Virtual power plant operation scheduling method and device, terminal, and storage medium

Abstract

The application provides a virtual power plant operation scheduling method and device, a terminal and a storage medium. The method comprises the following steps: determining a similar day corresponding to a prediction day according to historical data of a virtual power plant; obtaining unit power generation costs and unit carbon emissions of each device of the virtual power plant and a pre-established virtual power plant operation scheduling model; wherein the virtual power plant operation scheduling model is used to determine a scheduling scheme of each controllable load of the virtual power plant according to input parameters thereof; obtaining a solution of the virtual power plant operation scheduling model on the similar day, and taking the solution on the similar day as an initial solution of the virtual power plant operation scheduling model on the prediction day; and performing optimization on the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme of each controllable load of the virtual power plant in the prediction day. The application can effectively reduce the calculation amount of the virtual power plant operation scheduling model, improve the accuracy of the model, make the determined scheduling scheme more applicable, and make the energy-saving and emission-reducing effect of the virtual power plant operation better.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a virtual power plant operation and scheduling method, device, terminal, and storage medium. Background Technology

[0002] To address the scarcity of fossil fuels and the environmental pollution caused by their combustion, clean and renewable energy sources are being increasingly widely adopted. Virtual power plants control the scheduling of controllable loads through dispatch schemes, thereby achieving resource allocation. Currently, methods for determining virtual power plant dispatch schemes based on the massive operational data of virtual power plants generally suffer from high computational complexity and inaccurate calculations, impacting energy conservation and emission reduction effectiveness. Therefore, there is an urgent need for a method that can reduce computational complexity and improve energy conservation and emission reduction efficiency. Summary of the Invention

[0003] This application provides a virtual power plant operation scheduling method, device, terminal, and storage medium to solve the problems of large computational load and poor energy-saving and emission-reduction effects in the prior art when determining the scheduling scheme for virtual power plant operation.

[0004] In a first aspect, embodiments of this application provide a virtual power plant operation scheduling method, including:

[0005] Based on the historical data of the virtual power plant, determine the similar days corresponding to the prediction date;

[0006] The unit power generation cost and unit carbon emission of each device in the virtual power plant are obtained, as well as a pre-established virtual power plant operation and scheduling model; wherein, the virtual power plant operation and scheduling model is used to determine the scheduling scheme of each controllable load of the virtual power plant based on its input parameters;

[0007] Obtain the solution of the virtual power plant operation scheduling model on similar days, and use the solution on similar days as the initial solution of the virtual power plant operation scheduling model on the predicted day;

[0008] Based on the initial solution, the virtual power plant operation scheduling model is optimized to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day.

[0009] In one possible implementation, the optimization of the virtual power plant operation scheduling model based on the initial solution to obtain a scheduling scheme for each controllable load of the virtual power plant during the predicted day includes:

[0010] S1: Fine-tune the initial solution to obtain a population R with a population size of N-1. t Population R t The parent population P is obtained by merging the initial solution with the parent population of size N. t ;

[0011] S2: Initialize the number of iterations: t = 1;

[0012] S3: Construct a fitness function based on the mapping relationship and pre-set the fitness threshold;

[0013] S4: Calculate the fitness of individuals in the parent population and sort the individuals in the parent population according to their fitness.

[0014] S5: Determine whether there is at least one individual in the parent population whose fitness is greater than a preset fitness threshold. If there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold, then output the optimal solution. The optimal solution is the scheduling scheme of each controllable load of the virtual power plant corresponding to the maximum fitness value.

[0015] If the fitness of any individual in the parent population is not greater than the preset fitness threshold, then increment the iteration count by 1; determine if the iteration count is greater than the preset iteration count. If the iteration count is greater than the preset iteration count, then output the individual with the highest fitness in the parent population as the optimal solution. If the iteration count is not greater than the preset iteration count, then execute S6.

[0016] S6: Select, crossover, and mutate the parent population to obtain a new offspring population of N. Calculate and sort the fitness of individuals in the offspring population. Replace individuals with high fitness in the offspring population with individuals with low fitness in the parent population. Use the newly generated population after replacement as the parent population. Repeat S4-S6.

[0017] In one possible implementation, the method for establishing the virtual power plant operation and scheduling model includes:

[0018] Obtain carbon emission allowances for virtual power plants within the target area;

[0019] To minimize operating costs, a first objective function is constructed.

[0020] To minimize carbon emissions, a second objective function is constructed.

[0021] Based on the carbon emission quotas of the virtual power plants in the target area, the unit power generation cost and unit carbon emission of each piece of equipment in the virtual power plants, the constraints of the virtual power plant operation and scheduling model are determined.

[0022] Based on the first objective function, the second objective function, and the constraints, the virtual power plant operation and scheduling model is established.

[0023] In one possible implementation, the first objective function is:

[0024] f1=a×f 1a +b×f 1b +c×f 1c+d×f 1d

[0025] Where f1 is the operating cost, a is the power generation of the generator set, and f 1a Let b be the unit power generation cost of the generator set, b be the discharge capacity of the energy storage device, and f be the discharge capacity of the energy storage device. 1b Let c be the unit discharge cost of the energy storage device, and f be the power consumption of the electrical equipment. 1c Let d be the unit electricity cost of the electrical equipment, and f be the electricity purchased from the main grid. 1d The real-time electricity price for the main grid;

[0026] The second objective function is:

[0027] f2=a×f 2a +b×f 2b +c×f 2c

[0028] Where f2 is carbon emissions, a is the power generation of the generator set, and f 2a b is the unit carbon emission of the generator set, f is the discharge capacity of the energy storage device, and f is the unit carbon emission of the generator set. 2b Let f be the carbon emissions per unit of energy storage equipment, c be the electricity consumption of the electrical equipment, and f be the energy consumption per unit of energy storage equipment. 2c This refers to the carbon emissions per unit of electrical equipment.

