A method and system for configuring adjustable capacity of a virtual power plant based on optimization analysis

Abstract

This invention relates to the field of intelligent power supply system technology, specifically to a method and system for adjusting the capacity of a virtual power plant based on optimization analysis. In this method, the first power demand of each particle is obtained. The second power demand is obtained by combining the first power demand with distance adjustment. Further analysis of the proportion of renewable energy power allocation yields the green allocation degree for each particle. Particle swarm optimization based on the green allocation degree can simultaneously consider energy supply and demand relationships and the concept of green environmental protection, making the optimization results more in line with expectations. During particle updates, the power generation stability of the configured energy distribution points and the configured power are considered. The update speed of each particle is weighted using update speed weights, ultimately obtaining the optimal configuration scheme for the virtual power plant. This invention allocates power to energy distribution points and configuration points through the optimal configuration scheme, ensuring energy supply and demand while conforming to the concept of green environmental protection.

Description

Technical Field

[0001] This invention relates to the field of intelligent power supply system technology, specifically to a method and system for configuring adjustable capacity of a virtual power plant based on optimization analysis. Background Technology

[0002] A conceptual model or entity that achieves power supply through intelligent scheduling and integration of multiple distributed energy sources is called a virtual power plant. The energy that a virtual power plant can allocate includes renewable energy sources such as solar and wind power, as well as traditional energy sources such as natural gas and biomass energy. Compared to traditional energy sources, the use of renewable energy can not only significantly reduce the emission of harmful pollutants and help improve air quality, but it can also be continuously utilized. Therefore, improving the utilization rate of renewable energy is crucial when configuring energy in a virtual power plant.

[0003] Because virtual power plants involve numerous energy distribution points and configuration points, resulting in multiple configuration schemes, existing technologies treat each configuration scheme as a particle and then use particle swarm optimization (PSO) algorithms to find the optimal solution within the entire particle swarm. However, current technologies often only set the particle fitness based on single objectives such as resource utilization and layout rationality during the optimization process. This fails to address the specific optimization needs related to the green and environmentally friendly aspects of power resource configuration in virtual power plants. Furthermore, the particles exhibit weak adaptability during the optimization process, hindering safe, rapid, and effective particle updates. Summary of the Invention

[0004] To address the technical problem that existing technologies using particle swarm optimization (PSO) algorithms to optimize virtual power plant configurations often fail to meet green and environmental protection requirements, this invention aims to provide a method and system for configuring adjustable capacity in virtual power plants based on optimization analysis. The specific technical solution adopted is as follows:

[0005] This invention proposes a method for configuring the adjustable capacity of a virtual power plant based on optimization analysis, the method comprising:

[0006] Determine the configuration scheme between energy distribution points and configuration points; the energy distribution points include both renewable energy and traditional energy sources.

[0007] Each configuration scheme is treated as a particle in the particle swarm optimization algorithm, and optimization is performed to determine the optimal configuration scheme. The particle swarm optimization algorithm specifically includes the following steps in the optimization process:

[0008] For each particle, the first power demand of each particle is obtained based on the difference between the configured power of the energy distribution point corresponding to the particle and the power required by the configuration point; the first power demand is adjusted based on the distance between the configuration point and the energy distribution point to obtain the second power demand of each particle.

[0009] The second electricity demand is adjusted according to the proportion of renewable energy in the power configuration of each particle to obtain the green configuration degree of each particle;

[0010] Based on the power generation stability and power configuration of the energy distribution points configured in the particle, the update speed weight of each particle is obtained, and the update speed of each particle is weighted according to the update speed weight; based on the green configuration degree and the weighted update speed of each particle, all particles are iteratively updated until the update condition is met, and the globally optimal particle is obtained, which is then used as the optimal configuration scheme.

[0011] Furthermore, the method for obtaining the first electricity demand includes:

[0012] For each particle, the total power of each configuration point is obtained by configuring all energy distribution points; the difference between the total power of the configuration and the power required by each configuration point is processed using a symbol function to obtain the symbol tag value of each configuration point, wherein the symbol tag value is 1 or -1; the symbol tag values ​​of all configuration points of each particle are accumulated and then normalized to obtain the first power demand.

