029] In this embodiment of the invention, the power grid operation status data includes the real-time voltage of each node in the distribution network, the real-time load of each load, the real-time power of each power source, the real-time power of each energy storage, the current storage capacity of each energy storage, and the predicted power of each power source.

[0030] Specifically, real-time operational status data of the power grid is acquired through measuring equipment. This data reflects the grid's operational condition, such as whether equipment is functioning properly and whether power transmission is stable. For example, by installing current and voltage sensors at various nodes of the power grid, the system obtains real-time current and voltage values ​​and uses this data to determine the load conditions in different areas of the grid.

[0031] S200: Randomly generates an optimized computing population that meets preset capacity conditions. The optimized computing population includes multiple sets of operating instructions, which include control instructions for each port of the energy router.

[0032] It should be noted that the optimization computation population comprises multiple sets of operating instructions, each instructing the control status of each port of the energy router. Multiple candidate schemes are randomly generated based on the grid's capacity conditions. These candidate schemes satisfy the overall requirements of the grid under the capacity conditions, ensuring that each computational population reflects different possible control strategies. Each individual in the optimization computation population represents a possible control scheme, containing instructions for each port of the energy router. For example, in a distribution network, suppose there are three energy routers, each with several ports. The control instruction for each port might be adjusting the power output of a certain grid segment. Multiple combinations of operating instructions are generated through a random algorithm to enable more accurate optimization calculations.

[0033] In this embodiment of the invention, randomly generating an optimized computational population that satisfies a preset capacity condition includes: Based on the capacity range of each port of the energy router, the port power control target of each port is randomly generated to obtain a single set of operating instructions; Based on the acquired multiple sets of execution instructions, an optimized computing population is formed, and the number of execution instructions in the optimized computing population reaches the minimum population size.

[0034] Specifically, the system analyzes the capacity range of each port, i.e., the maximum and minimum power values ​​that each port can control. Based on this capacity range, the system randomly generates a power control target for each port. The generated target values ​​are within the capacity range of each port, ensuring that power control is within the allowable range of the device.

[0035] Specifically, based on the multiple execution instructions generated in the previous step, a new optimization calculation population is formed. The optimization calculation population refers to the set of instructions used for calculation and selection in the optimization algorithm; these instructions will be used in subsequent power optimization calculations. When generating the optimization calculation population, it is ensured that the number of instructions reaches the preset minimum population size.

[0036] It should be noted that the minimum population size can be set based on the complexity of the specific optimization problem, the availability of computing resources, and the required optimization accuracy. Typically, this number can be determined based on the number of energy router ports, the size of the power grid nodes, and the convergence characteristics of the optimization algorithm. For example, it can be set as a multiple of the number of ports or based on empirical values ​​to ensure that the initial population has sufficient diversity and representativeness to meet the evolutionary requirements of optimization methods such as genetic algorithms during the iterative process, thereby effectively improving the optimization success rate and the quality of the final solution.

[0037] In an optional embodiment, the acquisition of the optimized computational population can also be achieved by generating several initial running instructions based on the historical best combination of running instructions in typical scenarios, and constructing an initial population by combining its mutation operation, so as to improve convergence efficiency.

[0038] In an optional embodiment, the optimization computation population can also be obtained by using a heuristic method to generate an initial instruction set that satisfies the constraints, based on the power grid topology and load distribution characteristics, as the starting point for the optimization search.

[0039] It should be noted that step S200 above ensures that the generated instructions comply with device safety constraints and expands the optimization search space through population diversity. The random generation method avoids the limitations of manually setting initial solutions, which is conducive to exploring potential efficient operating strategies more comprehensively in subsequent iterations and improving global optimization capabilities.

[0040] S300: Based on grid operation status data and optimized computing population, calculate the grid loss of the distribution network under each set of operation commands.

[0041] It should be noted that, based on the acquired power grid operating status data and combined with the generated optimization computational population, the power grid losses corresponding to each set of operating commands are calculated. Power grid losses typically refer to the energy loss caused by factors such as conductors and electrical components during power transmission; specific loss types include conductor losses and transformer losses. The electrical behavior of the power grid is simulated through a simulation model to estimate the losses corresponding to each operating command.

