Power distribution network low-carbon operation control method and device based on source-grid-load-storage cooperation

Abstract

This invention provides a method and apparatus for low-carbon operation control of a distribution network with coordinated generation, grid, load, and energy storage, belonging to the field of distribution network technology. The method includes: acquiring operational data of the coordinated generation, grid, load, and energy storage system over a preset time period, the operational data including load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value, and total power generation; based on the operational data of the coordinated generation, grid, load, and energy storage system over the preset time period, and under preset constraints, determining an optimal operation strategy with minimizing a low-carbon exponential function as the optimization objective, the optimal operation strategy including energy storage charging and discharging control power, load control power, and photovoltaic output control power; and performing operation control of the distribution network based on the optimal operation strategy. This can achieve low-carbon operation of the coordinated generation, grid, load, and energy storage system, effectively supporting the optimized scheduling of distribution networks including distributed new energy sources, adjustable loads, and energy storage.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, specifically to a power distribution network low-carbon operation control method with source-grid-load-storage coordination, a power distribution network low-carbon operation control device with source-grid-load-storage coordination, a machine-readable storage medium, and an electronic device. Background Technology

[0002] With the construction of new power systems based on new energy sources, the distribution network is gradually transforming from a simple power network that receives and distributes electricity to users into a power network that integrates and interacts with power sources, grids, loads, and storage, and is flexibly coupled with microgrids. Its functions in promoting the local consumption of distributed power sources and supporting new types of loads are becoming increasingly significant. The new distribution system connects various power resources within a certain area, including traditional rigid loads, adjustable loads, photovoltaic power generation, and energy storage. By integrating and allocating these resources, the efficiency and reliability of energy utilization can be improved while ensuring safe and rapid response.

[0003] However, the output of distributed renewable energy is intermittent, random, and volatile. Its high proportion of integration complicates the power flow distribution of the distribution network. The traditional "source follows load" unidirectional power supply mode is ill-equipped to handle problems such as voltage exceeding limits, line congestion, and power backflow caused by uncertainties on both the source and load sides, affecting the safe, stable, and economical operation of the distribution network. Meanwhile, while adjustable loads and distributed energy storage systems possess rapid response and bidirectional regulation capabilities, they are currently mostly operating in a decentralized and disordered manner, lacking effective coordination with distributed renewable energy sources and failing to fully realize their potential for peak shaving, valley filling, fluctuation mitigation, and improving renewable energy absorption rates. Furthermore, as a major source of carbon emissions, the low-carbon transformation of the power system is imperative.

[0004] Traditional power distribution network optimization methods often aim to minimize network losses or operating costs, without systematically incorporating carbon emission factors into the joint decision-making of distributed renewable energy, adjustable loads, and energy storage. This leads to problems such as renewable energy curtailment and insufficient substitution of high-carbon power sources, which restricts the overall carbon emission reduction capacity of the power distribution network. Summary of the Invention

[0005] The purpose of this invention is to provide a method for controlling the low-carbon operation of a distribution network that integrates source, grid, load, and energy storage, a device for controlling the low-carbon operation of a distribution network that integrates source, grid, load, and energy storage, a machine-readable storage medium, and an electronic device. This method can realize the low-carbon operation of the source, grid, load, and energy storage system and effectively support the optimized scheduling of distribution networks that include distributed new energy sources, adjustable loads, and energy storage.

[0006] To achieve the above objectives, the first aspect of this application provides a method for low-carbon operation control of distribution networks with coordinated generation, grid, load, and storage, comprising: The system acquires operational data of the power generation, grid, load and energy storage coordinated system over a preset time period. The operational data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value and total power generation. Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined with the goal of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. Based on the aforementioned optimal operating strategy, the power distribution network is operated and controlled.

[0007] In this embodiment of the application, the optimization objective is expressed as: , , in, For a preset time period; For each time point within a preset time period; The load value during peak electricity consumption periods takes into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; Weighting of low-carbon load indicators; Weights for power-low carbon indicators.

[0008] In this embodiment of the application, the preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints; The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

[0009] In this embodiment of the application, the step of determining the optimal operating strategy based on the operating data of the source-grid-load-storage coordinated system over a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function, includes: Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined from a preset set of operating strategies by using a particle swarm optimization algorithm with the goal of minimizing the low-carbon exponential function.

[0010] In this embodiment of the application, the step of determining the optimal operating strategy from a preset set of operating strategies based on the operating data of the source-grid-load-storage coordinated system over a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function, includes: Based on the operation data of the source-grid-load-storage coordinated system over a preset time period, the particle population is initialized and the initial hyperparameter combination is determined; wherein, each individual particle corresponds to an operation strategy. Based on the initial hyperparameter combination, the optimal hyperparameter combination is determined using a Bayesian optimization algorithm; Based on the optimal combination of hyperparameters, with minimizing the low-carbon exponential function as the optimization objective, the optimal operating strategy is obtained by searching for operating strategies in a preset set of operating strategies.

[0011] In this embodiment of the application, the initialization of the particle population and determination of the initial hyperparameter combination based on the operating data of the source-grid-load-storage coordinated system over a preset time period includes: The particle population is divided into a main group and multiple slave groups, wherein the main group is used to summarize global information; The primary group and each secondary group are initialized separately to obtain the initial hyperparameter combination.

[0012] In this embodiment of the application, the step of optimizing the operating strategy based on the optimal hyperparameter combination, with minimizing the low-carbon exponential function as the optimization objective, and obtaining the optimal operating strategy from a preset set of operating strategies, includes: A1: For each particle in the swarm, the fitness value of each particle is obtained based on the corresponding running strategy and low-carbon exponential function. A2: Based on the fitness values ​​of each particle, determine the local optimal particle of each swarm; A3: Update the particle velocity and particle position of the local optimal particle in each of the subgroups; A4: Based on the local optimal particles of each slave group, update the particles of the main group to obtain the updated main group; A5: Calculate the fitness values ​​of the particles in the updated main group to obtain the fitness values ​​of each main group particle. A6: Based on the fitness values ​​of each main group particle, determine the globally optimal particle from the particles of the main group; A7: Send the globally optimal particle to each of the slave groups to update each of the slave groups; A8: Determine if the maximum number of iterations has been reached: A9: Given that the maximum number of iterations has been reached, the optimal running strategy is obtained based on the running strategy corresponding to the optimal particle in the main group; A10: If the maximum number of iterations has been reached, update the particle velocity and particle position in the main group and each of the slave groups, and then jump to execute A1.