[0029] In one possible implementation, the method for determining the unit carbon emission includes:

[0030] Obtain historical data for each device in the virtual power plant;

[0031] By analyzing the historical data of each device, we can obtain the historical energy consumption and historical power generation of generator sets of various energy sources, the historical power consumption and historical discharge of various energy storage devices, and the historical power consumption of various electrical devices.

[0032] Carbon content calculation is performed on the historical energy consumption of generator sets of various energy sources to obtain the historical carbon emissions of generator sets; based on the historical carbon emissions and historical power generation of generator sets, the unit carbon emissions of generator sets are determined.

[0033] Carbon content calculation is performed on the historical power consumption of various energy storage devices to obtain the historical carbon emissions of the energy storage devices; based on the historical carbon emissions and historical discharge of the energy storage devices, the unit carbon emissions of the energy storage devices are determined.

[0034] Carbon content is calculated based on the historical electricity consumption of various electrical devices to obtain the historical carbon emissions of the devices; based on the historical carbon emissions and historical electricity consumption of the devices, the unit carbon emissions of the devices are determined.

[0035] In one possible implementation, determining the similar day corresponding to the prediction day based on historical data from the virtual power plant includes:

[0036] Obtain the influencing factors and values ​​of each factor in historical daily electricity consumption;

[0037] Calculate the influence weight of each influencing factor based on the volatility and correlation of the values ​​of each influencing factor;

[0038] Obtain the values ​​of each influencing factor for the forecast date;

[0039] The similar days corresponding to the predicted day are determined based on the values ​​of each influencing factor for the predicted day, the influencing weights, and the values ​​of each influencing factor for the electricity consumption in the historical days.

[0040] The influencing factors include meteorological factors and non-meteorological factors.

[0041] In one possible implementation, determining the constraints of the virtual power plant operation scheduling model based on the carbon emission quotas of the virtual power plant within the target area, the unit power generation cost of each piece of equipment in the virtual power plant, and the unit carbon emission amount includes:

[0042] Based on the aforementioned carbon emission quotas, establish the following carbon emission quota constraint condition: f2≤P1;

[0043] Based on the aforementioned carbon emissions, greenhouse gas concentrations are calculated, and concentration constraints are established: y i ≤P 2i ;

[0044] Based on the power generation of the generator set, the discharge of the energy storage device, the power purchased by the main grid, and the power consumption of the electrical equipment, the power constraint condition is established: P3≤g1+g2+g3;

[0045] Where f2 is the carbon emission amount, P1 is the carbon emission allowance, and y i For each greenhouse gas concentration, P 2i For each greenhouse gas, P3 represents the electricity consumption of electrical equipment, g1 represents the power generation of generator sets, g2 represents the discharge of energy storage devices, and g3 represents the electricity purchased by the main grid.

[0046] The constraints of the virtual power plant operation scheduling model also include: virtual power plant operation constraint data.

[0047] Secondly, embodiments of this application provide a virtual power plant operation scheduling device, comprising:

[0048] The similarity day determination module is used to determine the similarity day corresponding to the prediction day based on the historical data of the virtual power plant.

[0049] The model building module is used to obtain the unit power generation cost and unit carbon emission of each device in the virtual power plant, as well as the pre-established virtual power plant operation and scheduling model; wherein, the virtual power plant operation and scheduling model is used to determine the scheduling scheme of each controllable load of the virtual power plant based on its input parameters;

[0050] The initial solution determination module is used to obtain the solution of the virtual power plant operation scheduling model on similar days, and use the solution on similar days as the initial solution of the virtual power plant operation scheduling model on the predicted day;

[0051] The scheduling scheme determination module is used to optimize the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day.

[0052] Thirdly, embodiments of this application provide a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect or any possible implementation of the first aspect above.

[0053] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation of the first aspect.

[0054] The beneficial effects of the virtual power plant operation scheduling method, device, terminal, and storage medium provided in this application embodiment are as follows:

[0055] This application obtains a more accurate virtual power plant operation and scheduling model by calculating the unit carbon emissions and unit power generation costs of each device. Based on historical data of the virtual power plant, this application determines the similar day corresponding to the forecast date and uses the solution of the virtual power plant operation and scheduling model on the similar day as the initial solution for the forecast date. Based on the initial solution, optimization is performed to obtain the scheduling scheme for each controllable load of the virtual power plant within the forecast date. The computational load is reduced during the optimization process, and the resulting scheduling scheme has higher accuracy, stronger applicability, and better energy-saving and emission-reduction effects. Attached Figure Description

[0056] 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.

[0057] Figure 1This is a flowchart illustrating the virtual power plant operation scheduling method provided in an embodiment of this application;

[0058] Figure 2 This is a schematic diagram of the structure of the virtual power plant operation and scheduling device provided in the embodiments of this application;

[0059] Figure 3 This is a schematic diagram of the virtual power plant operation and scheduling terminal provided in the embodiments of this application. Detailed Implementation

[0060] 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.

[0061] 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.

[0062] Figure 1 This is a flowchart illustrating the virtual power plant operation and scheduling method provided in an embodiment of this application. Figure 1 As shown, the method includes:

[0063] Step 101: Based on the historical data of the virtual power plant, determine the similar days corresponding to the prediction day.

[0064] In this embodiment, the historical data of the virtual power plant includes the influencing factors and values ​​of each influencing factor for historical daily electricity consumption within the carbon emission quota cycle. Similar days are determined by calculating the similarity between each influencing factor within the predicted day and each influencing factor within historical days. In determining similar days, the influence weight of each influencing factor is considered, which improves the accuracy of similar day determination.

[0065] Step 102: Obtain the unit power generation cost and unit carbon emission of each device in the virtual power plant, as well as the pre-established virtual power plant operation and scheduling model. The virtual power plant operation and scheduling model is used to determine the scheduling scheme for each controllable load of the virtual power plant based on its input parameters.