[0042] In this embodiment of the invention, calculating the power grid loss of the distribution network under each set of operating commands includes: Based on the power grid operation status data and each set of operation instructions in the optimized computing population, the power flow distribution of the power grid is calculated when each port of the energy router executes each set of operation instructions. If the calculation of power flow distribution fails, the corresponding running instruction is removed from the optimization calculation population; If the power flow distribution is successfully calculated, the grid loss corresponding to the operating command is determined based on the power flow distribution.

[0043] Specifically, by combining the power grid's operational status data with each set of operational commands, power flow analysis is performed to calculate the power distribution at each port of the power grid. Each set of operational commands includes the power setpoints for the energy router ports. In other words, the power grid's operational status data is acquired, and based on each set of operational commands, the power output target for each port is calculated. This target is then applied to the power grid model, and power flow calculation algorithms are used to analyze the power distribution within the power grid, generating a power flow distribution map.

[0044] Specifically, if the power flow distribution calculation fails, the corresponding execution instructions will be removed from the optimization calculation population to ensure that subsequent calculations and optimizations focus only on valid and successfully implemented execution instructions. In other words, when the system performs power flow calculations, if the calculation results are found to be inconsistent with the actual physical limitations of the power grid, the set of execution instructions will be marked as invalid and removed from the optimization calculation population.

[0045] Specifically, if the power flow calculation is successful, the power flow distribution is further analyzed, and the grid loss corresponding to each set of operating commands is calculated. For example, based on the results of the power flow calculation, the current data of each transmission line is obtained, the power loss of each line is calculated according to the current and resistance of the line, and the losses of each line and node are summarized to obtain the total grid loss.

[0046] In an optional embodiment, the calculation of grid losses can also be based on the relationship between node voltage and power injection, constructing a loss sensitivity matrix, and using matrix operations to quickly estimate the changes in system losses under different operating commands.

[0047] In an optional embodiment, the calculation of power grid losses can also utilize data-driven models such as neural networks. A loss prediction model is trained based on historical operating data, and the corresponding loss value is predicted directly according to the power grid status and command parameters, thereby improving computational efficiency while ensuring accuracy.

[0048] It should be noted that step S300 above, by combining the real-time status of the power grid with each set of operating instructions, performs power flow distribution simulation and power grid loss calculation, which can effectively evaluate and optimize the power control targets of each port in the power system, so as to improve the operating efficiency of the power grid, perform power flow calculation, and accurately determine the power grid loss.

[0049] S400: Based on grid losses, select some operating instructions that meet the loss conditions from the optimization calculation population, generate a new optimization calculation population based on the partial operating instructions, perform loss calculation and population screening and update on the new optimization calculation population, and obtain the target optimization calculation population.

[0050] It should be noted that the analysis of grid loss results selects operating instruction combinations that meet preset loss conditions. These compliant combinations are used to generate a new optimization calculation population. Based on the loss results calculated in the current step, low-loss instruction combinations are retained, high-loss schemes are removed, and a new optimization calculation population is generated. For example, if the grid loss corresponding to a certain operating instruction combination exceeds a set threshold, that instruction combination will be eliminated; while lower-loss instruction combinations will continue to participate in subsequent optimizations. In this way, through gradual selection and adjustment, a continuously optimized set of operating instructions is formed.

[0051] In this embodiment of the invention, a subset of running instructions that meet the loss conditions are selected from the optimization computation population, and a new optimization computation population is generated based on the subset of running instructions, including: Based on grid losses, a portion of the first operating commands are determined from multiple sets of operating commands; Based on the independent control instructions of each port in some of the first running instructions, multiple second running instructions are generated in a cross-referenced manner; A new optimized computation population is generated based on multiple first execution instructions and multiple second execution instructions.

[0052] Specifically, based on the calculated grid loss, the first operating instructions are selected from the optimization calculation population. The grid loss value of these instruction combinations must be less than a preset loss threshold, indicating that these instruction combinations are the best performing choices. In detail, the operating instructions can be sorted according to the grid loss value, and the groups with the lowest grid loss can be selected as the first operating instructions. For example, assuming there are 100 operating instructions in the optimization calculation population, after grid loss calculation, the system will select the 30 operating instructions with the lowest loss as the first operating instructions.

