Virtual power plant renewable energy optimization configuration method

Abstract

The invention relates to the technical field of power optimization, and discloses a virtual power plant renewable energy optimal configuration method, which comprises the following steps: generating a multi-time initial configuration scheme according to multi-time scale resource data; generating constraint conditions of the multi-time-scale resource data according to the constraint attributes of the virtual power plant, and constructing a multi-time-scale optimization model according to the constraint conditions and the multi-time-scale resource data; using the multi-time scale optimization model to analyze the minimum operation cost of the virtual power plant, and performing rolling time domain optimization on the multi-time initial configuration scheme according to the minimum operation cost; calculating the sensitivity of the optimized multi-time initial configuration scheme according to the constraint condition, and determining an optimization factor of the multi-time initial configuration scheme through the sensitivity; and generating a configuration path of renewable energy optimization configuration according to the optimization factor, and determining an optimal configuration scheme of renewable energy of the virtual power plant according to the configuration path. According to the invention, the accuracy of virtual power plant renewable energy optimization configuration can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power optimization, and in particular to a method for optimizing the configuration of renewable energy in a virtual power plant. Background Art

[0002] As the global demand for clean energy continues to increase, the installed capacity of renewable energy such as solar energy and wind energy continues to grow rapidly. However, renewable energy is intermittent and volatile, which means that after large-scale access to the power grid, it poses a huge challenge to the stable operation of the power system. More efficient energy configuration methods are needed to ensure a reliable supply of electricity.

[0003] Existing renewable energy optimization configuration technologies are mostly based on real-time data to build mathematical models, and the optimal configuration plan is obtained by solving the mathematical models. However, in the actual operation process, due to sensor failure, communication interruption and other reasons, data missing or abnormal situations may occur, resulting in low accuracy in the optimization configuration of renewable energy in virtual power plants. Summary of the invention

[0004] The present invention provides a method for optimizing the configuration of renewable energy in a virtual power plant, the main purpose of which is to solve the problem of low accuracy in optimizing the configuration of renewable energy in a virtual power plant.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for optimizing the configuration of renewable energy in a virtual power plant, comprising: Collect multi-time scale resource data of renewable energy in the area covered by the virtual power plant, and generate a multi-time initial configuration plan of renewable energy of the virtual power plant according to the multi-time scale resource data; Generating constraint conditions of the multi-timescale resource data according to constraint attributes of the virtual power plant, and constructing a multi-timescale optimization model according to the constraint conditions and the multi-timescale resource data, including: A multi-time scale optimization model is constructed according to the multi-time scale resource data under the constraint conditions, wherein the multi-time scale optimization model is: ; in, is the minimum function, is the maximum value function, is the unit power generation cost of the photovoltaic power station, For the The power generation of the photovoltaic power station at any moment, is the unit power generation cost of the wind farm, For the The power generation of the wind farm at the moment, For the The unit price of electricity purchased from the grid at any given moment, For the The power purchased from the grid at all times, For the The unit price of electricity sold to the grid at any given moment, The unit cost of charging the energy storage, For the The charging power of energy storage at all times, is the unit cost of energy storage discharge, For the The discharge power of the energy storage system at any moment, is the total number of time steps; Analyzing the minimized operating cost of the virtual power plant using the multi-time scale optimization model, and performing rolling time domain optimization on the multi-time initial configuration scheme according to the minimized operating cost; Calculate the sensitivity of the optimized multi-time initial configuration scheme according to the constraint conditions, and determine the optimization factor of the optimized multi-time initial configuration scheme according to the sensitivity; A configuration path for optimizing the configuration of renewable energy is generated according to the optimization factors, and an optimal configuration scheme for the renewable energy of the virtual power plant is determined according to the configuration path.

[0006] Optionally, the collecting of multi-time scale resource data of renewable energy in the area covered by the virtual power plant includes: Obtain data time scale for the area covered by the virtual power plant; Determining a data collection interval for renewable energy sources according to the data time scale; Collect resource data corresponding to the data time scale through the data collection interval; The resource data corresponding to the data time scales are collected to obtain multi-time scale resource data of renewable energy.

[0007] Optionally, the generating a multi-time initial configuration scheme of renewable energy of a virtual power plant according to the multi-time scale resource data comprises: Determining a long-term configuration requirement of a virtual power plant according to the long-term resource data in the multi-time scale resource data, and generating a long-term initial configuration plan according to the long-term configuration requirement; Determining a mid-term configuration requirement of a virtual power plant according to the mid-term resource data in the multi-timescale resource data, and generating a mid-term initial configuration plan according to the mid-term configuration requirement; Determine the short-term configuration requirements of the virtual power plant according to the short-term resource data in the multi-time scale resource data, and generate a short-term initial configuration plan according to the short-term configuration requirements; The long-term initial configuration plan, the medium-term initial configuration plan and the short-term initial configuration plan are integrated into a multi-time initial configuration plan for renewable energy.

[0008] Optionally, generating the constraint conditions of the multi-timescale resource data according to the constraint attributes of the virtual power plant includes: Extracting power balance constraint attributes, power generation equipment operation constraint attributes, energy storage constraint attributes and power grid interaction constraint attributes from the constraint attributes; A power balance constraint condition for the multi-time scale resource data is generated according to the power balance constraint attribute, wherein the power balance constraint condition is: ; in, For the The power generation of the photovoltaic power station at any moment, For the The power generation of the wind farm at the moment, For the The discharge power of the energy storage at any time, For the The power purchased from the grid at all times, For the The load power demand at the moment, For the The charging power of energy storage at all times, is the total number of time steps; The power constraints of the power generation equipment of the multi-time scale resource data are generated according to the power generation equipment operation constraint attributes, wherein the power generation equipment constraints are: ; in, For the The power generation of the photovoltaic power station at any moment, For the The power generation of the wind farm at the moment, is the maximum power generation capacity of the photovoltaic power station, is the maximum power generation of the wind farm; Generate energy storage constraint conditions for the multi-timescale resource data according to the energy storage constraint attributes, and generate power grid interaction constraint conditions for the multi-timescale resource data according to the power grid interaction constraint attributes; The power balance constraint condition, the power generation equipment constraint condition, the energy storage constraint condition and the power grid interaction constraint condition are determined as constraint conditions of multi-time scale resource data.