[0066] In this embodiment, the unit power generation cost and unit carbon emission of each device in the virtual power plant are obtained based on historical data. A virtual power plant operation and scheduling model is established based on these figures, aiming to minimize both operating costs and carbon emissions. Input parameters include: carbon emission quotas, real-time electricity prices, electricity demand of electrical equipment, and installed capacity data of the virtual power plant. The installed capacity data includes the installed capacity of generator sets, the installed capacity of electrical equipment, and the installed capacity of energy storage devices.

[0067] This embodiment takes into account both power generation costs and carbon emissions, and can simultaneously achieve the goals of cost reduction and carbon emission reduction.

[0068] Step 103: Obtain the solution of the virtual power plant operation scheduling model on similar days, and use the solution of the similar days as the initial solution of the virtual power plant operation scheduling model on the predicted day.

[0069] In this embodiment, the solution of the virtual power plant operation and scheduling model on similar days corresponds to the operation and scheduling scheme of each controllable load of the virtual power plant within the similar days. In this embodiment, the solution of the model on similar days is used as the initial solution of the virtual power plant operation and scheduling model on the prediction day, which can ensure the accuracy and applicability of the scheduling scheme and reduce the computational load of the virtual power plant operation and scheduling model.

[0070] Step 104: Optimize the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day.

[0071] In this embodiment, considering that the control devices in the virtual power plant are diverse and numerous when performing energy dispatch, this embodiment considers using the solution of the virtual power plant operation dispatch model on similar days as the initial solution to optimize the virtual power plant operation dispatch model. This can reduce the number of iterations in the optimization process, thereby reducing the computational load of the model.

[0072] This application obtains a more accurate virtual power plant operation and scheduling model by calculating the unit carbon emissions and unit power generation costs of each device. Based on historical data of the virtual power plant, this application determines the similar day corresponding to the forecast date and uses the solution of the virtual power plant operation and scheduling model on the similar day as the initial solution for the forecast date. Based on the initial solution, optimization is performed to obtain the scheduling scheme for each controllable load of the virtual power plant within the forecast date. The computational load is reduced during the optimization process, and the resulting scheduling scheme has higher accuracy, stronger applicability, and better energy-saving and emission-reduction effects.

[0073] In one possible implementation, the virtual power plant operation scheduling model is optimized based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day, including:

[0074] S1: Fine-tune the initial solution to obtain a population R with a size of N-1. t Population R t The parent population P is obtained by merging the initial solution with the parent population of size N. t .

[0075] S2: Initialize the number of iterations: t = 1.

[0076] S3: Construct a fitness function based on the mapping relationship and pre-set the fitness threshold.

[0077] S4: Calculate the fitness of individuals in the parent population and sort the individuals in the parent population according to their fitness.

[0078] S5: Determine whether there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold. If there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold, then output the optimal solution, which is the scheduling scheme of each controllable load of the virtual power plant corresponding to the maximum fitness value.

[0079] If the fitness of any individual in the parent population is not greater than the preset fitness threshold, then increment the iteration count by 1. Check if the iteration count is greater than the preset iteration count. If the iteration count is greater than the preset iteration count, then output the individual with the highest fitness in the parent population as the optimal solution. If the iteration count is not greater than the preset iteration count, then execute S6.

[0080] S6: Select, crossover, and mutate the parent population to obtain a new offspring population of N. Calculate and sort the fitness of individuals in the offspring population. Replace individuals with high fitness in the offspring population with individuals with low fitness in the parent population. Use the newly generated population after replacement as the parent population. Repeat S4-S6.

[0081] In this embodiment, the preset number of iterations and the preset fitness threshold can be set and modified according to actual conditions. The mapping relationship is: the lower the operating cost and the smaller the carbon emissions, the higher the fitness and the non-negative fitness. This application can obtain N-1 individuals with high accuracy by fine-tuning the initial solution. The parent population obtained by merging the fine-tuned individuals with the initial solution can effectively utilize the initial solution. Effective utilization of the initial solution can improve accuracy and reduce the number of iterations in the optimization process, thus reducing the amount of computation. In S5 of this embodiment, firstly, it is determined whether there is at least one individual in the parent population with a fitness greater than the preset fitness threshold. Based on the above judgment condition, it can be determined whether there is an optimal solution. Secondly, when the fitness of individuals in the parent population is not greater than the preset fitness threshold, the optimization can be terminated by judging whether the number of iterations is greater than the preset number of iterations, thereby reducing the number of iterations and controlling the optimization time. The two judgment conditions in this embodiment can obtain the individual with the highest fitness and control the optimization time within a reasonable range, achieving accurate and fast solution. In this embodiment S6, by replacing individuals with low fitness in the parent population with individuals with high fitness in the offspring population, individuals with low fitness in both the offspring and parent populations can be removed, resulting in a newly generated population with generally high fitness, thus ensuring the accuracy of the population individuals during the optimization process.

[0082] In one possible implementation, the method for establishing the virtual power plant operation and scheduling model includes:

[0083] Obtain carbon emission allowances for virtual power plants within the target area.

[0084] The first objective function is constructed with the goal of minimizing operating costs.

[0085] A second objective function is constructed with the goal of minimizing carbon emissions.

[0086] Based on the carbon emission quotas of virtual power plants within the target area, the unit power generation cost and unit carbon emission of each piece of equipment in the virtual power plant, the constraints of the virtual power plant operation and scheduling model are determined.

[0087] A virtual power plant operation and scheduling model is established based on the first objective function, the second objective function, and the constraints.

[0088] In this embodiment, the constraints of the virtual power plant operation and scheduling model also include: virtual power plant operation constraint data. Operating costs can be obtained by calculating the operating costs of generator sets, energy storage devices, electrical equipment, and the main grid's electricity purchase cost. Carbon emissions can be obtained by calculating the carbon emissions of generator sets, energy storage devices, and electrical equipment.