[0013] Furthermore, the method for obtaining the second electricity demand includes:

[0014] For each particle, the configuration point and the energy distribution point are paired to obtain a configuration combination; for each configuration combination, the distance between the configuration point and the energy distribution point is negatively correlated and normalized to obtain a distance weight; the power received by the configuration point from the energy distribution point is multiplied by the distance weight to obtain the initial adjustment weight of the configuration combination; the initial adjustment weights of all configuration combinations are accumulated and normalized to obtain the adjustment weight of each particle; the product of the adjustment weight and the first power demand is used as the second power demand.

[0015] Furthermore, the method for obtaining the green configuration degree includes:

[0016] For each configuration point in each particle, the ratio of the electricity required by the configuration point to the total electricity of the configuration is taken as the energy utilization rate of the configuration point, and the product of the energy utilization rate and the proportion of renewable energy power configuration corresponding to the configuration point is taken as the initial green weight of the configuration point; the initial green weights of all configuration points in each particle are accumulated and normalized to obtain the green weight of each particle, and the green weight is multiplied by the second electricity demand to obtain the green configuration degree of each particle.

[0017] Furthermore, the method for obtaining the stability of power generation includes:

[0018] A preset time period is divided according to a preset time frequency. The average power generation of each energy distribution point within the preset time period is obtained. The power generation difference between the power generation of each energy distribution point per unit time within the preset time period and the average power generation is obtained. The cumulative value of the power generation difference of the energy distribution point within the preset time period is taken as the power generation volatility. The power generation volatility is negatively correlated and normalized to obtain the power generation stability.

[0019] Furthermore, the method for obtaining the update speed weight includes:

[0020] For each configuration point in each particle, the configuration amount of the configuration point to the energy distribution point is multiplied by the power generation stability to obtain the initial security of each energy distribution point. The initial security of all energy distribution points configured by the configuration point is accumulated to obtain the security of the configuration point.

[0021] For each particle, the security of all the configuration points is accumulated and then normalized to obtain the update speed weight.

[0022] Further, the weighting of the update rate of each particle according to the update rate weight includes:

[0023] The weighted update speed is obtained by multiplying the update speed weight by the initial update speed.

[0024] Furthermore, the update condition is that the number of iterations reaches a preset maximum number of iterations.

[0025] Furthermore, the method for obtaining the required power for each configuration point includes:

[0026] The average electricity consumption per unit time for each configuration point within a preset historical time period is calculated to obtain the required electricity for each configuration point.

[0027] The present invention also proposes a virtual power plant adjustable capacity configuration system based on optimization analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the methods for virtual power plant adjustable capacity configuration based on optimization analysis.

[0028] The present invention has the following beneficial effects:

[0029] In the optimization process, this invention first obtains the primary power demand of each particle. This primary power demand characterizes the rationality of the power supply and demand relationship in the configuration scheme. Further considering that the distance between the configuration point and the energy distribution point leads to energy loss, the primary power demand is adjusted based on distance to obtain the secondary power demand. Based on the secondary power demand, the proportion of renewable energy power configuration is further analyzed to obtain the green configuration degree of each particle. Particle swarm optimization based on the green configuration degree can simultaneously consider the energy supply and demand relationship and the concept of green environmental protection, making the optimization results more in line with expectations. Furthermore, during the particle update process, the power generation stability of the configured energy distribution point and the configured power are considered. The update speed of each particle is weighted using an update speed weight, making the particle update process more adaptable and ultimately obtaining particles with relatively no energy risk and a green and environmentally friendly configuration scheme. Finally, the optimal configuration scheme of the virtual power plant is obtained. By allocating power to the energy distribution point and configuration point through the optimal configuration scheme, energy supply and demand can be guaranteed while adhering to the concept of green environmental protection. Attached Figure Description

[0030] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart illustrating a virtual power plant adjustable capacity configuration method based on optimization analysis, provided in one embodiment of the present invention;

[0032] Figure 2 This is a distribution diagram illustrating the relationship between configuration points and energy distribution points, provided in one embodiment of the present invention.

[0033] Figure 3 This is a flowchart of an optimization method for a particle swarm optimization algorithm provided in one embodiment of the present invention. Detailed Implementation

[0034] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a virtual power plant adjustable capacity configuration method and system based on optimization analysis proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0036] The following description, in conjunction with the accompanying drawings, details the specific scheme of the adjustable capacity configuration method and system for a virtual power plant based on optimization analysis provided by the present invention.