[0013] In this embodiment of the application, updating the particles of the main group based on the locally optimal particles of each slave group to obtain the updated main group includes: Based on the local optimal particles of each subgroup, the optimal solution of the subgroup is determined, wherein the optimal solution of the subgroup is the optimal particle in all subgroups; Determine whether the optimal solution of the slave group is better than the historical optimal solution of the particles in the main group; If it is determined that the optimal solution of the slave group is better than the optimal solution of the particle history of the main group, the optimal solution of the slave group is used as the optimal solution of the particle history of the main group to update the particles of the main group and obtain the updated main group.

[0014] In this embodiment of the application, updating the particle velocity and particle position of the main group includes: The particle velocity and particle position of the main group are updated using a dynamic jitter update formula, which is as follows: , in, For particles speed, For particles speed, For inertial weights, Indicates the first Round iteration, For particles Location, This is the optimal solution in the particle's history. To be the optimal solution for the group, and As a learning factor, and A random number within the interval [0, 1). This is a random disturbance factor.

[0015] The second aspect of this application provides a low-carbon operation control device for a distribution network that integrates source-grid-load-storage coordination, comprising: The acquisition module is used to acquire the operating data of the source-grid-load-storage coordinated system within a preset time period. The operating data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value, and total power generation. The determination module is used to determine the optimal operating strategy based on the operating data of the source-grid-load-storage coordinated system over a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. The control module is used to control the operation of the distribution network based on the optimal operating strategy.

[0016] In this embodiment of the application, the optimization objective is expressed as: , , in, For a preset time period; For each time point within a preset time period; The load value during peak electricity consumption periods takes into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; Weighting of low-carbon load indicators; Weights for power-low carbon indicators.

[0017] In this embodiment of the application, the preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints; The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

[0018] A third aspect of this application provides an electronic device, the electronic device comprising: At least one processor; A memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-mentioned source-grid-load-storage coordinated low-carbon operation control method for distribution networks by executing the instructions stored in the memory.

[0019] A fourth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned source-grid-load-storage coordinated low-carbon operation control method for distribution networks.

[0020] The above technical solution acquires operational data of the source-grid-load-storage coordinated system over a preset time period. This operational data includes load values, energy storage charging load values, energy storage discharging power values, photovoltaic output power values, and total power generation. Based on this operational data, and under preset constraints, an optimal operating strategy is determined with the goal of minimizing the low-carbon exponential function. This optimal operating strategy includes energy storage charging / discharging control power, load control power, and photovoltaic output control power. Based on this optimal operating strategy, the distribution network is controlled. By acquiring real-time operational data such as load, energy storage charging / discharging power, photovoltaic output, and total power generation within the preset time period, the optimization model accurately reflects the actual operating status of the system, providing a reliable data foundation and timeliness guarantee for the formulation of the optimal strategy. By minimizing the low-carbon exponential function as the optimization objective, the system is guided in principle to proactively reduce operational carbon emissions, prioritizing the use of clean energy and energy storage regulation capabilities to replace high-carbon power sources, thereby effectively suppressing the carbon footprint. Solving under preset constraints ensures that the obtained optimal operating strategy is both physically feasible and safe and reliable. The final output of energy storage charging and discharging control power, load control power, and photovoltaic output control power covers the main adjustable resources within the system. It can adjust the energy storage charging and discharging status, flexible load response level, and photovoltaic output in real time, enabling the actual system to operate along a low-carbon optimization trajectory. This forms a complete process from data acquisition and low-carbon optimization decision-making to closed-loop control, realizing the low-carbon operation of the source-grid-load-storage system and effectively supporting the optimized scheduling of the distribution network, which includes distributed new energy sources, adjustable loads, and energy storage.

[0021] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 The illustration shows a schematic flowchart of a low-carbon operation control method for a distribution network with source-grid-load-storage coordination according to an embodiment of this application; Figure 2 A schematic diagram illustrating a source-grid-load-storage collaborative architecture according to an embodiment of this application is shown. Figure 3 This illustration schematically shows a source-grid-load-storage collaborative system architecture based on an intelligent fusion terminal according to an embodiment of this application; Figure 4 A schematic diagram of a Bayesian multi-particle swarm optimization algorithm model according to an embodiment of this application is shown. Figure 5 This schematic diagram illustrates the structure of a low-carbon operation control device for a power distribution network with source-grid-load-storage coordination according to an embodiment of this application. Figure 6 The diagram illustrates the internal structure of a computer device according to an embodiment of this application.

[0023] Explanation of reference numerals in the attached figures 410 - Acquisition Module; 420 - Determination Module; 430 - Control Module; A01 - Processor; A02 - Network Interface; A03 - Internal Memory; A04 - Display Screen; A05 - Input Device; A06 - Non-Volatile Storage Medium; B01 - Operating System; B02 - Computer Program. Detailed Implementation