[0089] In one possible implementation, the first objective function is:

[0090] f1=a×f 1a +b×f 1b +c×f 1c +d×f 1d

[0091] Where f1 is the operating cost, a is the power generation of the generator set, and f 1a Let b be the unit power generation cost of the generator set, b be the discharge capacity of the energy storage device, and f be the discharge capacity of the energy storage device. 1b Let c be the unit discharge cost of the energy storage device, and f be the power consumption of the electrical equipment. 1c Let d be the unit electricity cost of the electrical equipment, and f be the electricity purchased from the main grid. 1d The real-time electricity price for the main grid.

[0092] The second objective function is:

[0093] f2=a×f 2a +b×f 2b +c×f 2c

[0094] Where f2 is carbon emissions, a is the power generation of the generator set, and f 2a b is the unit carbon emission of the generator set, f is the discharge capacity of the energy storage device, and f is the unit carbon emission of the generator set. 2b Let f be the carbon emissions per unit of energy storage equipment, c be the electricity consumption of the electrical equipment, and f be the energy consumption per unit of energy storage equipment. 2c This refers to the carbon emissions per unit of electrical equipment.

[0095] In this embodiment, the virtual power plant contains generator sets of various energy sources, various types of energy storage devices, and various types of electrical equipment. To improve the accuracy of the calculation of the first objective function and the second objective function, it is necessary to calculate the unit power generation cost and unit carbon emission of each device.

[0096] The operating cost of the generator set is a×f 1a The operating cost of the energy storage device is b×f 1b The operating cost of the electrical equipment is c×f 1c The cost of purchasing electricity from the main grid is d×f 1d The carbon emissions of the generator set are a×f 2a The carbon emissions of energy storage devices are b×f 2b The carbon emissions from electrical equipment are c×f 2c .

[0097] The unit power generation cost of the generator set is:

[0098]

[0099] Among them, f 2a A represents the unit power generation cost of the generator set. 2aFor the investment cost of the generator set, B 2aj C represents the operation and maintenance cost of the generator unit in year j. 2aj For the depreciation of the generator set in year j, E 2a For the environmental cost of generator sets, D 2aj This represents the power generation of the generator unit in year j.

[0100] The unit discharge cost of energy storage equipment is:

[0101]

[0102] Among them, f 2b A represents the unit discharge cost of energy storage devices. 2b For the investment cost of energy storage equipment, B 2bk Let C be the operation and maintenance cost of the energy storage device in year k. 2bk Let D be the depreciation of the energy storage device in year k, e be the number of charge-discharge cycles of the energy storage device, and D be the depreciation of the energy storage device in year k. 2b Let θ represent the capacity of the energy storage device, and θ represent the charging and discharging efficiency of the energy storage device.

[0103] The unit electricity cost of electrical equipment is:

[0104]

[0105] Among them, f 2c A represents the unit electricity cost of electrical equipment. 2c B represents the investment cost of electrical equipment. 2cm C represents the operation and maintenance cost of the electrical equipment in year m. 2cm For the depreciation of electrical equipment in year m, D 2cm Let be the electricity consumption of the electrical equipment in year m.

[0106] In one possible implementation, the method for determining the unit carbon emission includes:

[0107] Obtain historical data for each device in the virtual power plant.

[0108] By analyzing the historical data of each device, we can obtain the historical energy consumption and power generation of generator sets of various energy sources, the historical power consumption and discharge of various energy storage devices, and the historical power consumption of various electrical devices.

[0109] Carbon content calculations are performed on the historical energy consumption of generator sets of various energy sources to obtain the historical carbon emissions of the generator sets. Based on the historical carbon emissions and historical power generation of the generator sets, the unit carbon emissions of the generator sets are determined.

[0110] Carbon content calculations are performed on the historical electricity consumption of various energy storage devices to obtain their historical carbon emissions. Based on the historical carbon emissions and historical discharge volumes of the energy storage devices, the unit carbon emissions of the energy storage devices are determined.

[0111] Carbon content is calculated based on the historical electricity consumption of various electrical devices to obtain their historical carbon emissions. Based on the historical carbon emissions and historical electricity consumption of the electrical devices, the unit carbon emission of each device is determined.

[0112] In this embodiment, the generator sets for various energy sources include: conventional generator sets and new energy generator sets. Conventional generator sets mainly generate electricity using traditional energy sources (coal, crude oil, natural gas, hydropower, etc.), while new energy generator sets mainly include wind turbine generator sets and photovoltaic generator sets. Various energy storage devices include: mechanical energy storage devices, electrochemical energy storage devices, and electrical energy storage devices. Electrochemical energy storage devices are mainly used in daily life, such as car charging stations, lead-acid batteries, and lithium-ion batteries. Various electrical appliances include: household electrical appliances, enterprise electrical appliances, and industrial electrical appliances.

[0113] In one possible implementation, similar days corresponding to the prediction date are determined based on historical data from the virtual power plant, including:

[0114] Obtain the influencing factors and values ​​of each factor in historical daily electricity consumption.

[0115] The influence weight of each influencing factor is calculated based on the volatility and correlation of the values ​​of each influencing factor.

[0116] Obtain the values ​​of each influencing factor for the forecast date.

[0117] The similar days corresponding to the forecast date are determined based on the values ​​of each influencing factor, their weights, and the values ​​of each influencing factor for electricity consumption in historical days.

[0118] The influencing factors include meteorological factors and non-meteorological factors.

[0119] In this embodiment, it is necessary to preprocess the values ​​of various influencing factors of historical daily electricity consumption. Preprocessing may include: missing value completion, continuous outlier correction, discrete outlier correction, standardization, and normalization.