[0053] Specifically, the control instructions for each port in multiple first operating instructions are cross-combined to generate new second operating instructions. Possible optimization schemes are derived through the combination of different operating instructions. The cross-operation is used to combine the control instructions for each port in the first operating instructions to generate a new set of control instructions. For example, suppose there are two first operating instructions, A and B, where the first port control instruction of instruction A is to adjust the power to 50W, and the first port control instruction of instruction B is to adjust the power to 70W. Through the cross-operation, the system may extract the first port control instructions of instruction A and instruction B and combine them to generate a new second operating instruction C. This cross-generated second operating instruction will be used in the next optimization calculation.

[0054] Specifically, a new optimization calculation population is constructed based on multiple first and second operating instructions. The first operating instructions and the second operating instructions obtained through crossover are combined to form a new population set for the next round of optimization calculations. Specifically, the first operating instructions and the crossover-generated second operating instructions are used as input to the new population to continue calculating grid losses and iterating optimization. Through multiple iterations and population updates, an optimal set of control instructions can eventually be found. For example, after constructing the new population, loss calculations are performed again on these instruction combinations, and the instruction with the minimum loss is selected as the new optimization target. This process is repeated until a preset stopping condition is reached. The preset stopping condition could be that the optimal control instruction set remains unchanged for three consecutive generations, or that a preset number of iterations is reached.

[0055] It should be noted that the above embodiments determine the grid loss corresponding to each set of operating instructions in the optimized computing population by using grid operation status data and optimized computing population. Then, based on the magnitude of each grid loss, some first operating instructions are determined from multiple sets of operating instructions, and multiple second operating instructions are generated by cross-generating the independent control instructions of each port in the multiple first operating instructions, thereby constructing a new optimized computing population. A genetic algorithm is used for iteration to obtain a suitable optimized computing population.

[0056] In this embodiment of the invention, independent control instructions for each port are randomly selected from a plurality of first execution instructions to generate a plurality of second execution instructions. Each second execution instruction includes independent control instructions for all ports.

[0057] Specifically, independent control instructions for each port are randomly selected from multiple first operating instructions and combined to form new second operating instructions. Each second operating instruction will include independent control instructions for all ports, thereby generating new instruction combinations and expanding the scope of optimization calculations. Each first operating instruction contains multiple control ports that control different power grid equipment or electrical parameters, such as power and voltage. Control instructions are randomly selected from each port in each first operating instruction, and then these control instructions are combined to generate new second operating instructions.

[0058] In this embodiment of the invention, generating a new optimized computation population based on multiple first execution instructions and multiple second execution instructions includes: The population difference is determined based on the minimum population size for optimized computation, the number of first execution instructions, and the number of second execution instructions. A third running instruction is randomly generated in a quantity equal to the population difference, and the third running instruction satisfies the preset capacity condition; A new optimized computation population is constructed based on multiple first execution instructions, multiple second execution instructions, and multiple third execution instructions.

[0059] Specifically, the population difference is first calculated. This difference is determined by the difference between the minimum population size for optimization calculations, the number of first execution instructions, and the number of second execution instructions. The purpose of the population difference is to ensure that the population size is sufficiently large during the optimization calculation process to maintain diversity and promote global optimization. The minimum population size for optimization calculations is a preset threshold to guarantee computational diversity and avoid local optima. After comparing the sum of the first and second execution instructions with the minimum population size, if the sum is insufficient, new execution instructions are generated based on the difference. For example, assuming the system sets the minimum population size to 100, and there are currently 30 first execution instructions and 40 second execution instructions, then 30 new execution instructions need to be generated to supplement the population.

[0060] Specifically, based on the calculated population difference, a third execution instruction is randomly generated in a number that is greater than or equal to the population difference. Each third execution instruction must meet a preset capacity condition.

[0061] Specifically, a new optimization computation population is constructed based on multiple first execution instructions, second execution instructions, and a randomly generated third execution instruction. In other words, the system combines the first, second, and third execution instructions to form a new population set containing multiple control strategies. This new population set will serve as input for the next round of optimization computation, used for further loss calculation and performance evaluation.