[0024] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0025] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0026] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0027] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0028] Please refer to Figure 1 , Figure 1 This illustration schematically shows a flowchart of a distribution network low-carbon operation control method based on a source-grid-load-storage coordination according to an embodiment of this application. This embodiment provides a distribution network low-carbon operation control method based on a source-grid-load-storage coordination approach, comprising the following steps: Step 210: Obtain the operating data of the source-grid-load-storage coordinated system within a preset time period. The operating data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value, and total power generation. In this embodiment, the aforementioned source-grid-load-storage coordinated system includes: traditional rigid loads, adjustable loads, photovoltaic power generation, and energy storage equipment, etc. Please refer to... Figure 2 , Figure 2This diagram schematically illustrates a source-grid-load-storage collaborative architecture according to an embodiment of this application. Edge computing intelligent converged terminals can be deployed in distribution substations. Various resources within the substations include adjustable loads, photovoltaic equipment, and energy storage devices. Adjustable loads, photovoltaics, and energy storage are connected to the distribution transformer via smart switches, photovoltaic grid-connection switches, and energy storage control switches, respectively. Rigid loads are directly connected to the distribution transformer. The aforementioned preset time period can be defined according to actual conditions, for example, it can be 24 hours. For ease of storage, the aforementioned load value can be a load curve value. The aforementioned load curve describes the change of power load over time; the horizontal axis can be time, and the vertical axis can be power value. The load curve value represents the power value corresponding to each time period. The aforementioned energy storage charging load value can be an energy storage charging power curve value. The aforementioned energy storage charging power curve can refer to the curve of energy storage charging power changing over time; the horizontal axis can be time (usually hours or minutes), and the vertical axis is charging power. Accordingly, the energy storage charging power curve value represents the charging power of the energy storage device at each time period. Similarly, the energy storage discharging power value can be the discharging power of the energy storage device at each time period. The photovoltaic (PV) output power value can be a PV output curve value, which refers to a curve showing the change of PV output power over time. The horizontal axis can be time, and the vertical axis can be PV power generation. The total power generation refers to the sum of the instantaneous output of all power sources in the system (including energy storage discharge). The above operating data can be obtained by monitoring the source-grid-load-storage coordinated system, which is existing technology and will not be elaborated further here.

[0029] Step 220: Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, determine the optimal operating strategy with the goal of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. In this embodiment, the low-carbon exponential function can be used to quantify the carbon emission level of the source-grid-load-storage coordinated system during operation. By introducing preset constraints such as system power balance, equipment output upper and lower limits, energy storage state of charge and load adjustable range into the function, and using optimization algorithms (such as particle swarm optimization) to solve for the optimal operating strategy that minimizes the value of the low-carbon exponential function, it is possible to maximize the absorption of renewable energy and reduce the use of fossil energy while ensuring the safe and stable operation of the system, thereby achieving low carbon emissions for the entire system.

[0030] In some embodiments, the optimization objective can be expressed as: , , in, For a preset time period; For each time point within a preset time period; The load value during peak electricity consumption periods takes into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; The weighting of low-carbon load indicators can be preset as needed; The weights for low-carbon power indicators can be preset as needed.

[0031] In the above formula This is the low-carbon index function. By setting this low-carbon index function, the carbon emission level of the source-grid-load-storage coordinated system during operation can be quickly and accurately quantified, thus helping to accurately represent the optimization target.

[0032] In some embodiments, the preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints. The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. In this embodiment, the power balance constraint described above can be expressed as: , in, This refers to the power of the distribution network.

[0033] The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; In this embodiment, the above-mentioned load balancing constraint can be expressed as: , in, The rigid load value can be obtained from the rigid load curve. The transferable load value (i.e., adjustable load value) can be obtained from the transferable load curve.

[0034] The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. In this embodiment, the aforementioned new energy output constraint can be expressed as: ,in, The rated power of new energy power generation can be determined in advance.

[0035] The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

[0036] In this embodiment, the constraints of the energy storage device described above can be expressed as: ,in, The rated power for charging / discharging energy storage devices can be determined in advance.

[0037] By imposing constraints on power balance, load balance, renewable energy output, and energy storage equipment, these constraints directly correspond to the physical limits and safety boundaries of the distribution network. The resulting optimal operating strategy naturally meets the requirements for safe and stable system operation and will not lead to risks such as voltage overruns, overcharging and over-discharging of energy storage, line overload, or power backflow caused by excessive pursuit of low carbon emissions. This helps to achieve a balance between low carbon goals and safety constraints.

[0038] Step 230: Based on the optimal operating strategy, perform operation control on the distribution network.

[0039] In this embodiment, after obtaining the optimal operating strategy, the distribution network can be controlled according to the optimal operating strategy. Specifically, control commands can be generated based on the optimal operating strategy and issued to various types of switches, which then perform corresponding actions.

[0040] For example, please see Figure 3 , Figure 3 This diagram schematically illustrates a source-grid-load-storage coordinated system architecture based on an intelligent fusion terminal according to an embodiment of this application. Edge computing intelligent fusion terminals are deployed in the distribution transformer area, and various resources within the area include adjustable loads, photovoltaic equipment, and energy storage equipment. Adjustable loads, photovoltaics, and energy storage are connected to the system via smart switches, photovoltaic grid-connected switches, and energy storage control switches, respectively. The intelligent fusion terminal employs container technology, running four functional apps within the container: a photovoltaic monitoring app, an electricity consumption information collection app, an energy storage app, and a distribution monitoring app. These apps collect electrical quantity data from the aforementioned switching devices. The source-grid-load-storage coordinated app performs "source-grid-load-storage" scheduling strategy calculations, formulates a source-grid-load-storage coordinated strategy, distributes it to the four functional apps, and generates control commands to issue to various switches, which then execute corresponding actions.

[0041] In the above implementation process, the operating data of the source-grid-load-storage coordinated system within a preset time period is acquired. This operating data includes load values, energy storage charging load values, energy storage discharging power values, photovoltaic output power values, and total power generation. Based on this operating data, and under preset constraints, an optimal operating strategy is determined with the goal of minimizing the low-carbon exponential function. This optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. Based on this optimal operating strategy, the distribution network is controlled. By acquiring real-time operating data such as load, energy storage charging and discharging power, photovoltaic output, and total power generation within the preset time period, the optimization model can accurately reflect the actual operating status of the system, providing a reliable data foundation and timeliness guarantee for the formulation of the optimal strategy. By minimizing the low-carbon exponential function as the optimization objective, the system is guided in principle to proactively reduce carbon emissions, prioritizing the use of clean energy and energy storage regulation capabilities to replace high-carbon power sources, thereby effectively suppressing the carbon footprint. Solving under preset constraints ensures that the obtained optimal operating strategy is both physically feasible and safe and reliable. The final output of energy storage charging and discharging control power, load control power, and photovoltaic output control power covers the main adjustable resources within the system. It can adjust the energy storage charging and discharging status, flexible load response level, and photovoltaic output in real time, enabling the actual system to operate along a low-carbon optimization trajectory. This forms a complete process from data acquisition and low-carbon optimization decision-making to closed-loop control, realizing the low-carbon operation of the source-grid-load-storage system and effectively supporting the optimized scheduling of the distribution network, which includes distributed new energy sources, adjustable loads, and energy storage.