[0120] In this embodiment, the similarity between the historical day and the predicted day is calculated based on the values ​​of each influencing factor and its weight on the predicted day, as well as the values ​​of each influencing factor in the historical day's electricity consumption. The degree of influence of each influencing factor on electricity consumption can be obtained by calculating its weight. The CRITIC weighting method can be used to calculate the weight of each influencing factor. The CRITIC weighting method calculates weights based on the volatility (comparison strength) of each influencing factor value and the correlation between influencing factors, objectively assigning the weight of each influencing factor without manual determination. It takes into account the correlation between influencing factors, making the calculated similarity more accurate and improving the accuracy of similar day determination.

[0121] In this embodiment, the method for determining similarity may include, but is not limited to, Euclidean distance, Pearson correlation coefficient, Manhattan distance, cosine similarity, and dynamic time warping algorithm. Influencing factors may include: meteorological factors such as the highest and lowest temperatures of the day, the highest and lowest humidity of the day, wind direction, wind speed, and weather conditions; and non-meteorological factors such as season, day type (weekday, holiday, weekend), economic development level, and relevant policies. For example, taking Euclidean distance as an example, the method for determining the similarity between historical days and predicted days in this embodiment is as follows:

[0122]

[0123] Where s is the similarity between historical dates and predicted dates, r is the influencing factor number, and x r Let z be the influencing factor value corresponding to the r-th influencing factor in historical days. r To predict the value of the r-th influencing factor on a given day, h r Let r be the influence weight of the r-th influencing factor.

[0124] In one possible implementation, constraints on the virtual power plant operation and scheduling model are determined based on the carbon emission quotas of the virtual power plant within the target area, the unit power generation cost of each piece of equipment in the virtual power plant, and the unit carbon emission. These constraints include:

[0125] Establish carbon emission quota constraints based on carbon emission quotas: f2≤P1.

[0126] Establish concentration constraints based on greenhouse gas concentrations calculated from carbon emissions: y i ≤P 2i .

[0127] Based on the power generation of the generator set, the discharge of the energy storage device, the power purchased by the main grid, and the power consumption of the electrical equipment, the following power constraint condition is established: P3≤g1+g2+g3.

[0128] Where f2 is the carbon emission amount, P1 is the carbon emission allowance, and y i For each greenhouse gas concentration, P2i For each greenhouse gas, P3 represents the electricity consumption of electrical equipment, g1 represents the power generation of generator sets, g2 represents the discharge of energy storage devices, and g3 represents the electricity purchased by the main grid.

[0129] The constraints of the virtual power plant operation and scheduling model also include: virtual power plant operation constraint data.

[0130] In this embodiment, the carbon emission quota constraint established through carbon emission quotas can effectively control carbon emissions and prevent the virtual power plant from operating with a scheduling scheme that exceeds the carbon emission quota. Greenhouse gases include: carbon dioxide, methane, nitrous oxide, hydrofluorocarbons, perfluorinated carbon, sulfur hexafluoride, etc. For example, the environmental indicators corresponding to sulfur hexafluoride include: the permissible concentration of sulfur hexafluoride gas in the operating room air is not greater than 6 g / m³. 3 Alternatively, the oxygen content in the air should be greater than 18%; for short-term exposure, the permissible concentration of sulfur hexafluoride gas in the air should not exceed 7.5 g / m³. 3 .

[0131] In this embodiment, the virtual power plant operation constraint data includes: power balance constraints, node voltage constraints, upper and lower limits of output and ramp rate constraints of conventional generator sets, upper and lower limits of regulation and regulation rate constraints of controllable loads, charging and discharging power constraints of energy storage devices, maximum output constraints of wind power generation and maximum output constraints of photovoltaic power generation.

[0132] For example, the power balance constraint is that the difference between the generation and load of the virtual power plant is equal to the dispatched electricity between the virtual power plant and the main grid. The dispatched electricity between the virtual power plant and the main grid is the electricity purchased by the main grid.

[0133] For example, node voltage constraints require that the node voltage of each node within the virtual power plant meets voltage standards. For instance, the variation range of the node voltage for each node should be 50 ± 0.2 Hz.

[0134] For example, the upper and lower limits of the output of a conventional generator set should meet the design standards. This means the output power of the conventional generator set is greater than the minimum limit but less than the maximum limit. The ramp rate of the conventional generator set should be less than the set value.

[0135] For example, the upper and lower limits of controllable load regulation are constrained to ensure that the regulation power of the controllable load is greater than the minimum limit and less than the maximum limit. The minimum and maximum limits of the regulation power of the controllable load should be determined based on the operating conditions of the controllable load.

[0136] For example, the charging and discharging power constraints of energy storage devices are that the charging power and discharging power of energy storage devices should be greater than the minimum limit and less than the maximum limit.

[0137] For example, the maximum output constraint for wind power generation is that the output power of wind power generation should be less than the maximum limit.

[0138] For example, the maximum output constraint for photovoltaic power generation. The output power of photovoltaic power generation should be less than the maximum limit.

[0139] In this embodiment, considering both operating costs and carbon emissions, the determined scheduling scheme controls the operation of each controllable load of the virtual power plant within the forecast day, achieving carbon emission reduction targets at a lower cost. With the same amount of data, this scheme requires fewer iterations. By calculating the unit carbon emissions and unit power generation costs of each device, this application obtains more accurate carbon emissions and operating costs. The solution of the virtual power plant operation scheduling model on similar days is used as the initial solution for the forecast day. Optimizing the virtual power plant operation scheduling model based on this initial solution enables effective utilization of the initial solution, while simultaneously improving the accuracy of the virtual power plant operation scheduling model, enhancing the applicability of the scheduling scheme, and improving the energy-saving and emission-reduction effects during virtual power plant operation.

[0140] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0141] The following are device embodiments of this application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0142] Figure 2 A schematic diagram of the structure of the virtual power plant operation and scheduling device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown, and are described in detail below:

[0143] like Figure 2 As shown, the virtual power plant operation and scheduling device 20 includes:

[0144] The similarity day determination module 21 is used to determine the similar day corresponding to the predicted day based on the historical data of the virtual power plant.

