Hybrid power station optimization method and device, equipment, storage medium

Abstract

The application provides a hybrid energy power station optimization method and device, equipment and storage medium, and belongs to the technical field of energy power station optimization. The method comprises the following steps: establishing a node characteristic vector matrix based on electrical parameters and real-time operation data of each node in a power grid topology structure; establishing an energy storage characteristic vector matrix based on physical parameters of each energy storage module; constructing a correlation matrix representing the matching degree of the node characteristic vector and the energy storage characteristic vector by calculating the similarity of the node characteristic vector and the energy storage characteristic vector; obtaining an optimal solution set of each energy storage module by using a multi-objective particle swarm algorithm based on the node characteristic vector matrix, the energy storage characteristic vector matrix and optimization target parameters; and obtaining node power and node voltage in the power grid by using an energy management module, and optimizing output parameters of the multiple energy storage modules based on the correlation matrix in response to the node power or the node voltage not belonging to the range of the optimal solution set. The application can improve the operation efficiency of the power grid.

Description

Technical Field

[0001] This application belongs to the field of energy power plant optimization technology, and more specifically, relates to a method, apparatus, equipment, and storage medium for optimizing a hybrid energy power plant. Background Technology

[0002] With the continued growth of global energy demand and the accelerated transformation of the energy structure, the proportion of renewable energy in electricity supply is increasing. However, renewable energy is characterized by intermittency and volatility, posing a significant challenge to the stable operation of the power system. To effectively address this challenge, energy storage technology has emerged and developed rapidly. Energy storage systems can store energy when there is a surplus of renewable energy generation and release energy when there is a shortage, playing a role in "peak shaving and valley filling," thereby improving the stability and reliability of the power system. Hybrid energy power plants, as a comprehensive energy system integrating multiple energy forms and energy storage devices, can fully leverage the advantages of different energy sources and energy storage devices to achieve efficient energy utilization and optimized allocation, becoming a current research hotspot and development direction in the energy field.

[0003] In the research and application of hybrid energy power plants, most current energy storage deployments place the energy storage devices on the generation side and rely on historical operating data and empirical formulas to regulate the energy storage devices. Under this regulation method, when the grid node voltage changes, the energy storage may be unable to effectively suppress voltage exceedances or alleviate line congestion in a timely manner, leading to a decrease in grid operating efficiency. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a method, apparatus, equipment, and storage medium for optimizing hybrid energy power plants. Energy storage modules are installed on the generation, transmission, and distribution sides, and the adjustment parameters of each energy storage module can be optimized based on the power grid topology, thereby improving the operating efficiency of the power grid.

[0005] A first aspect of this application provides a hybrid power plant optimization method, applied to a hybrid power plant, the hybrid power plant including an energy management module and multiple energy storage modules, the multiple energy storage modules being respectively disposed on the generation side, transmission side, and distribution side; the hybrid power plant optimization method includes:

[0006] A node feature vector matrix is ​​established based on the electrical parameters and real-time operating data of each node in the power grid topology. Each row of the node feature vector matrix corresponds to the node feature vector of a node, and each column corresponds to the performance parameters of the node.

[0007] An energy storage characteristic vector matrix is ​​established based on the physical parameters of each energy storage module. Each row of the energy storage characteristic vector matrix corresponds to the energy storage characteristic vector of an energy storage module, and each column corresponds to the performance parameters of the energy storage module.

[0008] By calculating the similarity between the node feature vector and the energy storage characteristic vector, an association matrix representing the degree of matching between the two is constructed.

[0009] Based on the node feature vector matrix, energy storage characteristic vector matrix, and optimization target parameters, the optimal solution set for each energy storage module is obtained using the multi-objective particle swarm optimization algorithm.

[0010] The energy management module acquires the node power and node voltage in the power grid in real time. In response to the node power or node voltage not being within the range of the optimal solution set, the output parameters of multiple energy storage modules are optimized based on the correlation matrix.

[0011] A second aspect of this application provides a hybrid energy power plant optimization device, applied to a hybrid energy power plant. The hybrid energy power plant includes an energy management module and multiple energy storage modules, which are respectively disposed on the generation side, transmission side, and distribution side. The hybrid energy power plant optimization device includes:

[0012] The first data processing unit is used to establish a node feature vector matrix based on the electrical parameters and real-time operating data of each node in the power grid topology. Each row of the node feature vector matrix corresponds to the node feature vector of a node, and each column corresponds to the performance parameters of the node.

[0013] The second data processing unit is used to establish an energy storage characteristic vector matrix based on the physical parameters of each energy storage module. Each row of the energy storage characteristic vector matrix corresponds to the energy storage characteristic vector of an energy storage module, and each column corresponds to the performance parameters of the energy storage module.

[0014] The first computing unit is used to construct an association matrix representing the matching degree between the node feature vector and the energy storage characteristic vector by calculating the similarity between the two.

[0015] The second computing unit is used to obtain the optimal solution set of each energy storage module based on the node feature vector matrix, the energy storage characteristic vector matrix and the optimization target parameters, using the multi-objective particle swarm algorithm.

[0016] The parameter optimization unit is used to obtain the node power and node voltage in the power grid in real time using the energy management module. In response to the node power or node voltage not being within the range of the optimal solution set, it optimizes the output parameters of multiple energy storage modules based on the correlation matrix.

[0017] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described hybrid energy power plant optimization method.

[0018] In a fourth aspect of this application, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described hybrid power plant optimization method.