[0037] Please see Figure 1 The diagram illustrates a flowchart of a virtual power plant adjustable capacity configuration method based on optimization analysis, according to an embodiment of the present invention. The method includes:

[0038] Step S101: Determine the configuration scheme between energy distribution points and configuration points; energy distribution points include renewable energy and traditional energy.

[0039] A virtual power plant is a management system that integrates multiple energy resources, achieving the scientific allocation of electricity through intelligent scheduling and optimization. Please refer to [link / reference]. Figure 2 This diagram illustrates the relationship between configuration points and energy distribution points according to an embodiment of the present invention. In the virtual power plant, the deployable energy includes multiple renewable energy sources and multiple traditional energy sources, all collectively referred to as energy distribution points. It also includes multiple configuration points, which are the user points for which electricity needs to be configured. In the virtual power plant of this embodiment, the energy distribution points for renewable energy are considered to be n1, the energy distribution points for traditional energy are considered to be n2, the configuration points are considered to be m, and the total number of energy distribution points is considered to be n.

[0040] There are multiple configuration schemes between energy distribution points and configuration points. In one configuration scheme, each configuration point can obtain the electricity allocated by each energy distribution point.

[0041] Step S102: Treat each configuration scheme as a particle in the particle swarm optimization algorithm and perform optimization to determine the optimal configuration scheme.

[0042] The present invention aims to use the particle swarm optimization algorithm to find the optimal configuration scheme among multiple configuration schemes. Therefore, each configuration scheme can be regarded as a massless particle in space, thus obtaining a particle swarm. By using the particle swarm optimization algorithm for optimization, the optimal configuration scheme can be obtained.

[0043] It should be noted that the basic principle of the particle swarm optimization algorithm is a well-known technique in the art, and will not be elaborated upon here. In this embodiment of the invention, the number of particles is set to 100, the maximum number of iterations is 1000, the learning factor is set to 2, and the inertia weight is set to 0.5. Optimization can begin by initializing the particle positions and velocities.

[0044] To ensure that the final optimization result meets the energy supply and demand relationship while complying with green and environmentally friendly strategies, please refer to [link / reference]. Figure 3 The particle swarm optimization algorithm in this embodiment of the invention specifically includes the following in the optimization process:

[0045] Step S301: For each particle, obtain the first power demand of each particle based on the difference between the power required by the energy distribution point corresponding to the particle and the power configured at the configuration point; adjust the first power demand based on the distance between the configuration point and the energy distribution point to obtain the second power demand of each particle.

[0046] For a particle, if its corresponding configuration scheme is a relatively optimal one, then the configuration scheme should at least satisfy the supply and demand relationship of energy, that is, the configuration points of the energy distribution should be able to meet the power requirements of the configuration points. This is the basic power demand. Therefore, for each particle, the greater the difference between the configured power of the energy distribution points and the power required by the configuration points, the more sufficient the configuration points have to meet the basic supply and demand relationship. Thus, the primary power demand of each particle can be obtained based on the difference between the configured power of the energy distribution points and the power required by the configuration points.

[0047] Furthermore, considering that power distribution should be as close to the source as possible, the greater the distance between the allocation point and the energy distribution point, the higher the energy loss during transmission. Therefore, it is also necessary to further consider the distance between the allocation point and the energy distribution point. The shorter the distance, the more rational the allocation scheme, the higher the energy utilization efficiency, and the lower the potential energy risks. Therefore, the first power demand is further adjusted according to the distance between the allocation point and the energy distribution point to obtain the second power demand for each particle. The second power demand can be used to evaluate the rationality of the allocation scheme corresponding to the particle in the basic energy supply and demand relationship.