[0145] Model building module 22 is used to obtain the unit power generation cost and unit carbon emission of each device in the virtual power plant, as well as the pre-established virtual power plant operation and scheduling model. The virtual power plant operation and scheduling model is used to determine the scheduling scheme for each controllable load of the virtual power plant based on its input parameters.

[0146] The initial solution determination module 23 is used to obtain the solution of the virtual power plant operation scheduling model on similar days, and the solution on similar days will be used as the initial solution of the virtual power plant operation scheduling model on the predicted day.

[0147] The scheduling scheme determination module 24 is used to optimize the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day.

[0148] In one possible implementation, the scheduling scheme determination module 24 is used to optimize the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day.

[0149] This is used to optimize the virtual power plant operation scheduling model based on the initial solution, and to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day, including:

[0150] S1: Fine-tune the initial solution to obtain a population R with a size of N-1. t Population R t The parent population P is obtained by merging the initial solution with the parent population of size N. t .

[0151] S2: Initialize the number of iterations: t = 1.

[0152] S3: Construct a fitness function based on the mapping relationship and pre-set the fitness threshold.

[0153] S4: Calculate the fitness of individuals in the parent population and sort the individuals in the parent population according to their fitness.

[0154] S5: Determine whether there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold. If there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold, then output the optimal solution, which is the scheduling scheme of each controllable load of the virtual power plant corresponding to the maximum fitness value.

[0155] If the fitness of any individual in the parent population is not greater than the preset fitness threshold, then increment the iteration count by 1. Check if the iteration count is greater than the preset iteration count. If the iteration count is greater than the preset iteration count, then output the individual with the highest fitness in the parent population as the optimal solution. If the iteration count is not greater than the preset iteration count, then execute S6.

[0156] S6: Select, crossover, and mutate the parent population to obtain a new offspring population of N. Calculate and sort the fitness of individuals in the offspring population. Replace individuals with high fitness in the offspring population with individuals with low fitness in the parent population. Use the newly generated population after replacement as the parent population. Repeat S4-S6.

[0157] In one possible implementation, the model building module 22 is used to determine the method for building the virtual power plant operation and scheduling model.

[0158] The method for establishing a virtual power plant operation and scheduling model is determined, including:

[0159] Obtain carbon emission allowances for virtual power plants within the target area.

[0160] The first objective function is constructed with the goal of minimizing operating costs.

[0161] A second objective function is constructed with the goal of minimizing carbon emissions.

[0162] Based on the carbon emission quotas of virtual power plants within the target area, the unit power generation cost and unit carbon emission of each piece of equipment in the virtual power plant, the constraints of the virtual power plant operation and scheduling model are determined.

[0163] A virtual power plant operation and scheduling model is established based on the first objective function, the second objective function, and the constraints.

[0164] In one possible implementation, the model building module 22 is used to determine the first objective function and the second objective function.

[0165] The first objective function is:

[0166] f1=a×f 1a +b×f 1b +c×f 1c +d×f 1d

[0167] Where f1 is the operating cost, a is the power generation of the generator set, and f 1a Let b be the unit power generation cost of the generator set, b be the discharge capacity of the energy storage device, and f be the discharge capacity of the energy storage device. 1b Let c be the unit discharge cost of the energy storage device, and f be the power consumption of the electrical equipment. 1c Let d be the unit electricity cost of the electrical equipment, and f be the electricity purchased from the main grid. 1d The real-time electricity price for the main grid.

[0168] The second objective function is:

[0169] f2=a×f 2a +b×f 2b +c×f 2c

[0170] Where f2 is carbon emissions, a is the power generation of the generator set, and f 2a b is the unit carbon emission of the generator set, f is the discharge capacity of the energy storage device, and f is the unit carbon emission of the generator set. 2b Let f be the carbon emissions per unit of energy storage equipment, c be the electricity consumption of the electrical equipment, and f be the energy consumption per unit of energy storage equipment. 2c This refers to the carbon emissions per unit of electrical equipment.

[0171] In one possible implementation, model building module 22 is used to determine the unit carbon emissions.

[0172] Methods for determining unit carbon emissions include:

[0173] Obtain historical data for each device in the virtual power plant.

[0174] By analyzing the historical data of each device, we can obtain the historical energy consumption and power generation of generator sets of various energy sources, the historical power consumption and discharge of various energy storage devices, and the historical power consumption of various electrical devices.

[0175] Carbon content calculations are performed on the historical energy consumption of generator sets of various energy sources to obtain the historical carbon emissions of the generator sets. Based on the historical carbon emissions and historical power generation of the generator sets, the unit carbon emissions of the generator sets are determined.

[0176] Carbon content calculations are performed on the historical electricity consumption of various energy storage devices to obtain their historical carbon emissions. Based on the historical carbon emissions and historical discharge volumes of the energy storage devices, the unit carbon emissions of the energy storage devices are determined.

[0177] Carbon content is calculated based on the historical electricity consumption of various electrical devices to obtain their historical carbon emissions. Based on the historical carbon emissions and historical electricity consumption of the electrical devices, the unit carbon emission of each device is determined.

[0178] In one possible implementation, the similarity day determination module 21 is used to determine the similar day corresponding to the predicted day based on the historical data of the virtual power plant.

[0179] Based on historical data from the virtual power plant, similar days corresponding to the prediction date are determined, including:

[0180] Obtain the influencing factors and values ​​of each factor in historical daily electricity consumption.

[0181] The influence weight of each influencing factor is calculated based on the volatility and correlation of the values ​​of each influencing factor.

[0182] Obtain the values ​​of each influencing factor for the forecast date.

[0183] The similar days corresponding to the forecast date are determined based on the values ​​of each influencing factor, their weights, and the values ​​of each influencing factor for electricity consumption in historical days.

[0184] The influencing factors include meteorological factors and non-meteorological factors.