[0019] The beneficial effects of the hybrid energy power plant optimization method, apparatus, equipment, and storage medium provided in this application embodiment are as follows:

[0020] This application embodiment establishes a node feature vector matrix based on the electrical parameters and real-time operating data of each node in the power grid topology, and an energy storage characteristic vector matrix based on the physical parameters of each energy storage module. This accurately characterizes the operating status and characteristics of each node in the power grid, as well as the physical attributes and performance characteristics of each energy storage module. Furthermore, by calculating the similarity between the node feature vector and the energy storage characteristic vector, an association matrix representing their matching degree is constructed. This clarifies the matching relationship between each node in the power grid and different energy storage modules, enabling the rapid and accurate identification and adjustment of the most suitable energy storage module based on the actual needs of the node during subsequent optimization. Finally, the optimal solution set for each energy storage module is obtained using a multi-objective particle swarm optimization algorithm. If the node power or node voltage is not within the range of the optimal solution set, the output parameters of multiple energy storage modules are optimized based on the association matrix. This real-time monitoring and dynamic optimization method in this application embodiment can respond promptly to changes in the power grid operating status. When problems such as voltage exceeding limits or line congestion occur, the output parameters of the energy storage modules are quickly adjusted, effectively suppressing further deterioration of the problem, ensuring the stable operation of the power grid, and improving the operating efficiency and reliability of the power grid. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a hybrid energy power plant optimization method provided in an embodiment of this application;

[0023] Figure 2 A structural block diagram of a hybrid energy power plant optimization device provided in an embodiment of this application;

[0024] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0027] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a hybrid energy power plant optimization method according to an embodiment of this application. The method can be executed by electronic equipment. The hybrid energy power plant includes an energy management module and multiple energy storage modules, which are respectively located on the generation side, transmission side, and distribution side. The method may include steps S101 to S105.

[0028] In this embodiment, the hybrid energy power station also includes multiple energy generation modules, and energy storage modules are installed on the generation side, transmission side, and distribution side, with at least one energy storage module on each side. The energy management module is used to acquire operational data of the hybrid energy power station, including power generation data from each energy generation module, operational data from the energy storage modules, and operational data from the power grid connected to the hybrid energy power station, and sends the acquired data to electronic equipment for processing.

[0029] S101: Establish a node feature vector matrix based on the electrical parameters and real-time operating data of each node in the power grid topology.

[0030] Each row of the node feature vector matrix corresponds to the node feature vector of a node, and each column corresponds to the node's performance parameters.

[0031] In this embodiment, the power grid topology represents the physical connection relationships and layout structure of various electrical components (such as power generation equipment, transmission lines, distribution devices, energy storage module access points, loads, etc.) in the power network where the hybrid energy power station is located. This includes the connection methods, hierarchical relationships, and geographical / logical distribution between components, used to clarify the electrical connection paths and mutual influence relationships between nodes. The electrical equipment includes power generation equipment, transmission lines, distribution devices, and energy storage module access points, etc., and the connection methods between components include series and parallel connections.

[0032] Each node in the power grid topology represents a connection point or functional unit of electrical components within the topology. Specifically, these can include: generation-side nodes, such as grid connection points for new energy generation modules like photovoltaic and wind power modules; transmission-side nodes, such as the starting and ending points of transmission lines and transformer connection points; and distribution-side nodes, such as user load access points and distribution network branch connection points. The electrical parameters corresponding to each node, such as the node's rated voltage, voltage level, line connection impedance, and maximum power capacity, can be used to construct a node feature vector matrix. Real-time operational data represents data obtained by the energy management module through the power grid monitoring port, reflecting the dynamic operating status of the nodes. This includes, but is not limited to, real-time voltage values, real-time active / reactive power values, power fluctuation data (the change in power per unit time), and voltage deviation data (the difference between real-time voltage and rated voltage).

[0033] In this embodiment, a node feature vector matrix can be established based on the electrical parameters and real-time operating data of each node in the power grid topology. Each row of this matrix corresponds to the node feature vector of a node, and each column corresponds to the performance parameters of a node. For example, the power grid topology contains three nodes: node 1, node 2, and node 3. The electrical parameters and real-time operating data corresponding to each node are shown in Table 1.

[0034] Table 1 Electrical parameters and real-time operating data of each node

[0035]

[0036] The performance parameters for each node include the node load fluctuation coefficient, transmission capacity margin, and voltage sensitivity coefficient. The node load fluctuation coefficient is the product of the load fluctuation frequency and the peak-to-valley power difference, divided by the maximum carrying capacity. The transmission capacity margin is the difference between the maximum carrying capacity and the current average power, divided by the maximum carrying capacity. The voltage sensitivity coefficient is the product of the absolute value of the voltage deviation and the voltage level weight (assuming 1 for 110kV, 0.5 for 220kV, and 2 for 10kV).

[0037] Based on the above method, the node feature vector matrix X can be obtained, and the expression for X is:

[0038]

[0039] The values ​​of the column vectors in the node feature vector matrix have been normalized to eliminate dimensional differences, laying the foundation for subsequent calculations on the matching degree between nodes and energy storage modules.

[0040] S102: Establish an energy storage characteristic vector matrix based on the physical parameters of each energy storage module.

[0041] Each row of the energy storage characteristic vector matrix corresponds to the energy storage characteristic vector of an energy storage module, and each column corresponds to the performance parameters of the energy storage module.