[0048] Preferably, in one embodiment of the present invention, in order to effectively quantify the first power demand and highlight the characteristic of whether the supply and demand relationship is satisfied, for each particle, the difference between the total allocated power and the required power of each configuration point is processed using a sign function. The total allocated power is the sum of the allocated power obtained from all energy distribution points for each configuration point, representing the total power allocated to the configuration point in the configuration scheme corresponding to the particle. If the difference between the total allocated power and the required power of the configuration point is negative, it indicates that the configuration scheme of the particle cannot satisfy the supply and demand relationship of the configuration point; if it is positive, it indicates that it can be satisfied. Therefore, the sign of this difference can be output using a sign function to obtain a sign label value, i.e., a sign label value of 1 or -1. A sign label value of 1 indicates that the power supply and demand relationship of the configuration point is satisfied, and -1 indicates that it is not satisfied. Therefore, the sign label values ​​of all configuration points of each particle are summed and normalized to obtain the first power demand. The larger the first power demand, the more reasonable the configuration scheme corresponding to the particle is in terms of the power supply and demand relationship of the configuration point.

[0049] As an example, the primary electricity demand can be expressed by the formula:

[0050] Among them, Y ′ (A) represents the initial power demand of the A-th particle, m is the number of placement points, and n is the number of energy distribution points. The configured power received by the i-th configuration point from the j-th energy distribution point. Let H() represent the required power for the i-th configuration point, where f() represents the sign function and f() represents the normalization function.

[0051] It should be noted that the normalization method used in this embodiment of the invention is the maximum-minimum normalization method, which uses the data of all particles updated in each iteration as the dataset for normalization.

[0052] Furthermore, the method for obtaining the required power for each configuration point includes: statistically analyzing the average power consumption of each configuration point per unit time within a preset historical time period to obtain the required power for each configuration point. Since the virtual power plant needs to allocate power to each node at a certain moment, a historical time period consisting of multiple historical moments prior to that moment can be used as a reference time period. Statistically analyzing the average power consumption of configuration points within the historical time period yields the required power for each configuration point. In this embodiment of the invention, the historical time period is one month, and the time is set to one day; that is, the average daily power consumption of the configuration point within one month is used as the required power. It should be noted that since the required power can be considered as the daily power consumption of the configuration point, the configuration power received by the configuration point from the energy distribution point in the analysis of the first power demand is also the configuration power for one day.

[0053] Preferably, in one embodiment of the present invention, on the one hand, the distance between nodes in the configuration scheme is an important factor in evaluating the rationality of the configuration scheme; on the other hand, it is considered that energy distribution points that are closer together should be allocated more energy to ensure that energy loss is reduced. Therefore, the second method for obtaining electricity demand includes:

[0054] For each particle, a configuration combination is obtained by pairing the placement point with each energy distribution point. For each configuration combination, the distance between the placement point and the energy distribution point is negatively correlated and normalized to obtain a distance weight. The shorter the distance, the larger the distance weight, indicating that the placement point in that configuration combination should receive more power. Therefore, the initial adjustment weight of the configuration combination is obtained by multiplying the power received by the placement point from the energy distribution point by the distance weight. In other words, for each configuration combination, the smaller the distance between the placement point and the energy distribution point, and the greater the power allocated to the placement point, the more reasonable the configuration combination is, and the larger the initial adjustment weight.

[0055] Because each particle contains multiple configuration points, and each configuration point has a configuration combination with each energy distribution point, meaning each particle has a large number of configuration combinations, the initial adjustment weights of all configuration combinations are summed and normalized to obtain the adjustment weight for each particle. A larger adjustment weight indicates a more reasonable configuration scheme for that particle in terms of power transmission loss. Therefore, the product of the adjustment weight and the first power demand is used as the second power demand.

[0056] As an example, the second electricity demand can be expressed by the formula:

[0057] Where Y ″ (A) represents the second electrical demand of particle A, R i , j Let ε be the distance between the i-th configuration point and the j-th energy distribution point, and let ε be a preset hyperparameter. Here, ε is set to 1 to prevent the denominator from being 0. The distance weights are the result of negative correlation mapping and normalization of distances.