[0009] Optionally, generating the energy storage constraint condition of the multi-time scale resource according to the energy storage constraint attribute includes: The charge and discharge power constraint condition is generated according to the energy storage constraint attribute, wherein the charge and discharge power constraint condition is: ; in, For the The charging power of energy storage at all times, For the The discharge power of the energy storage at any time, is the maximum charging power of the energy storage, is the maximum discharge power of energy storage; The state of charge update equation is determined according to the charging power and discharging power of the energy storage, where the state of charge update equation is: ; in, For the The state of charge at the moment, For the The state of charge at the moment, For the The charging power of energy storage at all times, For the The discharge power of the energy storage system at any moment, is the time step, is the charging efficiency of energy storage, is the discharge efficiency of energy storage; Determining state of charge constraints using the state of charge update equation; The charging and discharging power constraint condition and the state of charge constraint condition are determined as energy storage constraint conditions of multi-time scale resource data.

[0010] Optionally, analyzing the minimization of operating costs of a virtual power plant by using the multi-time scale optimization model includes: Obtain real-time resource data of renewable energy for virtual power plants; Calculating the optimization value corresponding to the real-time resource data using the multi-time scale optimization model; The minimum optimization value is selected as the minimized operating cost of the virtual power plant.

[0011] Optionally, performing rolling time domain optimization on the multi-time initial configuration scheme according to the minimized operating cost includes: Configuring a rolling time domain of the multi-time initial configuration scheme; Extracting target resource data of renewable energy corresponding to the minimized operating cost; Optimizing the short-term initial configuration scheme in the multi-time initial configuration scheme according to the target resource data; Optimizing the mid-term initial configuration scheme in the multi-time initial configuration scheme by using the optimized short-term initial configuration scheme; Optimizing the long-term initial configuration scheme in the multi-time initial configuration scheme by using the optimized medium-term initial configuration scheme; The rolling direction of the optimized long-term initial configuration scheme is determined according to the rolling time domain, and the multi-time initial configuration scheme is optimized according to the rolling direction.

[0012] Optionally, calculating the sensitivity of the optimized multi-time initial configuration scheme according to the constraint condition includes: Extracting constraint data from the optimized multi-time initial configuration scheme; Determine the constraint factor corresponding to the constraint data according to the constraint condition: ; in, For the The constraint factor corresponding to the constraint data is For the Constraint data, No. Constraint conditions corresponding to constraint data; The sensitivity of the optimized multi-time initial configuration scheme is calculated according to the constraint factors: ; in, The optimized multi-time initial configuration scheme The sensitivity of the scheme corresponding to the time domain, The optimized multi-time initial configuration scheme The scheme corresponding to the time domain The constraint factor corresponding to the constraint data is The optimized multi-time initial configuration scheme The total number of constraints for the solution corresponding to the time domain.

[0013] Optionally, determining the optimization factor of the optimized multi-time initial configuration scheme through the sensitivity includes: When the sensitivity is equal to a preset first sensitivity threshold and greater than a preset second sensitivity threshold, determining the optimization factor of the optimized multi-time initial configuration scheme as the first factor; When the sensitivity is less than a preset second sensitivity threshold and greater than a preset third sensitivity threshold, the optimization factor of the optimized multi-time initial configuration scheme is determined as the second factor.

[0014] Optionally, generating a configuration path for optimizing the configuration of renewable energy according to the optimization factor includes: Determining the configuration path of the renewable energy optimization configuration as an open-loop path according to a first factor in the optimization factors; Determining the configuration path of the renewable energy optimization configuration as a closed-loop path according to the second factor in the optimization factor; A configuration decision tree for optimizing the configuration of renewable energy is generated according to the open-loop path and the closed-loop path, and a configuration path for optimizing the configuration of renewable energy is determined through the configuration decision tree.

[0015] The present invention can comprehensively grasp the distribution and change law of renewable energy in the area covered by the virtual power plant by collecting renewable energy resource data at multiple time scales; generate constraint conditions according to the constraint attributes of the virtual power plant, and ensure the feasibility and safety of the virtual power plant in the actual operation process; construct a multi-time scale optimization model, and can incorporate resource data and constraint conditions at different time scales into a unified model framework; analyze the minimized operating cost of the virtual power plant through the multi-time scale optimization model, and find the optimal operating strategy under various constraint conditions; determine the optimization factor of the optimized multi-time initial configuration scheme through sensitivity, and quantify the adjustment range of each factor; generate the configuration path of the optimal configuration of renewable energy according to the optimization factor, so that the optimization process is operable and controllable. Therefore, the present invention proposes a method for optimizing the configuration of renewable energy in a virtual power plant, which can solve the problem of low accuracy in optimizing the configuration of renewable energy in a virtual power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a method for optimizing renewable energy configuration in a virtual power plant provided in one embodiment of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] The embodiment of the present application provides a method for optimizing the configuration of renewable energy in a virtual power plant. The execution subject of the method for optimizing the configuration of renewable energy in a virtual power plant includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for optimizing the configuration of renewable energy in a virtual power plant can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 FIG. 1 is a flow chart of a method for optimizing the configuration of renewable energy in a virtual power plant according to an embodiment of the present invention. In this embodiment, the method for optimizing the configuration of renewable energy in a virtual power plant includes: S1. Collect multi-time scale resource data of renewable energy in the area covered by the virtual power plant, and generate a multi-time initial configuration plan of renewable energy in the virtual power plant based on the multi-time scale resource data.

[0021] In an embodiment of the present invention, the multi-time-scale resource data refers to various data sets covering different time dimensions about renewable energy in the coverage area of ​​the virtual power plant, including directly related data of renewable energy, such as solar radiation, wind speed, wind direction, etc., as well as other environmental data that affect renewable energy generation and derivative data related to energy production and consumption.

[0022] In the embodiment of the present invention, the collecting of multi-time scale resource data of renewable energy in the area covered by the virtual power plant includes: Obtain data time scale for the area covered by the virtual power plant; Determining a data collection interval for renewable energy sources according to the data time scale; Collect resource data corresponding to the data time scale through the data collection interval; The resource data corresponding to the data time scales are collected to obtain multi-time scale resource data of renewable energy.

[0023] In detail, the time scale is divided into long-term, medium-term and short-term. The long-term time scale is based on years and quarters, which are used to plan the construction and expansion of power generation equipment and the formulation of long-term energy strategies; the medium-term time scale is based on months and weeks, which are used to formulate phased power generation plans, equipment maintenance arrangements, etc.; the short-term time scale is based on days, hours and even minutes, which are used to monitor and dispatch energy production and distribution in real time to cope with rapid changes in load and intermittent fluctuations in renewable energy. After clarifying the data time scale, the corresponding data collection interval should be determined according to each time scale. For example, for the long-term time scale in years, the data collection interval may be annual data for the past 10 years or even longer; for the medium-term time scale, if it is based on months, the collection interval may be data for the past 12 months; for the short-term time scale, in hours, it may be hourly data in recent days, so as to ensure that the collected data is consistent and representative in time, so as to analyze the characteristics and laws of renewable energy at different time scales.