[0042] In this embodiment, energy storage modules are respectively installed on the generation side, transmission side, and distribution side. The energy storage modules on the generation side are mainly used to smooth power fluctuations in new energy generation (such as output power fluctuations caused by sudden changes in sunlight or unstable wind speed) and assist in the stable output of each energy generation module. The energy storage modules on the generation side can be lithium battery energy storage modules, flow battery energy storage modules, or flywheel energy storage modules, etc. The energy storage modules on the transmission side are mainly used to support voltage stability of transmission lines and alleviate power congestion on the lines, requiring large capacity and long-term regulation capabilities. The energy storage modules on the transmission side can be flow battery energy storage modules. The energy storage modules on the distribution side are mainly used to respond to load fluctuations and maintain stable distribution voltage, requiring rapid response and flexible adjustment. The energy storage modules on the distribution side can be supercapacitors and lead-acid batteries, etc.

[0043] The physical parameters of an energy storage module represent its inherent technical characteristics as static parameters, primarily including capacity, power, response, voltage, efficiency, and stability parameters. Normalizing the values ​​corresponding to the physical parameters of each energy storage module yields the energy storage characteristic vector matrix. Similar to the eigenvector matrix of the same node, the energy storage characteristic vector matrix has also undergone normalization to eliminate dimensional differences, laying the foundation for subsequent calculations of the matching degree between nodes and energy storage modules.

[0044] There is no strict execution order between S101 and S102. S101 can be executed before, after, or simultaneously with S102. Figure 1 The execution method described is merely an example and is not intended to be limiting.

[0045] S103: Construct an association matrix representing the matching degree between the node feature vector and the energy storage characteristic vector by calculating the similarity between the two.

[0046] In this embodiment, similarity is a quantitative indicator that measures the degree of similarity between two vectors in multi-dimensional features, and its value range is usually [0,1]. Common similarity calculation methods include cosine similarity, Euclidean distance, and Pearson correlation coefficient. The association matrix represents a matrix formed by arranging the "similarity" between all nodes and all energy storage modules in an ordered row and column order. Its dimension is "number of nodes × number of energy storage modules", and the element value in the j-th row and i-th column of the matrix represents the similarity (i.e., matching degree) between the j-th node and the i-th energy storage module.

[0047] S104: Based on the node feature vector matrix, energy storage characteristic vector matrix and optimization target parameters, the optimal solution set of each energy storage module is obtained by using the multi-objective particle swarm algorithm.

[0048] In this embodiment, the optimized target parameters represent the core technical indicators of the hybrid energy power plant's operational performance and are the optimization direction of the multi-objective particle swarm optimization algorithm. These parameters include, but are not limited to, energy loss indicators, grid stability indicators, and response time indicators. The energy loss indicator represents the total energy loss during the charging and discharging process of the energy storage module; the grid stability indicator represents node voltage deviation rate, power fluctuation amplitude, etc.; and the response time indicator represents the deviation between the actual response time of the energy storage module and the theoretical requirement.

[0049] Multi-objective particle swarm optimization (PSO) is a heuristic optimization algorithm based on swarm intelligence, used to solve optimization problems with multiple conflicting objectives, such as minimizing energy loss and optimizing grid stability. PSO iteratively updates the position and velocity of particles to gradually approach the optimal solution. Iteration stops when a termination condition is met, such as reaching a preset number of iterations or the difference in the fitness function of the optimal solution set across multiple consecutive iterations being less than a preset threshold. From the global optimal solution set, all non-dominated solutions corresponding to each energy storage module are extracted according to module classification, forming the optimal solution set for each module. Each optimal solution set contains the optimal output parameters of that energy storage module under different optimization objective parameters.

[0050] This embodiment uses a multi-objective particle swarm optimization algorithm to obtain the optimal solution set for each energy storage module, which enhances the grid voltage stability and power balance capability. This enables the energy storage modules to quickly respond to real-time changes in node power and voltage, ensuring that they can efficiently play a role in smoothing fluctuations and supporting stability under different operating scenarios, and significantly improving the overall operational reliability of the hybrid energy power plant.

[0051] S105: The energy management module is used to obtain the node power and node voltage in the power grid in real time. In response to the node power or node voltage not being within the range of the optimal solution set, the output parameters of multiple energy storage modules are optimized based on the correlation matrix.

[0052] The energy management module has the functions of data acquisition, status judgment, and command issuance. In this embodiment, the energy management module is used to acquire the node power and node voltage in the power grid in real time, and determine whether it belongs to the range of the optimal solution set based on the acquired data. If it is determined to be within the range of the optimal solution set, no parameter optimization is required; if it is determined not to be within the range of the optimal solution set, the output parameters of multiple energy storage modules need to be optimized based on the correlation matrix.

[0053] Among them, node power represents the active or reactive power values ​​of each key node in the power grid, reflecting the power supply and demand status of the node (such as load power consumption), and is a core indicator for measuring the power balance of the power grid. Node voltage represents the voltage amplitude of each node in the power grid, and is a fundamental indicator for the stable operation of the power grid. It must be maintained within the allowable deviation range of the rated voltage (such as ±5%). Abnormal voltage may lead to equipment damage or power grid collapse. The output parameters of the energy storage module represent the key adjustable parameters of the energy storage module during operation, such as charging and discharging power, response time, etc.

[0054] As can be seen from the above, traditional hybrid power plants mostly centrally install energy storage devices on the generation side. This layout is relatively simple and cannot fully address the complex needs of different stages of the power system. The hybrid power plant using this optimization method, however, places multiple energy storage modules on the generation, transmission, and distribution sides respectively. This multi-side layout fully leverages the unique advantages of energy storage modules in different locations, enabling the energy storage system to play a role in all stages of the power system. This better adapts to the various problems caused by the intermittency and volatility of renewable energy, effectively improving the overall adaptability of the hybrid power plant to different operating conditions and energy fluctuations.