[0185] In one possible implementation, the model building module 22 is used to determine the constraints of the virtual power plant operation and scheduling model based on the carbon emission quota of the virtual power plant in the target area, the unit power generation cost and unit carbon emission of each piece of equipment in the virtual power plant.

[0186] Based on the carbon emission quotas of virtual power plants within the target area, the unit power generation cost and unit carbon emission of each piece of equipment in the virtual power plants, the constraints of the virtual power plant operation and scheduling model are determined, including:

[0187] Establish carbon emission quota constraints based on carbon emission quotas: f2≤P1.

[0188] Establish concentration constraints based on greenhouse gas concentrations calculated from carbon emissions: y i ≤P 2i .

[0189] Based on the power generation of the generator set, the discharge of the energy storage device, the power purchased by the main grid, and the power consumption of the electrical equipment, the following power constraint condition is established: P3≤g1+g2+g3.

[0190] Where f2 is the carbon emission amount, P1 is the carbon emission allowance, and y i For each greenhouse gas concentration, P 2i For each greenhouse gas, P3 represents the electricity consumption of electrical equipment, g1 represents the power generation of generator sets, g2 represents the discharge of energy storage devices, and g3 represents the electricity purchased by the main grid.

[0191] The constraints of the virtual power plant operation and scheduling model also include: virtual power plant operation constraint data.

[0192] Figure 3 This is a schematic diagram of the virtual power plant operation and scheduling terminal provided in an embodiment of this application. Figure 3 As shown, the terminal 30 in this embodiment includes a processor 31, a memory 32, and a computer program 33 stored in the memory 32 and executable on the processor 31. When the processor 31 executes the computer program 33, it implements the steps described in the various virtual power plant operation scheduling method embodiments above, for example... Figure 1 As shown in 101 to 104. Alternatively, when processor 31 executes computer program 33, it implements the functions of each module in the above-described device embodiments, for example... Figure 2 The functions of modules 21 to 24 are shown.

[0193] For example, computer program 33 can be divided into one or more modules, one or more modules are stored in memory 32 and executed by processor 31 to complete this application. The one or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 33 in terminal 30. For example, computer program 33 can be divided into... Figure 2 Modules 21 to 24 are shown.

[0194] Terminal 30 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. Terminal 30 may include, but is not limited to, a processor 31 and a memory 32. Those skilled in the art will understand that... Figure 3 This is merely an example of terminal 30 and does not constitute a limitation on terminal 30. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal may also include input / output devices, network access devices, buses, etc.

[0195] The processor 31 may be a Central Processing Unit (CPU), or 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. A general-purpose processor may be a microprocessor or any conventional processor.

[0196] The memory 32 can be an internal storage unit of the terminal 30, such as a hard disk or RAM of the terminal 30. The memory 32 can also be an external storage device of the terminal 30, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal 30. Furthermore, the memory 32 can include both internal and external storage units of the terminal 30. The memory 32 is used to store computer programs and other programs and data required by the terminal. The memory 32 can also be used to temporarily store data that has been output or will be output.

[0197] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0198] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0199] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. 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 implementation should not be considered beyond the scope of this application.

[0200] In the embodiments provided in this application, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0203] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. 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 virtual power plant operation scheduling 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, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0204] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A virtual power plant operation and scheduling method, characterized in that, include: Based on the historical data of the virtual power plant, determine the similar days corresponding to the prediction date; The unit power generation cost and unit carbon emission of each device in the virtual power plant are obtained, as well as a pre-established virtual power plant operation and scheduling model; wherein, the virtual power plant operation and scheduling model is used to determine the scheduling scheme of each controllable load of the virtual power plant based on its input parameters; Obtain the solution of the virtual power plant operation scheduling model on similar days, and use the solution on similar days as the initial solution of the virtual power plant operation scheduling model on the predicted day; Based on the initial solution, the virtual power plant operation scheduling model is optimized to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day. The optimization of the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day includes: S1: Fine-tune the initial solution to obtain a population R with a population size of N-1. t Population R t The parent population P is obtained by merging the initial solution with the parent population of size N. t ; S2: Initialize the number of iterations: t=1; S3: Construct a fitness function based on the mapping relationship and pre-set a fitness threshold; the mapping relationship is: the lower the operating cost and the smaller the carbon emissions, the higher the fitness and the non-negative fitness. S4: Calculate the fitness of individuals in the parent population and sort the individuals in the parent population according to their fitness. S5: Determine whether there is at least one individual in the parent population whose fitness is greater than a preset fitness threshold. If there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold, then output the optimal solution. The optimal solution is the scheduling scheme of each controllable load of the virtual power plant corresponding to the maximum fitness value. If the fitness of any individual in the parent population is not greater than the preset fitness threshold, then increment the iteration count by 1; determine if the iteration count is greater than the preset iteration count. If the iteration count is greater than the preset iteration count, then output the individual with the highest fitness in the parent population as the optimal solution. If the iteration count is not greater than the preset iteration count, then execute S6. S6: Select, crossover, and mutate the parent population to obtain a new offspring population of N. Calculate and sort the fitness of individuals in the offspring population. Replace individuals with high fitness in the offspring population with individuals with low fitness in the parent population. Use the newly generated population after replacement as the parent population. Repeat S4-S6. The step of determining the similar day corresponding to the prediction day based on the historical data of the virtual power plant includes: Obtain the influencing factors and values ​​of each factor in historical daily electricity consumption; Calculate the influence weight of each influencing factor based on the volatility and correlation of the values ​​of each influencing factor; Obtain the values ​​of each influencing factor for the forecast date; The similar days corresponding to the predicted day are determined based on the values ​​of each influencing factor for the predicted day, the influencing weights, and the values ​​of each influencing factor for the electricity consumption in the historical days. The influencing factors include meteorological factors and non-meteorological factors.