[0024] Specifically, according to the determined data collection interval, the corresponding resource data is collected. For renewable energy, solar energy and wind energy data are collected by using solar irradiation sensors installed in and around the coverage area of ​​the virtual power plant to obtain data such as solar irradiation intensity and sunshine duration at different time scales. For wind energy resource data, wind speed, wind direction, wind power density and other data are collected through wind monitoring equipment. The production and consumption data of renewable energy are obtained from the pre-stored storage area through computer statements with data capture functions (such as Java statements, Python statements, etc.), and then the resource data of corresponding time scales collected in different data collection intervals are aggregated, and the annual and quarterly data at the long-term time scale, the monthly and weekly data at the medium-term time scale, and the daily and hourly data at the short-term time scale are aggregated together to obtain a renewable energy multi-time scale resource data set.

[0025] Furthermore, the optimal configuration of renewable energy can improve energy utilization efficiency and formulate flexible optimization strategies. Therefore, it is necessary to combine resource data at multiple time scales to generate an initial configuration plan so that virtual power plants can better utilize renewable energy resources.

[0026] In an embodiment of the present invention, the multi-time initial configuration plan refers to a complete plan determined by comprehensively considering the renewable energy configuration needs of virtual power plants under different time scales (long-term, medium-term, and short-term), covering multiple levels from long-term energy infrastructure construction planning to medium-term phased operation plans, and then to short-term real-time scheduling strategies.

[0027] In an embodiment of the present invention, the multi-time initial configuration scheme of renewable energy of a virtual power plant is generated according to the multi-time scale resource data, including: Determining a long-term configuration requirement of a virtual power plant according to the long-term resource data in the multi-time scale resource data, and generating a long-term initial configuration plan according to the long-term configuration requirement; Determining a mid-term configuration requirement of a virtual power plant according to the mid-term resource data in the multi-timescale resource data, and generating a mid-term initial configuration plan according to the mid-term configuration requirement; Determine the short-term configuration requirements of the virtual power plant according to the short-term resource data in the multi-time scale resource data, and generate a short-term initial configuration plan according to the short-term configuration requirements; The long-term initial configuration plan, the medium-term initial configuration plan and the short-term initial configuration plan are integrated into a multi-time initial configuration plan for renewable energy.

[0028] In detail, long-term resource data is based on annual and quarterly time scales, and contains information such as multi-year average solar radiation, annual average wind speed, and long-term power load growth trends. The energy supply and demand status of the virtual power plant over a longer period of time is determined based on long-term resource data. If the long-term solar radiation in a certain area is stable and high, then in the long run, there is a greater potential for the development of photovoltaic power generation, which means that it is necessary to plan and build larger-scale photovoltaic power stations, and then generate corresponding long-term initial configuration plans based on the determined long-term configuration needs, such as how many new photovoltaic power stations and wind farms are planned to be built in the next 5-10 years, as well as their specific locations and installed capacities; the layout and scale of energy storage facilities, such as the planned construction of battery energy storage power stations or pumped storage power stations of what capacity; the connection and interaction methods with the external power grid will also be considered to ensure a stable supply and efficient transmission of energy in the long term; medium-term resource data is based on monthly and weekly time scales, which can reflect the renewable energy resources and power load The changing patterns at the seasonal and monthly levels, for example, in some areas, the air-conditioning load is large in summer, and the peak of electricity demand is obvious, while solar energy resources are relatively abundant at this time; in winter, wind energy resources may be better, but the heating load will increase electricity demand. By analyzing the medium-term resource data, it can be determined how the virtual power plant needs to adjust the operation plan of the power generation equipment, the charging and discharging strategy of the energy storage system, and the power purchase and sales arrangements with the power grid within a few months to a year to meet the energy needs of different seasons and months. The medium-term initial configuration plan is generated based on the medium-term configuration requirements. The plan includes the maintenance plan of the power generation equipment in different seasons and months to ensure the stable operation of the equipment during the peak electricity consumption period; the charging and discharging schedule of the energy storage system is adjusted according to seasonal changes. For example, in the summer when solar energy is abundant, the charging capacity of the energy storage system is increased to prepare for the winter when energy supply is insufficient; and a medium-term electricity market trading strategy is formulated to reasonably arrange the timing of selling electricity to the power grid and purchasing electricity from the power grid according to the electricity price fluctuations in different months.

[0029] Specifically, short-term resource data uses days and hours as the time scale, and can reflect the power generation of renewable energy and the immediate changes in power load in real time. For example, through real-time monitoring of solar radiation intensity and wind speed data, the photovoltaic power generation and wind power generation at different times of the day can be predicted; at the same time, according to the real-time power load monitoring data, the current electricity demand can be understood, and by analyzing short-term data, it can be determined how the virtual power plant needs to accurately control the output of power generation equipment and the charging and discharging power of the energy storage system in the next few days or even hours to achieve real-time balance of electricity, and then generate a short-term initial configuration plan based on short-term configuration requirements. The plan will specify in detail the operating parameters of the power generation equipment each hour or day, such as the inverter output power adjustment of the photovoltaic power station and the angle adjustment of the wind turbine blades of the wind farm; the energy storage system Real-time charge and discharge control, according to the real-time situation of power generation and load, decide whether to charge or discharge and the power of charging and discharging; according to the real-time electricity price and power supply and demand, decide whether to purchase electricity from the power grid or sell electricity to the power grid, so as to aggregate the generated long-term, medium-term and short-term initial configuration plans, and obtain the multi-time initial configuration plan of renewable energy to ensure that the plans at each time scale are coordinated and complementary. For example, the short-term configuration plan must be implemented within the framework of long-term and medium-term planning, and cannot conflict with the long-term power generation equipment construction plan and the medium-term equipment maintenance plan; the medium-term configuration plan must provide guidance for short-term real-time scheduling, and at the same time must comply with the long-term energy development strategy; the long-term configuration plan must take into account the changes and adjustments that may occur in the medium-term and short-term operation, and have a certain degree of flexibility and adaptability.

[0030] Furthermore, in order to ensure the coordination of the long-term, medium-term and short-term operation strategies of the virtual power plant, it is necessary to constrain the obtained multi-time scale resource data. Therefore, it is necessary to determine the constraints so that the multi-time scale resource data is within a safe and reasonable range.

[0031] S2. Generate constraint conditions for the multi-time-scale resource data according to the constraint attributes of the virtual power plant, and construct a multi-time-scale optimization model according to the constraint conditions and the multi-time-scale resource data.

[0032] In the embodiment of the present invention, the constraint condition is a mathematical description of various restrictions and requirements during the operation of the virtual power plant, reflecting the relationship and operation rules between the internal components of the virtual power plant (power generation equipment, energy storage system, etc.) and the external power grid, limiting the feasible operation range of the virtual power plant at different time scales, and ensuring the effective utilization and optimal configuration of energy under the premise of safety and stability.