[0062] It should be noted that the above embodiments generate multiple second running instructions by randomly selecting independent control instructions for each port from multiple first running instructions. Then, based on the minimum population size of the optimized computation population, the number of first running instructions, and the number of second running instructions, the population difference is determined, and a third running instruction with a population difference is randomly generated to construct a new optimized computation population, thereby ensuring the diversity of the population in the genetic algorithm.

[0063] In an alternative embodiment, the step of generating a new optimization computational population can also introduce a simulated annealing mechanism, which not only retains low-loss individuals in each iteration, but also accepts some higher-loss individuals into the next generation with a certain probability, in order to enhance the ability to escape local optima.

[0064] In an optional embodiment, the step of generating a new optimization computation population can also employ the particle swarm optimization approach, recording the historical best position and global best position of each individual in the population, and generating a new generation of instruction sets based on position and velocity update formulas, thereby achieving more efficient directional search and convergence.

[0065] In embodiments of the present invention, such as Figure 2 The diagram shows the population iterative optimization flowchart for power flow optimization in distribution networks. The specific steps for calculating the optimal power flow of the system using the optimization algorithm include: Within the capacity range of each port of the energy router, a set of active and reactive port instructions are randomly generated. These instructions form an array and are denoted as a set of system operation instructions. The instructions are repeatedly generated to randomly construct N sets of system operation instructions. These system operation instructions constitute an optimization calculation population. For each set of system operation commands in the optimization calculation population, calculate the power flow distribution of the power grid under the operation command. If the power flow calculation is unsuccessful, it means that the system cannot operate under the operation command. If the power flow calculation is successful, then further calculate the network loss under the power flow distribution. The system operation instructions in the population are sorted in order of increasing network loss, and the top M1 sets of system operation instructions in the population are retained to enter the next generation of optimization computing population. The iteration continues until the system operation instruction set with the lowest network loss is selected through iterative optimization, and the iteration ends when the system operation instruction ranked first remains unchanged for three consecutive generations. Based on the retained M1 set of system operation instructions, some of the operation instructions are randomly selected and cross-referenced to form a new M2 set of hybrid operation instructions, which are then added to the next generation of optimization computing population. Randomly generate N-M1-M2 new sets of system execution instructions and add them to the next-generation optimization population, so that the number of system execution instructions in the next-generation optimization population reaches N sets. For details, please refer to [reference needed]. Figure 3 ; The next generation population is formed by the above N sets of operating instructions; After the iteration is completed, the system operation instruction ranked first in the last generation of the population is the optimal system operation instruction. The system power flow under this instruction is the optimal system power flow. The active and reactive power instructions of each port in the optimal operation instruction are taken as the power control targets of each port of the power router.

[0066] It should be noted that the power flow optimization control method in the above embodiments makes full use of the existing information of the power grid and the active power control capability of the energy router. By introducing optimization algorithms, it achieves optimal network loss operation based on the energy router, reduces system operating losses, and improves system operating efficiency.

[0067] In an optional embodiment, the target optimization computation population can also be obtained using a multi-objective optimization framework, which introduces indicators such as voltage deviation and load balancing while considering network loss, and uses the Pareto front to screen non-dominated solution sets to form the target population.

[0068] In an optional embodiment, the acquisition of the target optimization computation population can also be combined with reinforcement learning methods. With the power grid operating state as the state space and the port commands as the action space, the command generation policy is continuously updated through policy gradient or Q-learning, thereby directly outputting the target population that satisfies the optimization objective.

[0069] It should be noted that step S400 above involves selecting running instructions with lower overhead and then generating and supplementing these instructions through cross-referencing, continuously iterating and optimizing the population to gradually approach the optimal solution. This process simulates the survival-of-the-fittest mechanism in natural evolution, continuously improving the population quality through multiple iterations, and ultimately converging stably to the target set of running instructions that minimizes system overhead.

[0070] S500: Determines the target power parameters of each port in the energy router based on the optimal operating instructions of the target optimization calculation population.

[0071] It should be noted that the optimal operating instructions are selected from the target optimization computation population, and the target power parameters for each router port are determined based on these instructions. These target power parameters represent the power output value that each energy router port should achieve, used for energy scheduling in actual operation. The optimal operating instructions are derived through optimization algorithms, minimizing grid losses while meeting capacity requirements. For example, if the power demand at certain grid nodes is high, the power output of relevant router ports may be adjusted to ensure stable grid operation and minimize losses.