[0042] In some embodiments, to quickly and stably obtain a low-carbon optimal operation strategy that meets the constraints, particle swarm optimization (PSO) can be used for optimization. That is, based on the operation data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operation strategy is determined with the goal of minimizing the low-carbon exponential function, including: Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined from a preset set of operating strategies by using a particle swarm optimization algorithm with the goal of minimizing the low-carbon exponential function.

[0043] In this embodiment, each candidate operating strategy (including energy storage charging and discharging control power, load control power, and photovoltaic output control power) is first encoded as an individual particle in a particle swarm. All particles together constitute an initial population, i.e., a preset set of operating strategies. Then, using the operating data (load value, energy storage charging and discharging power, photovoltaic output, and total power generation) of the current preset time period as input, a low-carbon exponential function value is calculated for the strategy corresponding to each particle, and this value is used as the particle's fitness. During the iteration process, the particle swarm optimization algorithm dynamically updates the particle's velocity and position based on the individual particle's historical optimal position and the global optimal position of the population, thereby efficiently searching for the optimal solution that minimizes the low-carbon exponential function in the strategy space. After each update, it is necessary to verify whether the strategy represented by the particle meets preset constraints (such as power balance, energy storage state of charge limit, photovoltaic maximum output limit, load adjustment range, etc.). If not, a penalty function or boundary constraint processing mechanism guides it to the feasible region. After multiple iterations, the particle swarm gradually converges to the global optimal or near-optimal solution, and the strategy corresponding to this solution is the optimal operating strategy.

[0044] The above process does not require exhaustive traversal of the strategy set, and can quickly lock the optimal control scheme under the low-carbon operation objective in the continuous or discrete decision space. It can obtain the optimal low-carbon operation strategy that satisfies complex constraints quickly and stably while ensuring the accuracy of the solution.

[0045] It should be noted that the above particle swarm optimization algorithm can be a conventional particle swarm optimization algorithm or a variant thereof, such as the master-slave particle swarm optimization algorithm.

[0046] In some embodiments, the step of determining the optimal operating strategy from a preset set of operating strategies based on the operating data of the source-grid-load-storage coordinated system over a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function, using a particle swarm optimization algorithm, includes: First, based on the operating data of the source-grid-load-storage collaborative system over a preset time period, the particle population is initialized and the initial hyperparameter combination is determined; wherein, each individual particle corresponds to an operating strategy. In this embodiment, the particle swarm can be initialized based on the operational data of the source-grid-load-storage coordinated system over a preset time period to obtain an initial hyperparameter combination. First, system parameters and particle swarm optimization (PSO) algorithm parameters are configured, including photovoltaic, adjustable load, energy storage, and parameters such as the population size, maximum number of iterations, and acceleration factor of the PSO algorithm. Then, the particle swarm is initialized; each particle corresponds to an optimization scheme, including the power of the adjustable load and the charging / discharging power of the energy storage. Specifically, the particle swarm consists of multiple particles, each corresponding to a complete operational strategy. This strategy includes decision variables such as energy storage charging / discharging control power, load control power, and photovoltaic output control power. During initialization, based on the actual operational data over the preset time period within a preset boundary, each particle is randomly assigned an initial position and initial velocity, thus forming an initial strategy solution set. The aforementioned initial hyperparameter combination includes algorithm operational parameters such as the inertia weight, acceleration factor, population size, and maximum number of iterations of the PSO algorithm. These hyperparameters can be set empirically. Through the above initialization operation, a feasible initial solution space and algorithm operating environment can be established for subsequent iterative particle swarm search.

[0047] Then, based on the initial hyperparameter combination, the optimal hyperparameter combination is determined using a Bayesian optimization algorithm; In this embodiment, the initial hyperparameter combination can be optimized and adjusted using a Bayesian optimization algorithm to obtain the optimal hyperparameter combination. Specifically, the initial model parameters for Bayesian optimization are first set, including the initial hyperparameters of the mean function and covariance function (such as the radial basis function kernel function) of the Gaussian process, and the type of acquisition function (such as the desired improvement). Then, using the initial hyperparameter combination as the starting point, a Gaussian process regression model is constructed to fit the functional relationship between the hyperparameter combination and the target performance (such as the expected convergence accuracy or computational efficiency). Gaussian process regression not only provides the predicted mean of the target performance under each candidate hyperparameter combination, but also provides the prediction uncertainty (i.e., variance). Based on this, points are selected in the hyperparameter search space using the acquisition function, balancing "development" (selecting regions with good prediction performance) and "exploration" (selecting regions with high uncertainty), iteratively generating the next set of hyperparameter combinations to be evaluated. After each point selection, the performance feedback of the hyperparameter combination is obtained through a preset fast evaluation criterion (such as low-cost simulation or surrogate model based on historical running data), and the new sample points are added to the training set to update the Gaussian process regression model, making its approximation of the target function gradually more accurate. Repeat the above process until the preset number of iterations or convergence condition is reached. Finally, select the combination of hyperparameters that best achieves the target performance from all evaluated combinations; this is the optimal hyperparameter combination. The entire process requires no manual parameter tuning or exhaustive search, efficiently obtaining the optimal hyperparameter configuration for the particle swarm optimization algorithm with fewer evaluations.

[0048] For example, the objective of the Bayesian optimization algorithm can be set as: , in, For combinations of hyperparameters (such as learning factors) in particle swarm optimization algorithms, Hyperparameter combination Mapping to model generalization performance This represents the optimal combination of hyperparameters.