2. The method according to claim 1, characterized in that, The method for establishing the virtual power plant operation and scheduling model includes: Obtain carbon emission allowances for virtual power plants within the target area; To minimize operating costs, a first objective function is constructed. To minimize carbon emissions, a second objective function is constructed. Based on the carbon emission quotas of the virtual power plants in the target area, the unit power generation cost and unit carbon emission of each piece of equipment in the virtual power plants, the constraints of the virtual power plant operation and scheduling model are determined. Based on the first objective function, the second objective function, and the constraints, the virtual power plant operation and scheduling model is established.

3. The method according to claim 2, characterized in that, The first objective function is: in, For operating costs, The power generation of the generator set, The unit power generation cost of the generator set, This refers to the discharge capacity of the energy storage device. The unit discharge cost of energy storage devices. The power consumption of electrical equipment. The unit electricity cost of electrical equipment, Electricity purchased for the main network The real-time electricity price for the main grid; The second objective function is: in, For carbon emissions, The power generation of the generator set, This refers to the unit carbon emissions of the generator set. This refers to the discharge capacity of the energy storage device. This refers to the unit carbon emissions of energy storage devices. The power consumption of electrical equipment. This refers to the carbon emissions per unit of electrical equipment.

4. The method according to claim 3, characterized in that, The method for determining the unit carbon emission includes: Obtain historical data for each device in the virtual power plant; By analyzing the historical data of each device, we can obtain the historical energy consumption and historical power generation of generator sets of various energy sources, the historical power consumption and historical discharge of various energy storage devices, and the historical power consumption of various electrical devices. Carbon content is calculated for the historical energy consumption of generator sets of various energy sources to obtain the historical carbon emissions of the generator sets; based on the historical carbon emissions and historical power generation of the generator sets, the unit carbon emissions of the generator sets are determined. Carbon content calculation is performed on the historical power consumption of various energy storage devices to obtain the historical carbon emissions of the energy storage devices; based on the historical carbon emissions and historical discharge of the energy storage devices, the unit carbon emissions of the energy storage devices are determined. Carbon content is calculated based on the historical electricity consumption of various electrical devices to obtain the historical carbon emissions of the devices; based on the historical carbon emissions and historical electricity consumption of the devices, the unit carbon emissions of the devices are determined.

5. The method according to claim 2, characterized in that, The constraints for determining the virtual power plant operation and scheduling model based on the carbon emission quotas of the virtual power plant within the target area, the unit power generation cost of each piece of equipment in the virtual power plant, and the unit carbon emission amount include: Establish carbon emission quota constraints based on the aforementioned carbon emission quotas: ; Based on the aforementioned carbon emissions, greenhouse gas concentrations are calculated, and concentration constraints are established: ; Establish power constraints based on the power generation of generator sets, the discharge of energy storage devices, the power purchased by the main grid, and the power consumption of electrical equipment: ; in, For carbon emissions, For carbon emission quotas, For the concentrations of various greenhouse gases, For each greenhouse gas, the corresponding environmental indicators are: The power consumption of electrical equipment. The power generation of the generator set, This refers to the discharge capacity of the energy storage device. The amount of electricity purchased for the main network.

6. A virtual power plant operation and dispatching device, characterized in that, include: The similarity day determination module is used to determine the similarity day corresponding to the prediction day based on the historical data of the virtual power plant. The model building module is used to obtain the unit power generation cost and unit carbon emission of each device in the virtual power plant, as well as the pre-established virtual power plant operation and scheduling model; wherein, the virtual power plant operation and scheduling model is used to determine the scheduling scheme of each controllable load of the virtual power plant based on its input parameters; The initial solution determination module is used to obtain the solution of the virtual power plant operation scheduling model on similar days, and use the solution on similar days as the initial solution of the virtual power plant operation scheduling model on the predicted day; The scheduling scheme determination module is used to optimize the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day. The optimization of the virtual power plant operation scheduling model based on the initial solution to obtain the scheduling scheme for each controllable load of the virtual power plant during the predicted day includes: S1: Fine-tune the initial solution to obtain a population R with a population size of N-1. t Population R t The parent population P is obtained by merging the initial solution with the parent population of size N. t ; S2: Initialize the number of iterations: t=1; S3: Construct a fitness function based on the mapping relationship and pre-set a fitness threshold; the mapping relationship is: the lower the operating cost and the smaller the carbon emissions, the higher the fitness and the non-negative fitness. S4: Calculate the fitness of individuals in the parent population and sort the individuals in the parent population according to their fitness. S5: Determine whether there is at least one individual in the parent population whose fitness is greater than a preset fitness threshold. If there is at least one individual in the parent population whose fitness is greater than the preset fitness threshold, then output the optimal solution. The optimal solution is the scheduling scheme of each controllable load of the virtual power plant corresponding to the maximum fitness value. If the fitness of any individual in the parent population is not greater than the preset fitness threshold, then increment the iteration count by 1; determine if the iteration count is greater than the preset iteration count. If the iteration count is greater than the preset iteration count, then output the individual with the highest fitness in the parent population as the optimal solution. If the iteration count is not greater than the preset iteration count, then execute S6. S6: Select, crossover, and mutate the parent population to obtain a new offspring population of N. Calculate and sort the fitness of individuals in the offspring population. Replace individuals with high fitness in the offspring population with individuals with low fitness in the parent population. Use the newly generated population after replacement as the parent population. Repeat S4-S6. The step of determining the similar day corresponding to the prediction day based on the historical data of the virtual power plant includes: Obtain the influencing factors and values ​​of each factor in historical daily electricity consumption; Calculate the influence weight of each influencing factor based on the volatility and correlation of the values ​​of each influencing factor; Obtain the values ​​of each influencing factor for the forecast date; The similar days corresponding to the predicted day are determined based on the values ​​of each influencing factor for the predicted day, the influencing weights, and the values ​​of each influencing factor for the electricity consumption in the historical days. The influencing factors include meteorological factors and non-meteorological factors.

7. A terminal, 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 as described in any one of claims 1 to 5 above.

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 above.

Images