[0033] In the embodiment of the present invention, the generation of the constraint conditions of the multi-timescale resource data according to the constraint attributes of the virtual power plant includes: Extracting power balance constraint attributes, power generation equipment operation constraint attributes, energy storage constraint attributes and power grid interaction constraint attributes from the constraint attributes; A power balance constraint condition for the multi-time scale resource data is generated according to the power balance constraint attribute, wherein the power balance constraint condition is: ; in, For the The power generation of the photovoltaic power station at any moment, For the The power generation of the wind farm at the moment, For the The discharge power of the energy storage at any time, For the The power purchased from the grid at all times, For the The load power demand at the moment, For the The charging power of energy storage at all times, is the total number of time steps; The power constraints of the power generation equipment of the multi-time scale resource data are generated according to the power generation equipment operation constraint attributes, wherein the power generation equipment constraints are: ; in, For the The power generation of the photovoltaic power station at any moment, For the The power generation of the wind farm at the moment, is the maximum power generation capacity of the photovoltaic power station, is the maximum power generation of the wind farm; Generate energy storage constraint conditions for the multi-timescale resource data according to the energy storage constraint attributes, and generate power grid interaction constraint conditions for the multi-timescale resource data according to the power grid interaction constraint attributes; The power balance constraint condition, the power generation equipment constraint condition, the energy storage constraint condition and the power grid interaction constraint condition are determined as constraint conditions of multi-time scale resource data.

[0034] In detail, there are many constraints in the operation of virtual power plants. By extracting power balance constraint attributes, power generation equipment operation constraint attributes, energy storage constraint attributes and grid interaction constraint attributes, these attributes are summarized from the physical characteristics of the virtual power plant, operation requirements and interaction rules with the external power grid. According to the power balance constraint attributes, the power generation power of the photovoltaic power station, the power generation power of the wind farm, the discharge power of the energy storage system, the power purchased by the power grid, the load power demand, and the charging power of the energy storage system, the power balance constraint condition can be determined. The power balance constraint condition refers to the sum of all power generation sources in the virtual power plant, which must be equal to the sum of the load power demand and the charging power of the energy storage system at that moment. The power balance constraint condition is the basic condition for ensuring the stable operation of the power system, ensuring that the supply and demand of electricity are matched at any time to avoid excess or insufficient power. In the long-term planning, May represent months or years; in mid-term optimization, It can be days; for short-term scheduling, It may be hours or even shorter time intervals. , it means selling electricity to the power grid. The constraints of the power generation equipment can be determined according to the maximum power generation power of the photovoltaic power station, the maximum power generation power of the wind farm, the power generation power of the photovoltaic power station, and the power generation power of the wind farm in the power generation equipment operation constraint attributes. The power generation power of the photovoltaic power station is limited by its own maximum power generation power and cannot be a negative value. Similarly, the power generation power of the wind farm is also between 0 and its maximum power generation power, ensuring that the power generation equipment operates within a safe and reasonable power range to avoid equipment overload and damage.

[0035] Specifically, energy storage constraints for multi-time-scale resources are generated based on energy storage constraint attributes. The energy storage constraints will limit the charging and discharging power of the energy storage system and the capacity of the energy storage system. The energy storage constraints ensure that the energy storage system can not only effectively store and release electrical energy, but also ensure its safe and stable operation and extend its service life. The energy storage constraint attributes include the charging power of the energy storage system, the discharging power of the energy storage system, the maximum charging power of the energy storage, and the maximum discharging power of the energy storage.

[0036] In the embodiment of the present invention, the step of generating the energy storage constraint condition of the multi-time scale resource according to the energy storage constraint attribute includes: The charge and discharge power constraint condition is generated according to the energy storage constraint attribute, wherein the charge and discharge power constraint condition is: ; in, For the The charging power of energy storage at all times, For the The discharge power of the energy storage at any time, is the maximum charging power of the energy storage, is the maximum discharge power of energy storage; The state of charge update equation is determined according to the charging power and discharging power of the energy storage, where the state of charge update equation is: ; in, For the The state of charge at the moment, For the The state of charge at the moment, For the The charging power of energy storage at all times, For the The discharge power of the energy storage system at any moment, is the time step, is the charging efficiency of energy storage, is the discharge efficiency of energy storage; Determining state of charge constraints using the state of charge update equation; The charging and discharging power constraint condition and the state of charge constraint condition are determined as energy storage constraint conditions of multi-time scale resource data.

[0037] In detail, the charging and discharging power constraints are generated according to the energy storage constraint attributes, indicating that at every moment of the virtual power plant operation, the charging power of the energy storage system must be between 0 and the maximum charging power, and the discharging power must also be between 0 and the maximum discharging power, so as to ensure the safe and stable operation of the energy storage system, prevent damage to the energy storage equipment due to overcharging or excessive discharge power, and also help maintain the overall operational stability of the virtual power plant; and the state of charge is an important indicator for measuring the remaining power of the energy storage system. The state of charge update equation describes how the state of charge of the energy storage system changes with the charging and discharging process in each time step. When charging, the power of the energy storage system will increase, and when discharging, the power will decrease. The state of charge at the current moment can be accurately calculated based on the state of charge at the previous moment and the charging and discharging power at the current moment, providing a basis for the subsequent analysis of the operating status of the energy storage system. Based on the state of charge update equation, combined with the actual operating requirements of the energy storage system, the state of charge constraint can be determined, and the state of charge constraint is: ;in and They are the minimum and maximum values ​​of the energy storage system’s state of charge, respectively, ensuring that the energy storage system operates within a safe and effective range of state of charge, guaranteeing the stable operation of the virtual power plant and the reliability of energy allocation.

[0038] Specifically, the grid interaction constraint conditions generated according to the grid interaction constraint attributes are mainly used to limit the power interaction between the virtual power plant and the grid. The grid interaction power constraint has certain restrictions on the power purchased or sold from the grid, such as ,in and They are the minimum and maximum values ​​of the power for interaction with the power grid, and the upper and lower limits of the power purchased from the power grid, respectively, to ensure that the interaction between the virtual power plant and the power grid is within the range allowed by the safe operation of the power grid and to avoid adverse effects on the power grid. The generated power balance constraints, power generation equipment constraints, energy storage constraints and power grid interaction constraints are then integrated together to obtain the constraints for multi-time scale resource data. The constraints work together to restrict and regulate the operation of the virtual power plant at each time scale from different angles, providing basic conditions for the optimized operation and resource allocation of the virtual power plant.