[0049] According to Bayes' theorem: , Where GP is the Gaussian distribution function. Let covariance matrix be the variance matrix. Let be the probability distribution function. This is the mathematical expectation value. Through continuous iterative updates, it becomes... Ultimately, the optimized hyperparameters are obtained.

[0050] The Bayesian optimization process described above can be implemented using existing technologies, so it will not be elaborated further here.

[0051] Finally, based on the optimal combination of hyperparameters, with minimizing the low-carbon exponential function as the optimization objective, the optimal operating strategy is obtained by searching the preset set of operating strategies.

[0052] In this embodiment, the aforementioned preset set of operating strategies can be determined in advance based on historical operating strategies or experience, involving multiple operating strategies. After determining the optimal hyperparameter combination, the strategy optimization is performed according to the steps of the particle swarm optimization algorithm to obtain the optimal operating strategy.

[0053] By initializing the particle swarm based on the operational data of the source-grid-load-storage collaborative system over a preset time period, and using the Bayesian optimization algorithm to determine the optimal hyperparameter combination based on the initial hyperparameter combination, the optimal hyperparameter configuration of the particle swarm optimization algorithm can be obtained. Thus, based on the optimal hyperparameter combination, the optimal operating strategy can be quickly and accurately obtained from the preset operating strategy set with the goal of minimizing the low-carbon exponential function.

[0054] In some embodiments, when using a master-slave particle swarm optimization algorithm for strategy optimization, the initialization of the particle swarm based on the operating data of the source-grid-load-storage collaborative system over a preset time period, and the determination of the initial hyperparameter combination, includes: First, the particle population is divided into a main group and multiple slave groups, with the main group used to aggregate global information; In this embodiment, 2N particles are initialized. N particles can be randomly selected to form the main group, and the remaining N particles are divided into N / M slave groups (where M is the number of particles in each slave group). The main group learns from the superior particles provided by the slave groups, thereby improving its optimization performance.

[0055] Then, the main group and each slave group are initialized respectively to obtain the initial hyperparameter combination.

[0056] In this embodiment, the initial hyperparameters can be initialized separately, and the resulting initial hyperparameter combinations include the initial hyperparameter combination of the main group and the initial hyperparameter combinations of each slave group.

[0057] It should be noted that after obtaining the initial hyperparameter combination of the main group and the initial hyperparameter combinations of each slave group, Bayesian optimization algorithm can be used to adjust and optimize them to obtain the optimal hyperparameter combination of the main group and the optimal hyperparameter combination of each slave group, which can be used for subsequent optimization.

[0058] In some implementations, the optimal operating strategy is obtained by optimizing the operating strategy within a pre-set set of operating strategies, based on the optimal hyperparameter combination and with the goal of minimizing the low-carbon exponential function. This includes: Step A1: For each particle in the swarm, obtain the fitness value of each particle based on the corresponding running strategy and low-carbon exponential function; In this embodiment, each individual particle is used as the input objective function (low-carbon index function) for the optimization scheduling strategy of the source-grid-load-storage system to calculate the objective function value; for each individual particle, its fitness value is determined by the objective function value generated by the optimization scheme, that is, the low-carbon operation index of the system.

[0059] Step A2: Based on the fitness values ​​of each particle, determine the local optimal particle for each swarm; In this embodiment, the particles in each swarm can be sorted according to their fitness values, and the particle with the highest fitness value can be taken as the local optimal particle, thus obtaining the local optimal particles of each swarm.

[0060] Step A3: Update the particle velocity and particle position of the locally optimal particle in each of the subgroups; In this embodiment, the above update can be performed according to the update method in the existing particle swarm algorithm, which will not be described in detail here.

[0061] Step A4: Based on the local optimal particles of each slave group, update the particles of the main group to obtain the updated main group; In this embodiment, after obtaining the local optimal particles of each subgroup, it is possible to determine whether the current particle's solution is better than its historical optimal solution based on the subgroup's optimal solution Xsubbest and the main group's historical optimal solution Xbest. If the current solution is better than the historical optimal solution, then the current solution is taken as the new historical optimal solution; otherwise, the historical optimal solution is maintained unchanged, thus updating the particles of the main group.

[0062] In some embodiments, updating the particles of the main group based on the locally optimal particles of each of the slave groups to obtain an updated main group includes: The first step is to determine the optimal solution for each subgroup based on the local optimal particles of each subgroup. The optimal solution for each subgroup is the optimal particle among all subgroups. In this embodiment, the fitness values ​​of the local optimal particles in each group are compared, and the particle with the largest fitness value is selected as the optimal solution for the group.

[0063] The second step is to determine whether the optimal solution of the slave group is better than the historical optimal solution of the particles in the main group. In this embodiment, the fitness value of the optimal solution of the slave group is compared with the fitness value of the best historical solution of the main group. If the fitness value of the optimal solution of the slave group is greater than the fitness value of the best historical solution of the main group, it means that the optimal solution of the slave group is better than the best historical solution of the main group; otherwise, it is not.

[0064] The third step is to determine that the optimal solution of the slave group is better than the optimal solution of the particle history of the main group, and then use the optimal solution of the slave group as the optimal solution of the particle history of the main group to update the particles of the main group, thereby obtaining the updated main group.

[0065] In this embodiment, if the optimal solution of the slave group is better than the optimal solution of the particle history of the main group, then the optimal solution of the slave group is adopted as the new optimal solution of the particle history of the main group to update the particles of the main group. Otherwise, the optimal solution of the particle history of the main group remains unchanged.

[0066] Through the above steps, the main group learns by relying on the superior particles provided by the slave group, thereby improving its optimization performance.

[0067] Step A5: Calculate the fitness values ​​of the particles in the updated main group to obtain the fitness values ​​of each main group particle; In this embodiment, the process of calculating the fitness value of particles in the main group is the same as that of calculating the fitness value in step A1, and will not be repeated here.

[0068] Step A6: Based on the fitness values ​​of each main group particle, determine the globally optimal particle from the particles of the main group; In this embodiment, the aforementioned globally optimal particle can be a particle with a high fitness value selected from the particles in the main group. Specifically, it can be sorted according to the fitness value from high to low, and then randomly selected from the top few particles as the globally optimal solution, thus obtaining the globally optimal particle.