[0058] Step S302: Adjust the second electricity demand according to the proportion of renewable energy power configuration in each particle to obtain the green configuration degree of each particle;

[0059] The second electricity demand obtained from the above steps represents an evaluation of the basic electricity supply and demand relationship in the configuration scheme. To focus on the concept of green and environmentally friendly development, the rationality of renewable energy allocation in the power distribution process also needs to be analyzed. The higher the utilization rate of renewable energy, the greener and more environmentally friendly the configuration scheme. Therefore, this embodiment of the invention further adjusts the second electricity demand based on the proportion of renewable energy in the power allocation of each particle to obtain the green configuration degree of each particle. That is, the larger the proportion of renewable energy in the power allocation, the greener the power distribution in the configuration scheme, and the greater the second electricity demand. This indicates that the configuration scheme satisfies both the basic electricity supply and demand relationship and the green and environmentally friendly concept, thus resulting in a higher green configuration degree.

[0060] Preferably, in one embodiment of the present invention, it is further necessary to consider the utilization rate of the allocated power at the configuration point. That is, while ensuring the basic power supply and demand relationship, the required power should not differ significantly from the total allocated power to avoid waste in power allocation, which is also one of the factors for green environmental protection. Therefore, the method for obtaining the green configuration degree includes:

[0061] For each placement point within each particle, the ratio of the power required by that placement point to the total power required by all placement points is taken as the energy utilization rate of that placement point. The larger this ratio is, the closer it is to 1, the greater the energy utilization rate.

[0062] The initial green weight of a configuration point is the product of its energy utilization rate and the proportion of renewable energy power allocation corresponding to that configuration point. The larger the initial green weight, the more the configuration of that configuration point conforms to the concept of green environmental protection in the configuration scheme of that particle.

[0063] Since a particle contains multiple configuration points, the initial green weights of all configuration points in each particle are summed and normalized to obtain the green weight of each particle. The green weight is then multiplied by the second power demand to obtain the green configuration degree of each particle.

[0064] As an example, the green configuration degree can be expressed by the formula:

[0065] Where S(A) represents the green configuration degree of particle A. The configured power for the i-th configuration point is configured by the k-th renewable energy source.

[0066] Step S303: Based on the power generation stability and power configuration of the energy distribution points configured in the particle, obtain the update speed weight of each particle, and weight the update speed of each particle according to the update speed weight; based on the green configuration degree and the weighted update speed of each particle, iteratively update all particles until the update condition is met, obtain the globally optimal particle, and use the globally optimal particle as the optimal configuration scheme.

[0067] For each initially generated particle, the above steps yield its green configuration degree, evaluating its environmental friendliness under reasonable power configuration. During the optimization process, the optimal position of each particle needs to be updated first. By comparing the current particle's green configuration degree with the maximum green configuration degree recorded in its historical iterations, if the current green configuration degree is higher, it indicates a better configuration, and the particle's position is updated to the optimal position—the local optimum found during the entire search process. This helps guide the particle to move towards a better direction in subsequent iterations. Simultaneously, the particle swarm optimization algorithm also searches for the example with the best green configuration degree among all particles and updates the global optimal position. This means finding the example with the highest green configuration degree in the entire particle swarm and recording its position; the global optimal solution represents the best solution found by all particles at the current position in the iteration. Existing particle swarm optimization algorithms update the particle's update speed and position according to existing formulas and preset parameters during the above optimization process. However, this update method does not consider the actual needs of the virtual power plant scenario and cannot guarantee a fast and accurate optimal configuration that is stable in power configuration, meets supply and demand, and is environmentally friendly within a limited number of iterations.

[0068] Therefore, this embodiment of the invention employs a weighted strategy, assigning relatively larger weights to the update speed of particles with higher safety, thus giving them a more important position in the entire optimization algorithm. During the optimization process, particles with higher risk have smaller weights, reducing their impact on the final result and helping to guide the algorithm towards safer and more reasonable updates, thereby reducing potential risks.

[0069] Because energy distribution points are subject to the risk of unstable power supply, exhibiting intermittency and instability, especially renewable energy sources such as wind power which depend on natural conditions and whose power generation is affected by weather and seasons, the greater the power generation stability of the energy distribution point configured at that point, the higher the security of that point, and the greater its corresponding update speed weight should be. Therefore, this embodiment of the invention obtains the update speed weight of each particle based on the power generation stability and configured power of the energy distribution points configured at the particle's points. That is, the greater the power generation stability and the greater the configured power, the safer the corresponding point, and the greater the update speed weight of the corresponding particle.