[0039] Furthermore, as the energy environment continues to change, such as advances in renewable energy technology, changes in load characteristics, and adjustments to the grid structure, the optimization scheme can be dynamically adjusted on different time scales based on new resource data and constraints to adapt to these changes and maintain the efficient operation of the virtual power plant.

[0040] In the embodiment of the present invention, the multi-time scale optimization model is a mathematical model of the operation of the virtual power plant at different time scales, based on multi-time scale resource data, which contains the characteristics of renewable energy at different time granularities (such as long-term, medium-term, and short-term), load demand, and other related information. At the same time, combined with various constraints in the operation of the virtual power plant (such as power balance constraints, power generation equipment operation constraints, energy storage constraints, and grid interaction constraints, etc.), by adjusting the operating parameters of each energy device at different time points (such as power generation power, charging and discharging power, etc.), specific optimization goals (such as cost minimization, profit maximization, etc.) are achieved.

[0041] In an embodiment of the present invention, the step of constructing a multi-time-scale optimization model according to the constraint conditions and the multi-time-scale resource data includes: A multi-time scale optimization model is constructed according to the multi-time scale resource data under the constraint conditions, wherein the multi-time scale optimization model is: ; in, is the minimum function, is the maximum value function, is the unit power generation cost of the photovoltaic power station, For the The power generation of the photovoltaic power station at any moment, is the unit power generation cost of the wind farm, For the The power generation of the wind farm at the moment, For the The unit price of electricity purchased from the grid at any given moment, For the The power purchased from the grid at all times, For the The unit price of electricity sold to the grid at any given moment, The unit cost of charging the energy storage, For the The charging power of energy storage at all times, is the unit cost of energy storage discharge, For the The discharge power of the energy storage system at any moment, is the total number of time steps.

[0042] In detail, Indicates The power generation cost of the photovoltaic power station at this moment, Indicates The power generation cost of the wind farm at the moment, Indicates The cost of purchasing electricity from the grid at any time (when The cost of purchasing electricity is incurred only when Indicates The revenue from selling electricity to the grid at any time (when There is income from electricity sales only when Indicates The charging cost of the energy storage system at any time, Indicates The discharge cost of the energy storage system at each moment takes into account the total cost of the virtual power plant over the entire time range, ensuring comprehensive optimization of costs at multiple time scales so that it can better cope with the intermittent and volatility of renewable energy and the dynamic changes in load demand, and rationally plan and dispatch energy at different time scales to improve the overall operating efficiency and economic benefits of the virtual power plant.

[0043] Furthermore, the multi-time scale optimization model weighs the costs and benefits of various energy activities of the virtual power plant at different time steps through the objective function, and seeks the optimal operation strategy for minimizing the overall cost under the premise of meeting various constraints. Therefore, the multi-time scale optimization model can be used to analyze the minimized cost of the virtual power plant to generate the optimal configuration of renewable resources.

[0044] S3. Analyze the minimized operating cost of the virtual power plant using the multi-time scale optimization model, and perform rolling time domain optimization on the multi-time initial configuration plan based on the minimized operating cost.

[0045] In an embodiment of the present invention, the minimized operating cost refers to the lowest cost that can be achieved while satisfying all relevant constraints, by comprehensively considering various operating links such as renewable energy power generation, charging and discharging of energy storage systems, interaction with the power grid, as well as various factors such as the characteristics of power generation equipment, load demand, and power grid conditions during the operation of the virtual power plant.

[0046] In an embodiment of the present invention, the method of analyzing the minimized operating cost of a virtual power plant using the multi-time scale optimization model includes: Obtain real-time resource data of renewable energy for virtual power plants; Calculating the optimization value corresponding to the real-time resource data using the multi-time scale optimization model; The minimum optimization value is selected as the minimized operating cost of the virtual power plant.

[0047] In detail, the real-time resource data includes various key information of renewable energy in the area covered by the virtual power plant at the current moment, such as real-time solar radiation intensity, wind speed, wind direction, etc. These data directly affect the power generation of photovoltaic power stations and wind farms. At the same time, it also includes real-time load data, that is, the power demand situation in the area served by the virtual power plant at the current moment, the real-time charge status of the energy storage system, the real-time electricity price of the power grid and other data, and the acquired real-time resource data is substituted into the multi-time scale optimization model. That is, the multi-time scale optimization model will allocate different power generation schemes (such as the power generation power of photovoltaic power stations and wind farms, the charging and discharging power of the energy storage system, and the interactive power with the power grid, etc.) on the premise of meeting all constraints, and calculate the cost value corresponding to each scheme according to the objective function. The multi-time scale optimization model can simulate the cost situation corresponding to different operation strategies of the virtual power plant under the current real-time resource data conditions.

[0048] Specifically, after the optimization value is calculated using the multi-time scale optimization model, the optimization value represents the operating cost of the virtual power plant under different operating strategies. The smallest optimization value is selected from the calculation results, and the minimum value is identified as the minimum operating cost that the virtual power plant can achieve under the current real-time resource data. That is, under the premise of meeting all constraints, operating the virtual power plant according to the operating strategy corresponding to the minimum cost can minimize the operating cost, thereby enabling the virtual power plant to find the most economical operating mode and improve economic benefits in a complex and changeable operating environment.

[0049] Furthermore, renewable energy (such as solar energy and wind energy) has significant volatility and uncertainty. Based on real-time renewable energy resource data (such as real-time light intensity, wind speed, etc.), combined with the goal of minimizing operating costs, the multi-time initial configuration plan is continuously adjusted. Through this dynamic adjustment, the virtual power plant can better adapt to the random changes of renewable energy, ensure the stability of power supply, and reduce the adverse effects caused by energy fluctuations.

[0050] In an embodiment of the present invention, rolling time domain optimization is a dynamic optimization strategy. By setting a limited time range (i.e., rolling time domain), at each time point, based on the current real-time renewable energy data, load data, etc. and the system's operating goals (such as minimizing operating costs), the operating plan for a period of time in the future (i.e., within the rolling time domain) is optimized.

[0051] In an embodiment of the present invention, the step of performing rolling time domain optimization on the multi-time initial configuration scheme according to the minimized operating cost includes: Configuring a rolling time domain of the multi-time initial configuration scheme; Extracting target resource data of renewable energy corresponding to the minimized operating cost; Optimizing the short-term initial configuration scheme in the multi-time initial configuration scheme according to the target resource data; Optimizing the mid-term initial configuration scheme in the multi-time initial configuration scheme by using the optimized short-term initial configuration scheme; Optimizing the long-term initial configuration scheme in the multi-time initial configuration scheme by using the optimized medium-term initial configuration scheme; The rolling direction of the optimized long-term initial configuration scheme is determined according to the rolling time domain, and the multi-time initial configuration scheme is optimized according to the rolling direction.