[0055] Specifically, this embodiment establishes a node feature vector matrix based on the electrical parameters and real-time operating data of each node in the power grid topology, and an energy storage characteristic vector matrix based on the physical parameters of each energy storage module. This accurately characterizes the operating status and characteristics of each node in the power grid, as well as the physical attributes and performance characteristics of each energy storage module. Furthermore, by calculating the similarity between the node feature vector and the energy storage characteristic vector, an association matrix representing their matching degree is constructed. This clarifies the matching relationship between each node in the power grid and different energy storage modules, enabling the selection and adjustment of the most suitable energy storage module based on the actual needs of the node during subsequent optimization. Finally, the optimal solution set for each energy storage module is obtained using a multi-objective particle swarm optimization algorithm. If the node power or node voltage is not within the range of the optimal solution set, the output parameters of multiple energy storage modules are optimized based on the association matrix. This real-time monitoring and dynamic optimization method in this embodiment can respond promptly to changes in the power grid's operating status. When problems such as voltage exceeding limits or line congestion occur, the output parameters of the energy storage modules are quickly adjusted, effectively suppressing further deterioration of the problem, ensuring stable operation of the power grid, and improving the grid's operating efficiency and reliability.

[0056] In one embodiment of this application, based on the node feature vector matrix, the energy storage characteristic vector matrix, and the optimization target parameters, the optimal solution set for each energy storage module is obtained using a multi-objective particle swarm optimization algorithm, including:

[0057] The number of particles in a multi-objective particle swarm optimization algorithm is determined based on the number of energy storage modules.

[0058] The initial position and initial velocity of particles in a multi-objective particle swarm algorithm are determined based on the node feature vector matrix and the energy storage characteristic vector matrix.

[0059] Iterative calculations are performed based on the number of particles, the initial position of the particles, and the initial velocity of the particles until the following conditions are met, thus obtaining the optimal solution set for each energy storage module.

[0060] The conditions include:

[0061] The number of iterations is equal to the preset number of iterations, or the difference in the fitness function of the number of consecutive targets is less than the preset threshold.

[0062] In this embodiment, the number of particles is directly related to the number of energy storage modules. For example, the number of particles is K times the number of energy storage modules, where K is an empirical value. If there are 5 energy storage modules, the number of particles can be set to 5 × 10 = 50 (each module corresponds to 10 potential solutions), ensuring that each energy storage module has sufficient solution space for searching. The initial position of the particles is determined based on the node feature vector matrix and the energy storage characteristic vector matrix. For example, the position coordinates of each particle correspond to a set of output parameters of the energy storage module (such as charging and discharging power). Its initial value can be set according to the matching degree between the node feature vector and the energy storage characteristic vector. That is, parameter combinations with high matching degree are given priority as initial positions to reduce invalid searches. The initial velocity of the particles is also set based on the feature difference between the two matrices. For example, the greater the difference between the node and the energy storage capacity, the greater the initial velocity; the smaller the difference, the smaller the initial velocity, balancing global exploration and local development.

[0063] In addition to the parameters mentioned above, an inertia weight reference value can be set to balance the global exploration (large-scale search for new solutions) and local development of particles; a cognitive factor can be set to guide particles toward their own historical optimal solution; and a social factor can be set to guide particles toward the group's optimal solution. These parameters can be set based on experience.

[0064] In one embodiment, the hybrid energy power plant optimization method further includes:

[0065] In response to the number of iterations being less than or equal to the first number, the inertial weight reference value of the particle swarm algorithm is increased by the first inertial step size;

[0066] In response to the number of iterations exceeding the first number, the inertial weight reference value of the particle swarm algorithm is reduced by a second inertial step size.

[0067] In this embodiment, considering that in the early stages of particle swarm optimization (PSO) iterations, increasing the inertia weight reference value can give particles greater inertia, enabling them to perform a wider search within the search space with larger step sizes. This helps particles explore the entire search space more thoroughly in the initial stage, avoiding premature entrapment in local optima and increasing the likelihood of finding the global optimum. However, once the number of iterations exceeds a certain threshold, the PSO algorithm has gained a certain understanding of the search space. At this point, decreasing the inertia weight reference value allows particles to perform smaller search step sizes, focusing more on fine-grained searches within the current local region. As iterations progress, particles get closer to the optimal solution and need to find the optimal solution more precisely within the local area. A smaller inertia weight allows particles to explore more meticulously near their current relatively optimal position, improving the algorithm's convergence accuracy.

[0068] Therefore, a threshold can be set. When the number of iterations exceeds the threshold, the inertia weight reference value should be appropriately reduced. When the number of iterations is less than or equal to the threshold, the inertia weight reference value should be appropriately increased.

[0069] This threshold is the first quantity. It's important to note that the first quantity should be less than the target number of iterations. The first quantity can be determined as a certain proportion of the target number of iterations, such as one-third to one-half of the target number of iterations. The first inertial step size and the second inertial step size are the step sizes for adjusting the inertial weight reference value, and can be set based on the experimental data.

[0070] In this embodiment, iterative calculations are performed based on parameters such as the number of particles, the initial position and velocity of the particles, and the inertial weight reference value, until the number of iterations equals the preset number of iterations, or the difference in the fitness function of the number of consecutive targets is less than the preset threshold, thus obtaining the optimal solution set for each energy storage module.

[0071] The fitness function includes a first fitness function and a second fitness function; the preset threshold includes a first preset threshold and a second preset threshold.

[0072] The first fitness function is determined based on the energy loss parameter in the node feature vector matrix and the charge / discharge efficiency parameter in the energy storage characteristic vector matrix.

[0073] The second fitness function is determined based on the voltage stability parameter, power fluctuation parameter in the node feature vector matrix, and the response speed parameter in the energy storage characteristic vector matrix.