[0072] In this embodiment of the invention, determining the target power parameters of each port in the energy router includes: Extract the optimal operating instructions for the target optimization computation population. The optimal operating instructions include the control instructions for each port of the energy router. Extract the control instructions corresponding to each port from the optimal execution instructions; The control commands are converted into target power setpoints for each port, which include target active power and target reactive power. The power output of the corresponding port of the energy router is controlled according to the target power setpoint to perform power flow optimization operation.

[0073] Specifically, the optimal operating instructions are extracted from the target optimization calculation population. Based on these optimal instructions, the power setpoints for each port of the energy router are determined. Through analysis of the optimal instructions, the active and reactive power targets for each port are calculated. After obtaining the active and reactive power targets, these target values ​​are input into the energy router, and the power output of each port is adjusted.

[0074] It should be noted that the above implementation method determines the target active power and / or target reactive power of each port in the router by calculating the optimal operating instructions of the target optimization population. It can accurately adjust the power output of each port according to the optimal operating instructions, and control the energy router by port power to ensure the optimization of the power grid.

[0075] In one feasible implementation, a method for controlling the energy router to achieve optimal power flow operation of the power grid includes: It acquires the real-time voltage of each node in the distribution network, the real-time load of each load, the real-time output of each power source, and the real-time output of each energy storage. Obtain the current energy storage capacity of each energy storage unit in the distribution network, as well as the power prediction curve of each new energy source for the next day; An optimization algorithm is used to calculate the optimal power flow of the system based on the goal of minimizing system network loss, and to determine the power of each port of the energy router under the optimal power flow. The power obtained from the preceding steps is used as an instruction to control the energy router to exchange power with the power grid connected to each port, thereby achieving optimal power flow operation of the power grid.

[0076] It should be noted that the above step S500 controls the energy router according to the set value, which can realize the real-time optimization and scheduling of power grid flow, thereby effectively reducing the overall loss of the distribution network and improving the power grid operation efficiency and the capacity for new energy consumption while ensuring the safe and stable operation of the system.

[0077] Example 3: This example provides a power flow optimization system for a distribution network, including: The acquisition module is used to acquire power grid operating status data; The generation module is used to randomly generate an optimized computing population that meets the preset capacity conditions. The optimized computing population includes multiple sets of running instructions, which include control instructions for each port of the energy router. The calculation module is used to calculate the power grid loss of the distribution network under each set of operating commands based on power grid operation status data and optimized calculation population; The iterative module is used to select some operating instructions that meet the loss conditions from the optimization calculation population based on the power grid loss, generate a new optimization calculation population based on the partial operating instructions, perform loss calculation and population selection and update on the new optimization calculation population, and obtain the target optimization calculation population. The determination module is used to determine the optimal operating instructions for the population based on the target optimization calculation and to determine the target power parameters of each port in the energy router.

[0078] It should be noted that the technical solution of the distribution network power flow optimization system and the technical solution of the above-mentioned distribution network power flow optimization method belong to the same concept. For details not described in detail in the technical solution of the distribution network power flow optimization system in this embodiment, please refer to the description of the technical solution of the above-mentioned distribution network power flow optimization method.

[0079] The above-mentioned unit modules can be embedded in the processor of the electronic device in hardware form or independent of it, or they can be stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of the above modules.

[0080] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a power distribution network flow optimization method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0081] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method proposed in the above embodiments.

[0082] The storage medium proposed in this embodiment belongs to the same inventive concept as the method proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0083] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory, random access memory, flash memory, hard disk, or optical disk, and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute the method of the embodiments of the present invention.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A power flow optimization method for a distribution network, characterized in that, include: Acquire power grid operation status data; An optimized computing population that meets preset capacity conditions is randomly generated. The optimized computing population includes multiple sets of operating instructions, which include control instructions for each port of the energy router. Based on the power grid operation status data and the optimized calculation population, the power grid loss of the distribution network under each set of operation commands is calculated. Based on the power grid loss, select some operating instructions that meet the loss conditions from the optimized calculation population, generate a new optimized calculation population based on the selected operating instructions, perform loss calculation and population selection update on the new optimized calculation population, and obtain the target optimized calculation population. Based on the target optimization calculation population's optimal operating instructions, the target power parameters of each port in the energy router are determined.