[0070] By weighting the update rate of each particle according to its update rate, a new update rate and position can be obtained during the optimization process. This weighting mechanism makes the optimization process more stable, ultimately focusing on particles that meet both basic requirements and high safety. This improves the reliability of the optimization process.

[0071] Preferably, in one embodiment of the present invention, the method for obtaining power generation stability includes:

[0072] A preset time period is defined based on a preset time frequency. The average power generation of each energy distribution point within the preset time period is obtained. The difference between the power generation of each energy distribution point per unit time within the preset time period and the average power generation is obtained. The cumulative value of the power generation difference of the energy distribution point within the preset time period is taken as the power generation volatility. In this embodiment of the invention, the time frequency is set to daily, and the preset time period is one month. That is, the average power generation per day within one month is obtained and used as the basic reference data. The greater the difference between the daily power generation and the average power generation within this time period, the greater the power generation volatility. The power generation volatility is negatively correlated and normalized to obtain the power generation stability. In this embodiment of the invention, the power generation volatility is negatively correlated and normalized using a reciprocal form. The reciprocal of the result of adding the power generation volatility to a positive integer 1 is taken as the power generation stability.

[0073] Preferably, in one embodiment of the present invention, the method for obtaining the updated speed weight includes:

[0074] For each configuration point within a particle, the initial security of each energy distribution point is obtained by multiplying the configured power allocated to that energy distribution point by the power generation stability. That is, a higher configured power coupled with greater power generation stability indicates a more stable and reliable power distribution at that energy distribution point, resulting in higher initial security. Since a configuration point can be allocated power by multiple energy distribution points, the initial security of all energy distribution points configured to that point is accumulated to obtain the overall security of that configuration point. Combining the security of all configuration points within a particle, for each particle, the accumulated security of all configuration points is normalized to obtain the update velocity weight.

[0075] In this embodiment of the invention, the update speed weight is multiplied by the initial update speed to obtain the weighted update speed. It should be noted that the initial update speed here is the update speed obtained according to the update speed calculation formula in the traditional particle swarm optimization algorithm. That is, after each update speed is calculated using the traditional algorithm, it is further adjusted using the update speed weight to obtain the weighted update speed.

[0076] In this embodiment of the invention, the update condition is set to the number of iterations reaching a preset maximum number of iterations. Once the update condition is met, the globally optimal particle is obtained, and the configuration scheme of the globally optimal particle is the optimal configuration scheme. Through particle swarm optimization in this embodiment of the invention, the configuration scheme of the virtual power plant can take into account the basic power supply and demand relationship, further consider the concept of green environmental protection, and minimize the risks of power consumption at the configuration points, thus achieving optimal allocation of power resources in the virtual power plant.

[0077] In summary, during the optimization process, this invention first obtains the first power demand of each particle. This first power demand characterizes the rationality of the power supply and demand relationship in the configuration scheme. Further considering that the distance between the configuration point and the energy distribution point leads to energy loss, the first power demand is adjusted based on the distance to obtain the second power demand. Based on the second power demand, the proportion of renewable energy power configuration is further analyzed to obtain the green configuration degree of each particle. Particle swarm optimization based on the green configuration degree can simultaneously consider the energy supply and demand relationship and the concept of green environmental protection, making the optimization results more in line with expectations. Furthermore, during the particle update process, the power generation stability of the configured energy distribution point and the configured power are considered. The update speed of each particle is weighted using an update speed weight, making the particle update process more adaptable and ultimately obtaining particles with relatively no energy risk and a green and environmentally friendly configuration scheme. Finally, the optimal configuration scheme of the virtual power plant is obtained. By allocating power to the energy distribution point and configuration point through the optimal configuration scheme, energy supply and demand can be guaranteed while adhering to the concept of green environmental protection.

[0078] This invention also proposes a virtual power plant adjustable capacity configuration system based on optimization analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any one of the steps of a virtual power plant adjustable capacity configuration method based on optimization analysis.