[0069] Step A7: Send the globally optimal particle to each of the slave groups to update each slave group; Step A8: Determine if the maximum number of iterations has been reached: Step A9: Given that the maximum number of iterations has been reached, obtain the optimal running strategy based on the running strategy corresponding to the optimal particle in the main group; Step A10: If it is determined that the maximum number of iterations has been reached, update the particle velocity and particle position in the main group and each of the slave groups, and then proceed to step A1.

[0070] In this embodiment, the current iteration count is compared with the maximum iteration count. If the iteration count has reached the upper limit, the running strategy corresponding to the best particle in the main swarm is output as the optimal running strategy; otherwise, the velocity and position of each particle are updated to find a new individual solution and enter the next iteration. The above particle update can be performed according to the update method in the existing particle swarm algorithm, which will not be elaborated here.

[0071] In some embodiments, dynamic jitter updates can be performed on the main swarm particles to increase the algorithm's versatility and exploration capabilities. This involves updating the particle velocities and positions of the main swarm, including: The particle velocity and particle position of the main group are updated using a dynamic jitter update formula, which is as follows: , in, For particles speed, For particles speed, For inertial weights, Indicates the first Round iteration, For particles Location, This is the optimal solution in the particle's history. To be the optimal solution for the group, and As a learning factor, and A random number within the interval [0, 1). This is a random disturbance factor.

[0072] In this embodiment, a dynamic jittering update formula is obtained by introducing a random jittering term into the velocity update formula. The magnitude and direction of this term are randomly generated and vary within a certain range. The particle velocity update is subject to a certain degree of random disturbance, which helps to escape local optima and better explore the global solution space.

[0073] By combining Bayesian optimization and master-slave particle swarm optimization (PSO) algorithms, the operational strategy of a low-carbon operation model integrating source-grid-load-storage coordination is calculated. The population is divided into a master group and multiple slave groups, and Bayesian optimization is introduced to optimize and adjust the hyperparameters of the master and slave groups separately. Each subgroup evolves independently, using the standard PSO algorithm update formula for iterative updates; the master group learns from the superior particles provided by the subgroups, thereby improving its optimization performance. Through particle interaction between the master and slave groups, the optimal operational strategy can be quickly calculated.

[0074] To facilitate the explanation of the algorithm, a specific example is provided below. Please refer to [link / reference]. Figure 4 , Figure 4 A schematic diagram of a Bayesian multi-particle swarm optimization algorithm model according to an embodiment of this application is shown.

[0075] After obtaining the operational data of the source-grid-load-storage collaborative system over a preset time period, this operational data can be used as the raw dataset. The raw dataset undergoes preprocessing, including interpolation and cleaning, and is then divided into training and testing datasets. For the training dataset, a PSO model is used for initialization, followed by Bayesian optimization of the initial hyperparameters. Specifically, the initial model parameters for Bayesian optimization are first set, including the initial hyperparameters of the Gaussian process's mean function and covariance function (such as the radial basis function kernel), as well as the type of acquisition function (e.g., desired improvement). Then, using the initial hyperparameter combination as a starting point, a Gaussian process regression model is constructed to fit the functional relationship between the hyperparameter combination and the target performance (e.g., expected convergence accuracy or computational efficiency). Gaussian process regression not only provides the predicted mean of the target performance under each candidate hyperparameter combination but also provides the prediction uncertainty (i.e., variance). Based on this, points are selected within the hyperparameter search space using the acquisition function, iteratively generating the next set of hyperparameter combinations to be evaluated. After each point selection, performance feedback for the hyperparameter combination is obtained through a pre-defined rapid evaluation criterion (such as low-cost simulation or surrogate models based on historical operating data). New sample points are added to the training set, and the Gaussian process regression model is updated to progressively improve its approximation of the objective function. This process is repeated until a pre-defined number of iterations or convergence condition is reached. Finally, the optimal parameter combination is selected from all evaluated hyperparameter combinations to achieve the best target performance. After obtaining the optimal parameter combination, the PSO model is updated using it to obtain the optimized PSO model. The optimized PSO model can then be validated using a test dataset. Finally, the optimized PSO model is used to further refine the source-grid-load-storage coordinated strategy, i.e., the optimal operating strategy.

[0076] Please refer to Figure 5 , Figure 5 This schematic diagram illustrates the structure of a power grid low-carbon operation control device with source-grid-load-storage coordination according to an embodiment of this application. This embodiment provides a power grid low-carbon operation control device with source-grid-load-storage coordination, including an acquisition module 410, a determination module 420, and a control module 430, wherein: The acquisition module 410 is used to acquire the operating data of the source-grid-load-storage coordinated system during a preset time period. The operating data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value, and total power generation. The determination module 420 is used to determine the optimal operating strategy based on the operating data of the source-grid-load-storage coordinated system during a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. The control module 430 is used to control the operation of the distribution network based on the optimal operation strategy.

[0077] The optimization objective is expressed as: , , in, For a preset time period; For each time point within a preset time period; The load value during peak electricity consumption periods takes into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; Weighting of low-carbon load indicators; Weights for power-low carbon indicators.

[0078] The preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints. The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

[0079] The source-grid-load-storage coordinated distribution network low-carbon operation control device includes a processor and a memory. The aforementioned acquisition module 410, determination module 420, and control module 430 are all stored in the memory as program units. The processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0080] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters enables coordinated low-carbon operation control of the distribution network, integrating power generation, grid, load, and storage.

[0081] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0082] This invention provides a machine-readable storage medium storing a program that, when executed by a processor, implements the source-grid-load-storage coordinated low-carbon operation control method for distribution networks.

[0083] This invention provides a processor for running a program, wherein the program executes the source-grid-load-storage coordinated low-carbon operation control method for distribution networks.