[0074] The differences in the fitness functions for consecutive target numbers are all less than a preset threshold, including:

[0075] The difference in the first fitness function of the number of consecutive targets is less than the first preset threshold;

[0076] The difference in the second fitness function of the number of consecutive targets is less than the second preset threshold.

[0077] In this embodiment, based on the energy loss parameter in the node feature vector matrix and the charge / discharge efficiency parameter in the energy storage characteristic vector matrix, the first fitness function is determined using the first formula, which is:

[0078]

[0079] Where k is the number of energy storage modules, and T is the total number of time intervals within the optimization period. Let be the charging power of the i-th energy storage module during the t-th time interval. Let be the charging efficiency of the i-th energy storage module. Let be the discharge power of the i-th energy storage module during the t-th time interval. Let be the discharge efficiency of the i-th energy storage module. This refers to the energy loss rate during the charging process. This represents the energy loss rate during the discharge process.

[0080] In the first fitness function, the node energy loss parameter and the energy storage charge / discharge efficiency parameter are coupled through the power-efficiency term in the first formula ( and It is directly related to the grid transmission loss and the energy storage loss itself can be reduced at the same time during optimization, so that the reduction of energy loss is more in line with the actual physical process.

[0081] In this embodiment, based on the voltage stability parameter, power fluctuation parameter in the node feature vector matrix, and response speed parameter in the energy storage characteristic vector matrix, the second fitness function is determined using the second formula, which is:

[0082]

[0083] Where n is the total number of power grid nodes. Let be the real-time voltage of the j-th node. The rated voltage of the j-th node, Let j be the real-time power of the j-th node. Let j be the rated power of the j-th node. Let be the difference between the actual response time and the theoretical response time of the i-th energy storage module. Let be the maximum allowable response delay of the i-th energy storage module. , and These are the weighting coefficients.

[0084] In this embodiment, node voltage parameters, node power parameters, and energy storage response speed parameters are coupled by deviation rate weighting. This allows the optimization to consider not only the current stability deviation of the power grid but also the response time of the energy storage module, making the equipment regulation more dynamic and adaptable, and avoiding the problem of focusing only on static deviation while ignoring the timeliness of regulation.

[0085] As can be seen from the above, the embodiments of this application set the number of particles according to the number of energy storage modules, and determine the initial position and velocity of the particles based on the correlation matrix between nodes and energy storage modules, thereby reducing the number of iterations and the iteration time of the algorithm. Secondly, by setting multiple fitness functions and optimizing multiple objective parameters, the optimal solution set of each energy storage module is finally obtained, making the optimization of energy storage modules more reliable, ensuring the stable operation of the power grid, and improving the operating efficiency of the power grid.

[0086] In one embodiment of this application, the output parameters of multiple energy storage modules are optimized based on the correlation matrix, including:

[0087] The power grid is divided into different control areas based on the matching degree between each node and the energy storage module in the correlation matrix, and each control area corresponds to an energy storage module.

[0088] The compensation power of each energy storage module on the power generation side is calculated using a two-factor weighted algorithm of matching degree and capacity elasticity coefficient. The capacity elasticity coefficient is the coefficient that the capacity regulation capability of the energy storage module changes dynamically with the power of the corresponding node.

[0089] Based on the line transient impedance correction coefficient, a power regulation dynamic coefficient matrix is ​​constructed by combining the matching degree in the correlation matrix. The charging and discharging power of each energy storage module on the transmission side is corrected based on the power regulation dynamic coefficient matrix. The line transient impedance correction coefficient is the ratio of the current real-time impedance of the line to the rated impedance.

[0090] The matching degree in the correlation matrix is ​​sorted to establish a voltage response virtual queue. Based on the voltage response virtual queue, the reactive power response parameters of each energy storage module on the distribution side when participating in voltage regulation are adjusted.

[0091] In this embodiment, the power grid is divided into different control areas based on the matching degree between each node and the energy storage module in the correlation matrix. Each control area corresponds to one energy storage module, and each energy storage module corresponds to one or more nodes. By optimizing the output parameters of the energy storage modules on the generation, transmission, and supply sides in different ways, the regulation capability of each energy storage module is highly adapted to the real-time demand of the corresponding node. Power fluctuations in the power grid are accurately smoothed, voltage is stabilized within the rated range, and energy loss during transmission is significantly reduced. Ultimately, this achieves a comprehensive improvement in the coordinated efficiency and overall stability of all aspects of the hybrid energy power plant.

[0092] In one embodiment, a two-factor weighted algorithm based on matching degree and capacity elasticity coefficient is used to calculate the compensation power of each energy storage module on the generation side, including:

[0093] The compensation power for each energy storage module on the generation side is calculated based on the following method:

[0094] Obtain the baseline load values ​​for multiple nodes corresponding to each energy storage module;

[0095] The proportion of the real-time load value of each node to the total load value within the service range of the corresponding energy storage module is used as the node weight coefficient.

[0096] The sub-compensation power of each node is calculated based on the baseline load value of each node and a two-factor weighted algorithm.

[0097] The compensation power of the corresponding energy storage module is obtained by weighted summation based on the partial compensation power of each node and the node weight coefficient of each node.

[0098] In this embodiment, the capacity elasticity coefficient is a coefficient that reflects the dynamic change in the capacity regulation capability of the energy storage module with the corresponding node power. The greater the node power fluctuation, the higher the coefficient. The compensation power is the regulation power output by the generation-side energy storage module to smooth out power fluctuations in new energy generation (such as photovoltaic and wind power), and it needs to be matched with the node power fluctuation to maintain power balance.