2. The power flow optimization method for a distribution network as described in claim 1, characterized in that, The step of selecting a subset of running instructions that meet the loss conditions from the optimization computation population, and generating a new optimization computation population based on the subset of running instructions, includes: Based on the aforementioned power grid losses, a portion of the first operating instructions are determined from multiple sets of operating instructions; Based on the independent control instructions of each port in the first running instructions, multiple second running instructions are generated in a cross-referenced manner; A new optimized computation population is generated based on multiple first execution instructions and multiple second execution instructions.

3. The power flow optimization method for a distribution network as described in claim 2, characterized in that, The process of generating a new optimization computation population based on multiple first execution instructions and multiple second execution instructions includes: The population difference is determined based on the minimum population size of the optimized computation population, the number of the first running instructions, and the number of the second running instructions; A third running instruction is randomly generated in a quantity equal to the population difference, and the third running instruction satisfies a preset capacity condition; A new optimized computation population is constructed based on multiple first execution instructions, multiple second execution instructions, and multiple third execution instructions.

4. The power flow optimization method for a distribution network as described in claim 3, characterized in that, Determining the target power parameters for each port in the energy router includes: Extract the optimal operating instructions of the target optimization computation population, wherein the optimal operating instructions include the control instructions of each port of the energy router; Extract the control instructions corresponding to each port from the optimal running instructions; The control command is converted into a target power setting value for each port, the target power setting value including target active power and target reactive power; The power output of the corresponding port of the energy router is controlled according to the target power setting value to perform power flow optimization operation.

5. The power flow optimization method for a distribution network as described in claim 1, characterized in that, The power grid operation status data includes the real-time voltage of each node in the distribution network, the real-time load of each load, the real-time power of each power source, the real-time power of each energy storage, the current storage capacity of each energy storage, and the predicted power of each power source.

6. The power flow optimization method for a distribution network as described in claim 5, characterized in that, The randomly generated optimization computation population that satisfies the preset capacity condition includes: Based on the capacity range of each port of the energy router, the port power control target of each port is randomly generated to obtain a single set of operating instructions; Based on the acquired multiple sets of running instructions, the optimized computing population is formed, and the number of running instructions in the optimized computing population reaches the minimum population size.

7. The power flow optimization method for a distribution network as described in claim 6, characterized in that, The calculation of the power distribution network losses under each set of operating commands includes: Based on the power grid operation status data and each set of operation instructions in the optimization calculation population, the power flow distribution of the power grid is calculated when each port of the energy router executes each set of operation instructions; If the calculation of the power flow distribution fails, the corresponding running instruction is removed from the optimization calculation population; If the power flow distribution calculation is successful, the grid loss corresponding to the operation command is determined based on the power flow distribution.

8. A power flow optimization system for a distribution network, employing a power flow optimization method for a distribution network as described in any one of claims 1 to 7, characterized in that, include: The acquisition module is used to acquire power grid operating status data; The generation module is used to randomly generate an optimized computing population that meets preset capacity conditions. The optimized computing population includes multiple sets of running instructions, which include control instructions for each port of the energy router. The calculation module is used to calculate the power grid loss of the distribution network under each set of operating commands based on the power grid operation status data and the optimized calculation population. An iterative module is used to select a portion of the operating instructions that meet the loss conditions from the optimized calculation population based on the power grid loss, generate a new optimized calculation population based on the portion of the operating instructions, perform loss calculation and population selection and update on the new optimized calculation population, and obtain the target optimized calculation population. The determination module is used to determine the target power parameters of each port in the energy router based on the optimal operating instructions of the target optimization calculation population.

9. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store computer-executable instructions, and when the processor executes the computer-executable instructions, it implements the steps of the power flow optimization method for a power distribution network as described in any one of claims 1 to 7.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer-executable instructions are executed by the processor, they implement the steps of the power flow optimization method for a power distribution network as described in any one of claims 1 to 7.

Images