[0084] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown in the figure, the computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05, and a memory (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A06. The network interface A02 is used for communication with external terminals via a network connection. When the computer program is executed by the processor A01, it implements a low-carbon operation control method for a power distribution network that integrates power generation, grid, load, and storage. The display screen A04 can be an LCD screen or an e-ink display screen. The input device A05 can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0085] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0086] In one embodiment, the source-grid-load-storage coordinated low-carbon operation control device for distribution networks provided in this application can be implemented as a computer program, which can be implemented in the form of, for example... Figure 6The computer device shown runs on this system. The computer device's memory can store the various program modules that make up the low-carbon operation control device of the power distribution network that integrates source-grid-load-storage coordination, for example... Figure 5 The acquisition module 410, determination module 420, and control module 430 are shown. The computer program composed of these modules causes the processor to execute the steps in the source-grid-load-storage coordinated low-carbon operation control method for distribution networks described in the various embodiments of this application.

[0087] Figure 6 The computer device shown can be used as follows Figure 5 The acquisition module 410 in the power grid low-carbon operation control device for source-grid-load-storage coordination shown executes step 210. The computer device can execute step 220 through the determination module 420. The computer device can execute step 230 through the control module 430.

[0088] This application provides an electronic device comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the aforementioned source-grid-load-storage coordinated low-carbon operation control method for distribution networks by executing the instructions stored in the memory. When the processor executes the instructions, it performs the following steps: The system acquires operational data of the power generation, grid, load and energy storage coordinated system over a preset time period. The operational data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value and total power generation. Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined with the goal of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. Based on the aforementioned optimal operating strategy, the power distribution network is operated and controlled.

[0089] In one embodiment, the optimization objective is expressed as: , , in, For a preset time period; For each time point within a preset time period; The load value during peak electricity consumption periods takes into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; Weighting of low-carbon load indicators; Weights for power-low carbon indicators.

[0090] In one embodiment, the preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints. The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

[0091] In one embodiment, determining the optimal operating strategy based on the operating data of the source-grid-load-storage coordinated system over a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function, includes: Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined from a preset set of operating strategies by using a particle swarm optimization algorithm with the goal of minimizing the low-carbon exponential function.

[0092] In one embodiment, based on the operational data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operational strategy is determined using a particle swarm optimization algorithm from a pre-set set of operational strategies, with the goal of minimizing the low-carbon exponential function. This includes: Based on the operation data of the source-grid-load-storage coordinated system over a preset time period, the particle population is initialized and the initial hyperparameter combination is determined; wherein, each individual particle corresponds to an operation strategy. Based on the initial hyperparameter combination, the optimal hyperparameter combination is determined using a Bayesian optimization algorithm; Based on the optimal combination of hyperparameters, with minimizing the low-carbon exponential function as the optimization objective, the optimal operating strategy is obtained by searching for operating strategies in a preset set of operating strategies.

[0093] In one embodiment, the initialization of the particle population and determination of the initial hyperparameter combination based on the operational data of the source-grid-load-storage coordinated system over a preset time period includes: The particle population is divided into a main group and multiple slave groups, wherein the main group is used to summarize global information; The primary group and each secondary group are initialized separately to obtain the initial hyperparameter combination.

[0094] In one embodiment, the step of optimizing the operating strategy based on the optimal hyperparameter combination, with minimizing the low-carbon exponential function as the optimization objective, and obtaining the optimal operating strategy from a preset set of operating strategies, includes: A1: For each particle in the swarm, the fitness value of each particle is obtained based on the corresponding running strategy and low-carbon exponential function. A2: Based on the fitness values ​​of each particle, determine the local optimal particle of each swarm; A3: Update the particle velocity and particle position of the local optimal particle in each of the subgroups; A4: Based on the local optimal particles of each slave group, update the particles of the main group to obtain the updated main group; A5: Calculate the fitness values ​​of the particles in the updated main group to obtain the fitness values ​​of each main group particle. A6: Based on the fitness values ​​of each main group particle, determine the globally optimal particle from the particles of the main group; A7: Send the globally optimal particle to each of the slave groups to update each of the slave groups; A8: Determine if the maximum number of iterations has been reached: A9: Given that the maximum number of iterations has been reached, the optimal running strategy is obtained based on the running strategy corresponding to the optimal particle in the main group; A10: If the maximum number of iterations has been reached, update the particle velocity and particle position in the main group and each of the slave groups, and then jump to execute A1.

[0095] In one embodiment, updating the particles of the main group based on the locally optimal particles of each of the slave groups to obtain the updated main group includes: Based on the local optimal particles of each subgroup, the optimal solution of the subgroup is determined, wherein the optimal solution of the subgroup is the optimal particle in all subgroups; Determine whether the optimal solution of the slave group is better than the historical optimal solution of the particles in the main group; If it is determined that the optimal solution of the slave group is better than the optimal solution of the particle history of the main group, the optimal solution of the slave group is used as the optimal solution of the particle history of the main group to update the particles of the main group and obtain the updated main group.

[0096] In one embodiment, updating the particle velocity and particle position of the main group includes: The particle velocity and particle position of the main group are updated using a dynamic jitter update formula, which is as follows: , in, For particles speed, For particles speed, For inertial weights, Indicates the first Round iteration, For particles Location, This is the optimal solution in the particle's history. To be the optimal solution for the group, and As a learning factor, and A random number within the interval [0, 1). This is a random disturbance factor.

[0097] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0099] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0100] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0101] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0102] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0103] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0104] It should also be noted that 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 process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0105] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for low-carbon operation control of a distribution network with coordinated generation, grid, load, and storage, characterized in that, include: The system acquires operational data of the power generation, grid, load and energy storage coordinated system over a preset time period. The operational data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value and total power generation. Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined with the goal of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. Based on the aforementioned optimal operating strategy, the power distribution network is operated and controlled.

2. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 1, characterized in that, The optimization objective is expressed as: ， ， in, For a preset time period; For each time point within a preset time period; The load value is calculated during peak electricity consumption periods, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the energy storage system. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; Weighting of low-carbon load indicators; Weights for power-low carbon indicators.

3. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 1, characterized in that, The preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints. The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

4. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 1, characterized in that, Based on the operational data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operational strategy is determined with the goal of minimizing the low-carbon exponential function, including: Based on the operating data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, the optimal operating strategy is determined from a preset set of operating strategies by using a particle swarm optimization algorithm with the goal of minimizing the low-carbon exponential function.

5. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 4, characterized in that, Based on the operational data of the source-grid-load-storage coordinated system over a preset time period, and under preset constraints, with the optimization objective of minimizing the low-carbon exponential function, the optimal operational strategy is determined using a particle swarm optimization algorithm from a preset set of operational strategies, including: Based on the operation data of the source-grid-load-storage coordinated system over a preset time period, the particle population is initialized and the initial hyperparameter combination is determined; wherein, each individual particle corresponds to an operation strategy. Based on the initial hyperparameter combination, the optimal hyperparameter combination is determined using a Bayesian optimization algorithm; Based on the optimal combination of hyperparameters, with minimizing the low-carbon exponential function as the optimization objective, the optimal operating strategy is obtained by searching for operating strategies in a preset set of operating strategies.

6. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 5, characterized in that, The process of initializing the particle population and determining the initial hyperparameter combination based on the operational data of the source-grid-load-storage coordinated system over a preset time period includes: The particle population is divided into a main group and multiple slave groups, wherein the main group is used to summarize global information; The primary group and each secondary group are initialized separately to obtain the initial hyperparameter combination.

7. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 6, characterized in that, Based on the optimal hyperparameter combination, with minimizing the low-carbon exponential function as the optimization objective, the optimal operating strategy is obtained by searching within a pre-set set of operating strategies, including: A1: For each particle in the swarm, the fitness value of each particle is obtained based on the corresponding running strategy and low-carbon exponential function. A2: Based on the fitness values ​​of each particle, determine the local optimal particle of each swarm; A3: Update the particle velocity and particle position of the local optimal particle in each of the subgroups; A4: Based on the local optimal particles of each slave group, update the particles of the main group to obtain the updated main group; A5: Calculate the fitness values ​​of the particles in the updated main group to obtain the fitness values ​​of each main group particle. A6: Based on the fitness values ​​of each main group particle, determine the globally optimal particle from the particles of the main group; A7: Send the globally optimal particle to each of the slave groups to update each of the slave groups; A8: Determine if the maximum number of iterations has been reached: A9: Given that the maximum number of iterations has been reached, the optimal running strategy is obtained based on the running strategy corresponding to the optimal particle in the main group; A10: If the maximum number of iterations has been reached, update the particle velocity and particle position in the main group and each of the slave groups, and then jump to execute A1.

8. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 7, characterized in that, The step of updating the particles of the main group based on the locally optimal particles of each of the slave groups to obtain the updated main group includes: Based on the local optimal particles of each subgroup, the optimal solution of the subgroup is determined, wherein the optimal solution of the subgroup is the optimal particle in all subgroups; Determine whether the optimal solution of the slave group is better than the historical optimal solution of the particles in the main group; If it is determined that the optimal solution of the slave group is better than the optimal solution of the particle history of the main group, the optimal solution of the slave group is used as the optimal solution of the particle history of the main group to update the particles of the main group and obtain the updated main group.

9. The low-carbon operation control method for distribution networks with source-grid-load-storage coordination according to claim 7, characterized in that, Updating the particle velocities and positions of the main group includes: The particle velocity and particle position of the main group are updated using a dynamic jitter update formula, which is as follows: ， in, For particles speed, For particles speed, For inertial weights, Indicates the first Round iteration, For particles Location, This is the optimal solution in the particle's history. To be the optimal solution for the group, and As a learning factor, and A random number within the interval [0, 1). This is a random disturbance factor.

10. A low-carbon operation control device for a distribution network with coordinated generation, grid, load, and storage, characterized in that, include: The acquisition module is used to acquire the operating data of the source-grid-load-storage coordinated system within a preset time period. The operating data includes load value, energy storage charging load value, energy storage discharging power value, photovoltaic output power value, and total power generation. The determination module is used to determine the optimal operating strategy based on the operating data of the source-grid-load-storage coordinated system over a preset time period, under preset constraints, with the optimization objective of minimizing the low-carbon exponential function. The optimal operating strategy includes energy storage charging and discharging control power, load control power, and photovoltaic output control power. The control module is used to control the operation of the distribution network based on the optimal operating strategy.

11. The source-grid-load-storage coordinated low-carbon operation control device for distribution networks according to claim 10, characterized in that, The optimization objective is expressed as: ， ， in, For a preset time period; For each time point within a preset time period; The load value is calculated during peak electricity consumption periods, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the energy storage system. The load value is calculated during off-peak electricity hours, taking into account energy storage, adjustable loads, and the optimized coordination between the distribution network and the power grid. This represents the total load value of the source-grid-load-storage coordinated system. This is an adjustable load value; This represents the energy storage charging load value. This refers to the photovoltaic power output value. This represents the energy storage discharge power value. The total power generation capacity of the power generation, grid-load-storage coordinated system; Weighting of low-carbon load indicators; Weights for power-low carbon indicators.

12. The source-grid-load-storage coordinated low-carbon operation control device for distribution networks according to claim 10, characterized in that, The preset constraints include: power balance constraints, load balance constraints, new energy output constraints, and energy storage device constraints. The power balance constraint is that the total power generated by the source-grid-load-storage coordinated system is equal to the sum of the energy storage discharge power, the photovoltaic output power, and the power of the distribution network. The load balance constraint is that the load of the source-grid-load-storage coordinated system during a preset time period is equal to the sum of the rigid load and the adjustable load; The constraint on new energy output is that the photovoltaic output power shall not exceed the rated power of the new energy power generation. The constraint for the energy storage device is that the energy storage discharge power does not exceed the rated charge and discharge power of the energy storage device.

13. An electronic device, characterized in that, The electronic device includes: At least one processor; A memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the source-grid-load-storage coordinated low-carbon operation control method for distribution networks according to any one of claims 1 to 9 by executing the instructions stored in the memory.

14. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the distribution network low-carbon operation control method according to any one of claims 1 to 9.

Images