[0099] In this embodiment, the compensation power of each energy storage module on the power generation side is calculated as follows: First, the baseline load value (such as planned load or historical average load) of each node within the service range of the energy storage module is obtained as a benchmark for judging real-time load fluctuations, clarifying the base of power deviation to be compensated. Second, the proportion of the real-time load value of each node to the total real-time load within the service range of the energy storage module is calculated as the node weight coefficient. That is, the higher the proportion of the real-time load value of a node, the greater its impact on the overall power balance of the region, and the higher its weight in the total compensation power. Third, for each node, the sub-compensation power of the node is obtained by weighting it using a dual factor of "matching degree + capacity elasticity coefficient" based on the deviation between its baseline load value and the real-time load. Finally, the sub-compensation power of each node is weighted and summed according to its node weight coefficient to obtain the total compensation power of the energy storage module.

[0100] As can be seen from the above, the compensation power not only reflects the differences in load proportion of each node, but also takes into account the adaptability and dynamic adjustment capability of energy storage and nodes, which can ensure that power fluctuations on the generation side are accurately suppressed and improve the efficiency and stability of regional power balance.

[0101] In one embodiment, the reactive power response parameters of each energy storage module on the distribution side participating in voltage regulation are adjusted based on a voltage response virtual queue, including:

[0102] Periodically acquire the voltage fluctuation amplitude and energy storage module charge of each node;

[0103] The virtual queue is updated based on the voltage fluctuation amplitude of each node and the energy storage module's charge level.

[0104] The reactive power response parameters of each energy storage module on the distribution side are adjusted based on the updated virtual queue order when participating in voltage regulation.

[0105] In this embodiment, the voltage fluctuation amplitude and energy storage module charge of each node are periodically acquired, for example, every 1 minute, 2 minutes, 5 minutes, etc., to ensure that the data reflects the real-time state of the power grid. The sorting rules of the voltage response virtual queue are updated based on the collected data. Generally, energy storage modules corresponding to nodes with larger voltage fluctuation amplitudes are ranked higher (prioritizing urgent needs), while energy storage modules with charge within a reasonable range have higher ranking weights (prioritizing modules with strong regulation capabilities), avoiding regulation failure due to abnormal energy storage charge status.

[0106] Based on the updated virtual queue ranking, the reactive power response parameters of energy storage modules are adjusted differently: energy storage modules ranked higher can be allocated faster response speeds and larger adjustment limits, and are given priority in intervening in the regulation of nodes with the most severe voltage fluctuations; modules ranked lower are on standby or assisted in regulation according to suboptimal parameters, ensuring that limited energy storage resources are prioritized for the most critical voltage stability needs, thereby improving the efficiency and reliability of voltage regulation on the distribution side.

[0107] Corresponding to the hybrid energy power plant optimization method in the above embodiment, Figure 2 This is a structural block diagram of a hybrid energy power plant optimization device according to an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. This hybrid energy power plant optimization device is applied to a hybrid energy power plant, which includes an energy management module and multiple energy storage modules, respectively located on the generation side, transmission side, and distribution side. (Reference) Figure 2 The hybrid energy power plant optimization device 20 includes: a first data processing unit 21, a second data processing unit 22, a first calculation unit 23, a second calculation unit 24, and a parameter optimization unit 25.

[0108] The first data processing unit 21 is used to establish a node feature vector matrix based on the electrical parameters and real-time operating data of each node in the power grid topology. Each row of the node feature vector matrix corresponds to the node feature vector of a node, and each column corresponds to the performance parameters of the node.

[0109] The second data processing unit 22 is used to establish an energy storage characteristic vector matrix based on the physical parameters of each energy storage module. Each row of the energy storage characteristic vector matrix corresponds to the energy storage characteristic vector of an energy storage module, and each column corresponds to the performance parameters of the energy storage module.

[0110] The first computing unit 23 is used to construct an association matrix representing the matching degree between the node feature vector and the energy storage characteristic vector by calculating the similarity between the two.

[0111] The second computing unit 24 is used to obtain the optimal solution set of each energy storage module based on the node feature vector matrix, the energy storage characteristic vector matrix and the optimization target parameters, using the multi-objective particle swarm algorithm.

[0112] The parameter optimization unit 25 is used to obtain the node power and node voltage in the power grid in real time using the energy management module. In response to the node power or node voltage not being within the range of the optimal solution set, the output parameters of multiple energy storage modules are optimized based on the correlation matrix.

[0113] In one embodiment of this application, the second computing unit 24 is specifically used for:

[0114] The number of particles in a multi-objective particle swarm optimization algorithm is determined based on the number of energy storage modules.

[0115] The initial position and initial velocity of particles in a multi-objective particle swarm algorithm are determined based on the node feature vector matrix and the energy storage characteristic vector matrix.

[0116] Iterative calculations are performed based on the number of particles, the initial position of the particles, and the initial velocity of the particles until the following conditions are met, thus obtaining the optimal solution set for each energy storage module.

[0117] The condition includes:

[0118] The number of iterations is equal to the preset number of iterations, or the difference in the fitness function of the number of consecutive targets is less than the preset threshold.

[0119] In one embodiment of this application, the fitness function includes a first fitness function and a second fitness function; the preset threshold includes a first preset threshold and a second preset threshold. The second calculation unit 24 is specifically used for:

[0120] The difference in the first fitness function of the number of consecutive targets is less than the first preset threshold;

[0121] The difference in the second fitness function of the number of consecutive targets is less than the second preset threshold.