[0052] In detail, the rolling time domain defines the future time range considered each time in the optimization process, and determines the time span and frequency of the optimization. For example, for short-term power dispatching, the rolling time domain may be set to the next 24 hours, that is, each optimization is based on the situation in the next 24 hours. After calculating the minimized operating cost through the multi-time scale optimization model, the data of renewable energy corresponding to the minimized operating cost can be extracted, reflecting the power generation status, resource conditions and other information of renewable energy when the minimum operating cost is reached, that is, the power generation power of the photovoltaic power station, the unit power generation cost of the wind farm, the power generation power of the wind farm, the unit price of electricity purchased from the power grid, the power of electricity purchased from the power grid, the unit price of electricity sold to the power grid, the unit cost of energy storage charging, the charging power of energy storage, the unit cost of energy storage discharging, and the discharge power of the energy storage system. Then, the short-term initial configuration plan is adjusted according to the extracted target resource data.

[0053] For example, the target data shows that the current lighting conditions are good, and the actual power generation of the photovoltaic power station can be increased. Under the premise of not exceeding its maximum power generation, its power generation setting in the next few hours can be increased; if the power generation of the wind farm is stable and the unit power generation cost is low, the power generation task of the wind farm can be increased in the short-term plan; on the contrary, if the power generation fluctuates greatly and the cost is high, its power generation setting can be appropriately reduced; when it is found that the power purchase price of the power grid is at a low point in a certain period of time, and the power generation and energy storage discharge of the virtual power plant itself are not enough to meet the load, the power purchased from the power grid during this period is appropriately increased to ensure power supply and reduce costs; when real-time monitoring shows that the power sales price of the power grid has increased, and the power generation of the virtual power plant is greater than the sum of the load demand and the energy storage charging demand, the short-term configuration plan is adjusted to sell the excess power to the power grid at a high price; when the power generation of the photovoltaic power station is high and the energy storage charging cost is low, the charging power of the energy storage is appropriately increased to store the excess solar power; during peak hours of electricity consumption, when the energy storage discharge cost is lower than the cost of purchasing electricity from the power grid, the discharge power of the energy storage system is increased, the purchase of electricity from the power grid is reduced, and the operating cost is reduced.

[0054] Specifically, if it is found in multiple short-term optimizations that the photovoltaic power station generates electricity stably and at low cost during a specific time period, this time period can be set as the key power generation period of the photovoltaic power station in the medium-term initial configuration plan to ensure its efficient operation during this period; if it is found in the short-term optimization that the power purchase price of the power grid is low during a certain type of power consumption period (such as daytime on weekdays), a more flexible power purchase strategy can be formulated for this period in the medium-term plan, such as signing a long-term low-price power purchase contract or increasing the power purchase budget for this period; if the short-term optimization shows that the cost of energy storage charging is low every night and there is a surplus of renewable energy power generation, it can be planned in the medium-term plan to increase the charging of the energy storage system during this period of each week. If the mid-term operation shows that a certain area has abundant wind energy resources and the long-term operation cost-effectiveness of the wind farm is good, the long-term plan can consider increasing the construction scale of the wind farm and investing in more wind turbines. If the mid-term optimization shows that establishing a long-term cooperative relationship with the power grid company and signing a preferential power purchase contract for a specific period of time can significantly reduce costs, the long-term plan can negotiate with the power grid company for a longer-term and more preferential power purchase contract to ensure a stable and low-cost power supply. If the mid-term operation finds that the energy storage system plays an important role in balancing the supply and demand of electricity and reducing costs, but the capacity gradually cannot meet the demand, the long-term plan can plan to increase the capacity of the energy storage system.

[0055] Furthermore, the rolling direction is long-term initial configuration plan-medium-term initial configuration plan-short-term initial configuration plan-long-term initial configuration plan, and then the multi-time initial configuration plans are optimized in sequence according to the rolling direction to obtain the optimal renewable energy configuration plan.

[0056] S4. Calculate the sensitivity of the optimized multi-time initial configuration scheme according to the constraint conditions, and determine the optimization factor of the optimized multi-time initial configuration scheme according to the sensitivity.

[0057] In the embodiment of the present invention, the sensitivity is an indicator for measuring the sensitivity of the optimized multi-time initial configuration scheme to the constraint conditions, and reflects the degree of fit between the constraint data in the scheme and the constraint conditions under the current optimized configuration.

[0058] In the embodiment of the present invention, the step of calculating the sensitivity of the optimized multi-time initial configuration scheme according to the constraint condition includes: Extracting constraint data from the optimized multi-time initial configuration scheme; Determine the constraint factor corresponding to the constraint data according to the constraint condition: ; in, For the The constraint factor corresponding to the constraint data is For the Constraint data, No. Constraint conditions corresponding to constraint data; The sensitivity of the optimized multi-time initial configuration scheme is calculated according to the constraint factors: ; in, The optimized multi-time initial configuration scheme The sensitivity of the scheme corresponding to the time domain, The optimized multi-time initial configuration scheme The scheme corresponding to the time domain The constraint factor corresponding to the constraint data is The optimized multi-time initial configuration scheme The total number of constraints for the solution corresponding to the time domain.

[0059] In detail, the optimized multi-time initial configuration scheme includes the energy configuration strategy and related operating parameters of the virtual power plant at different time scales (such as long-term, medium-term, and short-term). These strategies and parameters need to meet a series of constraints, such as power balance constraints, power generation equipment operation constraints, energy storage constraints, and grid interaction constraints. For each extracted constraint data By the corresponding constraints Compare and determine its constraint factor. For example, for the operating constraint of power generation equipment, if the value of the photovoltaic power station power generation at a certain moment in the optimized configuration plan meets the condition range of the operating constraint of the power generation equipment, that is, the constraint factor corresponding to the constraint data is 1. Otherwise, if it exceeds this range, the constraint factor is 0.

[0060] Specifically, when calculating the sensitivity, for each time domain (such as short-term, medium-term, and long-term are considered as different time domains) in the optimized multi-time initial configuration scheme, the constraint factors corresponding to all constraint data in each scheme are first counted. For example, in the short-term configuration scheme, assuming that Constraints, for each constraint a corresponding constraint factor is determined , these 10 Add and divide by 10 to get the sensitivity of the short-term configuration solution. . Sensitivity The value of is between 0 and 1. The closer the value is to 1, the higher the degree of satisfaction of the solution corresponding to the time domain for the constraint conditions, that is, the solution is relatively insensitive to changes in the constraint conditions; the closer the value is to 0, the lower the degree of satisfaction of the solution for the constraint conditions, and the more sensitive it is to changes in the constraint conditions.

[0061] Furthermore, if the sensitivity of a constraint is low, it means that the configuration parameters related to it need to be adjusted to a greater extent to effectively improve the solution; conversely, the parameter adjustment range corresponding to the constraint with high sensitivity can be relatively small, thereby accurately guiding the configuration solution to develop in a better direction.