[0079] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for configuring adjustable capacity of a virtual power plant based on optimization analysis, characterized in that, The method includes: Determine the configuration scheme between energy distribution points and configuration points; the energy distribution points include both renewable energy and traditional energy sources. Each configuration scheme is treated as a particle in the particle swarm optimization algorithm, and optimization is performed to determine the optimal configuration scheme. The particle swarm optimization algorithm specifically includes the following steps in the optimization process: For each particle, the first power demand of each particle is obtained based on the difference between the configured power of the energy distribution point corresponding to the particle and the power required by the configuration point; the first power demand is adjusted based on the distance between the configuration point and the energy distribution point to obtain the second power demand of each particle. The second electricity demand is adjusted according to the proportion of renewable energy in the power configuration of each particle to obtain the green configuration degree of each particle; Based on the power generation stability and power configuration of the energy distribution points configured in the particle, the update speed weight of each particle is obtained, and the update speed of each particle is weighted according to the update speed weight; based on the green configuration degree and the weighted update speed of each particle, all particles are iteratively updated until the update condition is met, and the globally optimal particle is obtained, which is then used as the optimal configuration scheme. The degree of green configuration satisfies the following formula: Where S(A) represents the green configuration degree of particle A, This represents the power required for the i-th configuration point. This represents the configured power received by the i-th configuration point from the j-th energy distribution point. Y represents the configured electricity at the i-th configuration point configured by the k-th renewable energy source. ″ (A) represents the second electrical demand of particle A, and f() represents the normalization function.

2. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 1, characterized in that, The first method for obtaining electricity demand includes: For each particle, the total power of each configuration point is obtained by configuring all energy distribution points; the difference between the total power of the configuration and the power required by each configuration point is processed using a symbol function to obtain the symbol tag value of each configuration point, wherein the symbol tag value is 1 or -1; the symbol tag values ​​of all configuration points of each particle are accumulated and then normalized to obtain the first power demand.

3. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 1, characterized in that, The second method for obtaining electricity demand includes: For each particle, the configuration point and the energy distribution point are paired to obtain a configuration combination; for each configuration combination, the distance between the configuration point and the energy distribution point is negatively correlated and normalized to obtain a distance weight; the power received by the configuration point from the energy distribution point is multiplied by the distance weight to obtain the initial adjustment weight of the configuration combination; the initial adjustment weights of all configuration combinations are accumulated and normalized to obtain the adjustment weight of each particle; the product of the adjustment weight and the first power demand is used as the second power demand.

4. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 2, characterized in that, The method for obtaining the green configuration degree includes: For each configuration point in each particle, the ratio of the electricity required by the configuration point to the total electricity of the configuration is taken as the energy utilization rate of the configuration point, and the product of the energy utilization rate and the proportion of renewable energy power configuration corresponding to the configuration point is taken as the initial green weight of the configuration point; the initial green weights of all configuration points in each particle are accumulated and normalized to obtain the green weight of each particle, and the green weight is multiplied by the second electricity demand to obtain the green configuration degree of each particle.

5. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 1, characterized in that, The method for obtaining the stability of power generation includes: A preset time period is divided according to a preset time frequency. The average power generation of each energy distribution point within the preset time period is obtained. The power generation difference between the power generation of each energy distribution point per unit time within the preset time period and the average power generation is obtained. The cumulative value of the power generation difference of the energy distribution point within the preset time period is taken as the power generation volatility. The power generation volatility is negatively correlated and normalized to obtain the power generation stability.

6. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 1, characterized in that, The method for obtaining the update speed weight includes: For each configuration point in each particle, the configuration amount of the configuration point to the energy distribution point is multiplied by the power generation stability to obtain the initial security of each energy distribution point. The initial security of all energy distribution points configured by the configuration point is accumulated to obtain the security of the configuration point. For each particle, the security of all the configuration points is accumulated and then normalized to obtain the update speed weight.

7. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 1, characterized in that, The step of weighting the update rate of each particle according to the update rate weight includes: The weighted update speed is obtained by multiplying the update speed weight by the initial update speed.

8. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 1, characterized in that, The update condition is that the number of iterations reaches the preset maximum number of iterations.

9. The method for configuring adjustable capacity of a virtual power plant based on optimization analysis according to claim 2, characterized in that, The method for obtaining the required power for each configuration point includes: The average electricity consumption per unit time for each configuration point within a preset historical time period is calculated to obtain the required electricity for each configuration point.

10. A virtual power plant adjustable capacity configuration system based on optimization analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for configuring adjustable capacity of a virtual power plant based on optimization analysis as described in any one of claims 1 to 9.

Images