[0122] In one embodiment of this application, the second computing unit 24 is further configured to:

[0123] The first fitness function is determined based on the energy loss parameter in the node feature vector matrix and the charge / discharge efficiency parameter in the energy storage characteristic vector matrix.

[0124] The second fitness function is determined based on the voltage stability parameter, power fluctuation parameter in the node feature vector matrix, and the response speed parameter in the energy storage characteristic vector matrix.

[0125] In one embodiment of this application, the parameter optimization unit 25 is specifically used for:

[0126] The power grid is divided into different control areas based on the matching degree between each node and the energy storage module in the correlation matrix, and each control area corresponds to an energy storage module.

[0127] The compensation power of each energy storage module on the power generation side is calculated using a two-factor weighted algorithm of matching degree and capacity elasticity coefficient. The capacity elasticity coefficient is the coefficient that the capacity regulation capability of the energy storage module changes dynamically with the power of the corresponding node.

[0128] Based on the line transient impedance correction coefficient, a power regulation dynamic coefficient matrix is ​​constructed by combining the matching degree in the correlation matrix. The charging and discharging power of each energy storage module on the transmission side is corrected based on the power regulation dynamic coefficient matrix. The line transient impedance correction coefficient is the ratio of the current real-time impedance of the line to the rated impedance.

[0129] The matching degree in the correlation matrix is ​​sorted to establish a voltage response virtual queue. Based on the voltage response virtual queue, the reactive power response parameters of each energy storage module on the distribution side when participating in voltage regulation are adjusted.

[0130] In one embodiment of this application, the parameter optimization unit 25 is specifically used for:

[0131] The compensation power for each energy storage module on the generation side is calculated based on the following method:

[0132] Obtain the baseline load values ​​for multiple nodes corresponding to each energy storage module;

[0133] The proportion of the real-time load value of each node to the total load value within the service range of the corresponding energy storage module is used as the node weight coefficient.

[0134] The sub-compensation power of each node is calculated based on the baseline load value of each node and a two-factor weighted algorithm.

[0135] The compensation power of the corresponding energy storage module is obtained by weighted summation based on the partial compensation power of each node and the node weight coefficient of each node.

[0136] In one embodiment of this application, the parameter optimization unit 25 is specifically used for:

[0137] Periodically acquire the voltage fluctuation amplitude and energy storage module charge of each node;

[0138] The virtual queue is updated based on the voltage fluctuation amplitude of each node and the energy storage module's charge level.

[0139] The reactive power response parameters of each energy storage module on the distribution side are adjusted based on the updated virtual queue order when participating in voltage regulation.

[0140] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the units in the above-described device embodiments, for example... Figure 2 The functions of the first data processing unit 21, the second data processing unit 22, the first calculation unit 23, the second calculation unit 24, and the parameter optimization unit 25 are shown.

[0141] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0142] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0143] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory.

[0144] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the hybrid energy power plant optimization method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0145] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0146] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0147] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0148] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules / units, or it may be an electrical, mechanical, or other form of connection.

[0150] The modules / units described as separate components may or may not be physically separate. Similarly, the components shown as modules / units may or may not be physical modules / units; they may be located in one place or distributed across multiple network modules / units. Some or all of the modules / units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0151] Furthermore, the functional modules / units in the various embodiments of this application can be integrated into one processing module / unit, or each module / unit can exist physically separately, or two or more modules / units can be integrated into one module / unit. The integrated modules / units described above can be implemented in hardware or in the form of software functional modules / units.

[0152] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for optimizing a hybrid energy power plant, characterized in that, The method is applied to the hybrid energy power station, which includes an energy management module and multiple energy storage modules, respectively located on the generation side, transmission side, and distribution side; the optimization method includes: A node feature vector matrix is ​​established based on the electrical parameters and real-time operating data of each node in the power grid topology. Each row of the node feature vector matrix corresponds to the node feature vector of a node, and each column corresponds to the performance parameters of the node. An energy storage characteristic vector matrix is ​​established based on the physical parameters of each energy storage module. Each row of the energy storage characteristic vector matrix corresponds to the energy storage characteristic vector of an energy storage module, and each column corresponds to the performance parameters of the energy storage module. By calculating the similarity between the node feature vector and the energy storage characteristic vector, an association matrix representing the degree of matching between the two is constructed. Based on the node feature vector matrix, the energy storage characteristic vector matrix, and the optimization target parameters, the optimal solution set for each energy storage module is obtained using the multi-objective particle swarm optimization algorithm. The power and voltage of nodes in the power grid are obtained in real time using the energy management module. In response to the node power or node voltage not falling within the range of the optimal solution set, the output parameters of multiple energy storage modules are optimized based on the correlation matrix. Based on the node feature vector matrix, the energy storage characteristic vector matrix, and the optimization target parameters, the optimal solution set for each energy storage module is obtained using a multi-objective particle swarm optimization algorithm, including: The number of particles in the multi-objective particle swarm algorithm is determined based on the number of energy storage modules. The initial positions and initial velocities of particles in the multi-objective particle swarm algorithm are determined based on the node feature vector matrix and the energy storage characteristic vector matrix. Based on the number of particles, the initial position of the particles, and the initial velocity of the particles, iterative calculations are performed until the following conditions are met to obtain the optimal solution set for each energy storage module; The following conditions are included: The number of iterations equals the preset number of iterations, or the difference in the fitness function of the number of consecutive targets is less than the preset threshold; The optimization of the output parameters of multiple energy storage modules based on the correlation matrix includes: Based on the matching degree between each node and the energy storage module in the correlation matrix, the power grid is divided into different control areas, and each control area corresponds to an energy storage module. The compensation power of each energy storage module on the power generation side is calculated using a two-factor weighted algorithm of matching degree and capacity elasticity coefficient. The capacity elasticity coefficient is a coefficient that dynamically changes the capacity adjustment capability of the energy storage module with the power of the corresponding node. Based on the line transient impedance correction coefficient, a power adjustment dynamic coefficient matrix is ​​constructed by combining the matching degree in the correlation matrix. The charging and discharging power of each energy storage module on the transmission side is corrected based on the power adjustment dynamic coefficient matrix. The line transient impedance correction coefficient is the ratio of the current real-time impedance of the line to the rated impedance. The matching degrees in the correlation matrix are sorted to establish a voltage response virtual queue. Based on the voltage response virtual queue, the reactive power response parameters of each energy storage module on the distribution side when participating in voltage regulation are adjusted.