[0062] In the embodiment of the present invention, the optimization factor is a quantitative parameter used to guide the adjustment of the optimized multi-time initial configuration scheme, reflecting the direction and degree of adjustment of the configuration scheme.

[0063] In the embodiment of the present invention, the optimization factor of the optimized multi-time initial configuration scheme is determined by the sensitivity, including: When the sensitivity is equal to a preset first sensitivity threshold and greater than a preset second sensitivity threshold, determining the optimization factor of the optimized multi-time initial configuration scheme as the first factor; When the sensitivity is less than a preset second sensitivity threshold and greater than a preset third sensitivity threshold, the optimization factor of the optimized multi-time initial configuration scheme is determined as the second factor.

[0064] In detail, the first sensitivity threshold is 1, the second sensitivity threshold is half, and the third sensitivity threshold is 0. That is, when the sensitivity is greater than the first sensitivity threshold and greater than the second sensitivity threshold, the optimization factor of the optimized multi-time initial configuration scheme is determined as the first factor, and the first factor is 1, indicating that the multi-time initial configuration scheme at this time does not need to be optimized anymore.

[0065] Specifically, when the sensitivity is less than the second sensitivity threshold and greater than the third sensitivity threshold, the optimization factor of the optimized multi-time initial configuration scheme is determined as the second factor, and the second factor is a value of 0, indicating that the multi-time initial configuration scheme at this time needs to be optimized again so that the configuration scheme can develop in a better direction under different sensitivity levels, thereby continuously improving the operating performance and economic benefits of the virtual power plant.

[0066] Furthermore, the optimization factor serves as a guiding parameter for each step, making the entire optimization process logical and coherent. Through orderly optimization steps, the configuration effect of renewable energy can be gradually improved, avoiding chaotic and disorderly adjustments.

[0067] S5. Generate a configuration path for optimizing the configuration of renewable energy according to the optimization factors, and determine the optimal configuration plan for the renewable energy of the virtual power plant according to the configuration path.

[0068] In the embodiment of the present invention, the configuration path refers to a series of orderly operation steps and decision-making processes taken from the current configuration state to achieve the optimal or more optimal configuration state during the process of optimizing the configuration of renewable energy.

[0069] In an embodiment of the present invention, generating a configuration path for optimizing the configuration of renewable energy sources according to the optimization factor includes: Determining the configuration path of the renewable energy optimization configuration as an open-loop path according to a first factor in the optimization factors; Determining the configuration path of the renewable energy optimization configuration as a closed-loop path according to the second factor in the optimization factor; A configuration decision tree for optimizing the configuration of renewable energy is generated according to the open-loop path and the closed-loop path, and a configuration path for optimizing the configuration of renewable energy is determined through the configuration decision tree.

[0070] In detail, when the optimization factor is the first factor, it means that there is no need to optimize the configuration of renewable resources, that is, the configuration path of the renewable optimization configuration is determined as an open-loop path, and when the optimization factor is the second factor, it means that the multi-time configuration scheme corresponding to the renewable resources needs to be optimized again, then the above optimization steps are repeated, that is, the configuration path is determined as a closed-loop path, and then a configuration decision tree for the optimal configuration of renewable resources is generated according to the open-loop path and the closed-loop path, that is, when it is detected that the sensitivity at a certain moment meets the conditions of the first factor, the configuration optimization is performed along the steps set by the open-loop path branch; and when the sensitivity changes and meets the conditions of the second factor, it switches to the closed-loop path branch and optimizes the configuration according to its dynamic adjustment method. In this way, the configuration decision tree provides a flexible and comprehensive framework for the optimal configuration of renewable energy, which can select the most appropriate configuration path according to different situations.

[0071] Specifically, the optimal configuration scheme of renewable energy of the virtual power plant is determined according to the configuration path, that is, when the configuration path is an open-loop path, the optimized multi-time configuration scheme of renewable energy is determined as the optimal configuration scheme, and when the configuration path is a closed-loop path, the optimized multi-time configuration scheme of renewable energy is optimized again according to the optimization steps until the configuration path of the optimized configuration scheme is an open-loop path, and the optimal configuration scheme of renewable energy is obtained.

[0072] The present invention can comprehensively grasp the distribution and change law of renewable energy in the area covered by the virtual power plant by collecting renewable energy resource data at multiple time scales; generate constraint conditions according to the constraint attributes of the virtual power plant, and ensure the feasibility and safety of the virtual power plant in the actual operation process; construct a multi-time scale optimization model, and can incorporate resource data and constraint conditions at different time scales into a unified model framework; analyze the minimized operating cost of the virtual power plant through the multi-time scale optimization model, and find the optimal operating strategy under various constraint conditions; determine the optimization factor of the optimized multi-time initial configuration scheme through sensitivity, and quantify the adjustment range of each factor; generate the configuration path of the optimal configuration of renewable energy according to the optimization factor, so that the optimization process is operable and controllable. Therefore, the present invention proposes a method for optimizing the configuration of renewable energy in a virtual power plant, which can solve the problem of low accuracy in optimizing the configuration of renewable energy in a virtual power plant.

[0073] In several embodiments provided by the present invention, it should be understood that the disclosed method can be implemented in other ways.

[0074] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0075] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method and technology of using digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for optimizing the configuration of renewable energy in a virtual power plant, characterized in that: The method comprises: Collect multi-time scale resource data of renewable energy in the area covered by the virtual power plant, and generate a multi-time initial configuration plan of renewable energy of the virtual power plant according to the multi-time scale resource data; Generating constraint conditions of the multi-timescale resource data according to constraint attributes of the virtual power plant, and constructing a multi-timescale optimization model according to the constraint conditions and the multi-timescale resource data, including: A multi-time scale optimization model is constructed according to the multi-time scale resource data under the constraint conditions, wherein the multi-time scale optimization model is: ； in, is the minimum function, is the maximum value function, is the unit power generation cost of the photovoltaic power station, For the The power generation of the photovoltaic power station at any moment, is the unit power generation cost of the wind farm, For the The power generation of the wind farm at the moment, For the The unit price of electricity purchased from the grid at any given moment, For the The power purchased from the grid at all times, For the The unit price of electricity sold to the grid at any given moment, The unit cost of charging the energy storage, For the The charging power of energy storage at all times, is the unit cost of energy storage discharge, For the The discharge power of the energy storage system at any moment, is the total number of time steps; Analyzing the minimized operating cost of the virtual power plant using the multi-time scale optimization model, and performing rolling time domain optimization on the multi-time initial configuration scheme according to the minimized operating cost; Calculate the sensitivity of the optimized multi-time initial configuration scheme according to the constraint conditions, and determine the optimization factor of the optimized multi-time initial configuration scheme according to the sensitivity; A configuration path for optimizing the configuration of renewable energy is generated according to the optimization factors, and an optimal configuration scheme for the renewable energy of the virtual power plant is determined according to the configuration path.

2. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The multi-time scale resource data of renewable energy in the area covered by the virtual power plant is collected, including: Obtain data time scale for the area covered by the virtual power plant; Determining a data collection interval for renewable energy sources according to the data time scale; Collect resource data corresponding to the data time scale through the data collection interval; The resource data corresponding to the data time scales are collected to obtain multi-time scale resource data of renewable energy.

3. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The method of generating a multi-time initial configuration scheme of renewable energy sources of a virtual power plant according to the multi-time scale resource data comprises: Determining a long-term configuration requirement of a virtual power plant according to the long-term resource data in the multi-time scale resource data, and generating a long-term initial configuration plan according to the long-term configuration requirement; Determining a mid-term configuration requirement of a virtual power plant according to the mid-term resource data in the multi-timescale resource data, and generating a mid-term initial configuration plan according to the mid-term configuration requirement; Determine the short-term configuration requirements of the virtual power plant according to the short-term resource data in the multi-time scale resource data, and generate a short-term initial configuration plan according to the short-term configuration requirements; The long-term initial configuration plan, the medium-term initial configuration plan and the short-term initial configuration plan are integrated into a multi-time initial configuration plan for renewable energy.

4. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The generating of the constraint conditions of the multi-timescale resource data according to the constraint attributes of the virtual power plant includes: Extracting power balance constraint attributes, power generation equipment operation constraint attributes, energy storage constraint attributes and power grid interaction constraint attributes from the constraint attributes; A power balance constraint condition for the multi-time scale resource data is generated according to the power balance constraint attribute, wherein the power balance constraint condition is: ； in, For the The power generation of the photovoltaic power station at any moment, For the The power generation of the wind farm at the moment, For the The discharge power of the energy storage at any time, For the The power purchased from the grid at all times, For the The load power demand at the moment, For the The charging power of energy storage at all times, is the total number of time steps; The power constraints of the power generation equipment of the multi-time scale resource data are generated according to the power generation equipment operation constraint attributes, wherein the power generation equipment constraints are: ； in, For the The power generation of the photovoltaic power station at any moment, For the The power generation of the wind farm at the moment, is the maximum power generation capacity of the photovoltaic power station, is the maximum power generation of the wind farm; Generate energy storage constraint conditions for the multi-timescale resource data according to the energy storage constraint attributes, and generate power grid interaction constraint conditions for the multi-timescale resource data according to the power grid interaction constraint attributes; The power balance constraint condition, the power generation equipment constraint condition, the energy storage constraint condition and the power grid interaction constraint condition are determined as constraint conditions of multi-time scale resource data.

5. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 4, characterized in that: The generating the energy storage constraint condition of the multi-time scale resource according to the energy storage constraint attribute includes: The charge and discharge power constraint condition is generated according to the energy storage constraint attribute, wherein the charge and discharge power constraint condition is: ； in, For the The charging power of energy storage at all times, For the The discharge power of the energy storage at any time, is the maximum charging power of the energy storage, is the maximum discharge power of energy storage; The state of charge update equation is determined according to the charging power and discharging power of the energy storage, where the state of charge update equation is: ； in, For the The state of charge at the moment, For the The state of charge at the moment, For the The charging power of energy storage at all times, For the The discharge power of the energy storage system at any moment, is the time step, is the charging efficiency of energy storage, is the discharge efficiency of energy storage; Determining state of charge constraints using the state of charge update equation; The charging and discharging power constraint condition and the state of charge constraint condition are determined as energy storage constraint conditions of multi-time scale resource data.

6. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The method of analyzing the minimized operating cost of a virtual power plant by using the multi-time scale optimization model includes: Obtain real-time resource data of renewable energy for virtual power plants; Calculating the optimization value corresponding to the real-time resource data using the multi-time scale optimization model; The minimum optimization value is selected as the minimized operating cost of the virtual power plant.

7. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The step of performing rolling time domain optimization on the multi-time initial configuration scheme according to the minimized operating cost includes: Configuring a rolling time domain of the multi-time initial configuration scheme; Extracting target resource data of renewable energy corresponding to the minimized operating cost; Optimizing the short-term initial configuration scheme in the multi-time initial configuration scheme according to the target resource data; Optimizing the mid-term initial configuration scheme in the multi-time initial configuration scheme by using the optimized short-term initial configuration scheme; Optimizing the long-term initial configuration scheme in the multi-time initial configuration scheme by using the optimized medium-term initial configuration scheme; The rolling direction of the optimized long-term initial configuration scheme is determined according to the rolling time domain, and the multi-time initial configuration scheme is optimized according to the rolling direction.

8. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The step of calculating the sensitivity of the optimized multi-time initial configuration scheme according to the constraint conditions includes: Extracting constraint data from the optimized multi-time initial configuration scheme; Determine the constraint factor corresponding to the constraint data according to the constraint condition: ； in, For the The constraint factor corresponding to the constraint data is For the Constraint data, No. Constraint conditions corresponding to constraint data; The sensitivity of the optimized multi-time initial configuration scheme is calculated according to the constraint factors: ； in, The optimized multi-time initial configuration scheme The sensitivity of the scheme corresponding to the time domain, The optimized multi-time initial configuration scheme The scheme corresponding to the time domain The constraint factor corresponding to the constraint data is The optimized multi-time initial configuration scheme The total number of constraints for the solution corresponding to the time domain.

9. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: The step of determining the optimization factor of the optimized multi-time initial configuration scheme through the sensitivity includes: When the sensitivity is equal to a preset first sensitivity threshold and greater than a preset second sensitivity threshold, determining the optimization factor of the optimized multi-time initial configuration scheme as the first factor; When the sensitivity is less than a preset second sensitivity threshold and greater than a preset third sensitivity threshold, the optimization factor of the optimized multi-time initial configuration scheme is determined as the second factor.

10. The method for optimizing the configuration of renewable energy in a virtual power plant according to claim 1, characterized in that: Generating a configuration path for optimizing the configuration of renewable energy sources according to the optimization factors includes: Determining the configuration path of the renewable energy optimization configuration as an open-loop path according to a first factor in the optimization factors; Determining a configuration path of the renewable energy optimization configuration as a closed-loop path according to a second factor in the optimization factor; A configuration decision tree for optimizing the configuration of renewable energy is generated according to the open-loop path and the closed-loop path, and a configuration path for optimizing the configuration of renewable energy is determined through the configuration decision tree.

Images