2. The method as described in claim 1, characterized in that, The fitness function includes a first fitness function and a second fitness function; the preset threshold includes a first preset threshold and a second preset threshold; The differences in the fitness functions of the consecutive target numbers are all less than a preset threshold, including: The difference in the first fitness function of the number of consecutive targets is less than the first preset threshold; The difference in the second fitness function of the number of consecutive targets is less than the second preset threshold.

3. The method as described in claim 2, characterized in that, Also includes: The first fitness function is determined based on the energy loss parameter in the node feature vector matrix and the charge / discharge efficiency parameter in the energy storage characteristic vector matrix. The second fitness function is determined based on the voltage stability parameter, power fluctuation parameter in the node feature vector matrix, and the response speed parameter in the energy storage characteristic vector matrix.

4. The method as described in claim 1, characterized in that, The calculation of the compensation power of each energy storage module on the generation side using a two-factor weighted algorithm based on matching degree and capacity elasticity coefficient includes: The compensation power for each energy storage module on the generation side is calculated based on the following method: Obtain the baseline load values ​​for multiple nodes corresponding to each energy storage module; The proportion of the real-time load value of each node to the total load value within the service range of the corresponding energy storage module is used as the node weight coefficient. The sub-compensation power of each node is calculated based on the baseline load value of each node and the two-factor weighted algorithm. The compensation power of the corresponding energy storage module is obtained by weighted summation based on the partial compensation power of each node and the node weight coefficient of each node.

5. The method as described in claim 1, characterized in that, The adjustment of reactive power response parameters of each energy storage module on the distribution side when participating in voltage regulation based on the voltage response virtual queue includes: Periodically acquire the voltage fluctuation amplitude and energy storage module charge of each node; The virtual queue is updated based on the voltage fluctuation amplitude of each node and the energy storage module's charge level. The reactive power response parameters of each energy storage module on the distribution side are adjusted based on the updated sorting of the virtual queue when participating in voltage regulation.

6. A hybrid energy power plant optimization device, characterized in that, The system is applied to the hybrid energy power station, which includes an energy management module and multiple energy storage modules, the latter being respectively located on the generation side, transmission side, and distribution side; the optimization device includes: The first data processing unit is used to establish a node feature vector matrix based on the electrical parameters and real-time operating data of each node in the power grid topology. Each row of the node feature vector matrix corresponds to the node feature vector of a node, and each column corresponds to the performance parameters of the node. The second data processing unit is used to establish an energy storage characteristic vector matrix based on the physical parameters of each energy storage module. Each row of the energy storage characteristic vector matrix corresponds to the energy storage characteristic vector of an energy storage module, and each column corresponds to the performance parameters of the energy storage module. The first calculation unit is used to construct an association matrix representing the matching degree between the node feature vector and the energy storage characteristic vector by calculating the similarity between the two. The second computing unit is used to obtain the optimal solution set of each energy storage module based on the node feature vector matrix, the energy storage characteristic vector matrix and the optimization target parameters, using a multi-objective particle swarm optimization algorithm. The parameter optimization unit is used to obtain the node power and node voltage in the power grid in real time using the energy management module. In response to the node power or node voltage not being within the range of the optimal solution set, the unit optimizes the output parameters of multiple energy storage modules based on the correlation matrix. The second computing unit is specifically used to: determine the number of particles in the multi-objective particle swarm algorithm based on the number of energy storage modules; The initial positions and initial velocities of particles in the multi-objective particle swarm algorithm are determined based on the node feature vector matrix and the energy storage characteristic vector matrix. Based on the number of particles, the initial position of the particles, and the initial velocity of the particles, iterative calculations are performed until the following conditions are met to obtain the optimal solution set for each energy storage module; The following conditions are included: The number of iterations equals the preset number of iterations, or the difference in the fitness function of the number of consecutive targets is less than the preset threshold; The parameter optimization unit is specifically used for: Based on the matching degree between each node and the energy storage module in the correlation matrix, the power grid is divided into different control areas, and each control area corresponds to an energy storage module. The compensation power of each energy storage module on the power generation side is calculated using a two-factor weighted algorithm of matching degree and capacity elasticity coefficient. The capacity elasticity coefficient is a coefficient that dynamically changes the capacity adjustment capability of the energy storage module with the power of the corresponding node. Based on the line transient impedance correction coefficient, a power adjustment dynamic coefficient matrix is ​​constructed by combining the matching degree in the correlation matrix. The charging and discharging power of each energy storage module on the transmission side is corrected based on the power adjustment dynamic coefficient matrix. The line transient impedance correction coefficient is the ratio of the current real-time impedance of the line to the rated impedance. The matching degrees in the correlation matrix are sorted to establish a voltage response virtual queue. Based on the voltage response virtual queue, the reactive power response parameters of each energy storage module on the distribution side when participating in voltage regulation are adjusted.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images