Method and device for acquiring virtual power plant scheduling strategy and computer equipment

Abstract

The invention relates to a virtual power plant scheduling strategy obtaining method and device and computer equipment. The method comprises the following steps: acquiring energy parameters, historical operation data and energy conversion efficiency of each component of a target virtual power plant; constructing an operation model of each component according to the energy parameters of each component of the target virtual power plant; sampling to generate a plurality of operation modes of the target virtual power plant according to the historical operation data; determining a risk index and a resource consumption index of the virtual power plant in each operation mode according to the operation data of each operation mode; determining a target operation model of the target virtual power plant based on the operation model of each component, each operation mode, the corresponding risk index and resource consumption index, and the energy conversion efficiency; and determining a scheduling strategy of each component of the target virtual power plant according to the target operation model of the target virtual power plant. By adopting the method, the operation efficiency and stability of the virtual power plant in a complex environment can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power engineering, in particular to a method and device for obtaining a virtual power plant scheduling strategy, a computer device, a storage medium and a computer program product. BACKGROUND

[0002] With the development of energy internet technology, virtual power plant technology has gradually matured. It integrates distributed power generation, energy storage, load and other resources with the help of information technology to realize collaborative operation, and plays an important role in improving energy utilization and promoting new energy consumption. Traditional scheduling methods have effectively supported basic operation in the early development of virtual power plants. By formulating scheduling strategies through simple models and historical data, they can meet the basic power supply demand in conventional scenarios and ensure the stable operation of the power system. However, as the scale of virtual power plants expands and the number of components increases, traditional methods gradually expose their shortcomings. Relying solely on a single model and limited data, with simple constraint settings, they are difficult to cope with diversified operating scenarios, resulting in scheduling strategies that are not strongly adaptive in complex conditions. SUMMARY

[0003] Therefore, it is necessary to provide a method and device for obtaining a virtual power plant scheduling strategy, a computer device, a computer readable storage medium and a computer program product to solve the above technical problems.

[0004] In a first aspect, the present application provides a method for obtaining a virtual power plant scheduling strategy. The method comprises:

[0005] obtaining energy parameters and historical operating data of each component of a target virtual power plant, and energy conversion efficiency; wherein the components of the virtual power plant include at least one of the following: power generation equipment, energy storage equipment, transmission equipment, and load equipment;

[0006] constructing an operating model for each component according to the energy parameters of each component of the target virtual power plant; and sampling to generate a plurality of operating modes for the target virtual power plant according to the historical operating data;

[0007] determining a risk index and a resource consumption index of the virtual power plant in each operating mode according to the operating data of each operating mode;

[0008] determining a target operating model for the target virtual power plant based on the operating model of each component, each operating mode, and the corresponding risk index and resource consumption index, and the energy conversion efficiency;

[0009] determining a scheduling strategy for each component of the target virtual power plant according to the target operating model of the target virtual power plant.

[0010] In one of the embodiments, the sampling generates a plurality of operation modes of the target virtual power plant according to the historical operation data, including:

[0011] The Latin hypercube sampling strategy is used to process the historical operation data to obtain a plurality of initial operation modes of the target virtual power plant.

[0012] The differences between the initial operation modes are compared, and the initial operation modes satisfying the preset requirements are merged to obtain a plurality of operation modes of the target virtual power plant.

[0013] In one of the embodiments, the scheduling strategy of each component of the target virtual power plant is determined according to the target operation model of the target virtual power plant, including:

[0014] The upper and lower limit parameters of the operation power of the power generation equipment, the charging and discharging power and capacity parameters of the energy storage equipment, and the transmission capacity parameters of the transmission equipment are obtained.

[0015] The power generation equipment constraint condition is established according to the upper and lower limit parameters of the operation power of the power generation equipment; the energy storage equipment constraint condition is established according to the charging and discharging power and capacity parameters of the energy storage equipment; and the transmission equipment constraint condition is established according to the transmission capacity parameters of the transmission equipment.

[0016] The target operation model of the target virtual power plant is solved according to the power generation equipment constraint condition, the energy storage equipment constraint condition, and the transmission equipment constraint condition to obtain the scheduling strategy of each component of the target virtual power plant.

[0017] In one of the embodiments, the risk index and resource consumption index of the virtual power plant under each operation mode are determined according to the operation data of each operation mode, including:

[0018] The prediction data of each operation mode is obtained according to the historical operation data of each component of the target virtual power plant.

[0019] The risk index is determined based on the difference between the operation data and the corresponding prediction data of the operation mode.

[0020] The resource consumption index is determined according to the energy consumption data and loss data of each component of the target virtual power plant.

[0021] In one of the embodiments, the power generation equipment includes thermal power units, wind power units, and photovoltaic power generation units; and the operation model of the power generation equipment is constructed, including:

[0022] The power generation power and start-up resource consumption of the thermal power unit, the power generation power and wind speed prediction data of the wind power unit, and the light intensity prediction data and power generation power of the photovoltaic power generation unit are obtained.

[0023] According to the power generation of the thermal power generating unit and the starting resource consumption, an operation model of the thermal power generating unit is constructed;

[0024] According to the power generation of the wind power generating unit and the wind speed prediction data, an operation model of the wind power generating unit is constructed;

[0025] According to the light intensity prediction data and the power generation of the photovoltaic power generating unit, an operation model of the photovoltaic power generating unit is constructed.

[0026] In one of the embodiments, an operation model of the energy storage device is constructed, including:

[0027] The electric capacity and the charging and discharging power of the energy storage device are acquired;

[0028] According to the electric capacity and the charging and discharging power of the energy storage device, an operation model of the energy storage device is constructed.

[0029] In the second aspect, the application further provides an acquisition device of a virtual power plant scheduling strategy. The device includes:

[0030] A data acquisition module is configured to acquire energy parameters and historical operation data of each component of a target virtual power plant and energy conversion efficiency, wherein the components of the virtual power plant include at least one of the following: power generating equipment, energy storage equipment, transmission equipment, and load equipment;

[0031] A model construction module is configured to construct an operation model of each component according to the energy parameters of each component of the target virtual power plant, and to sample and generate a plurality of operation modes of the target virtual power plant according to the historical operation data;

[0032] The data acquisition module is further configured to determine a risk index and a resource consumption index of the virtual power plant in each operation mode according to operation data of each operation mode;

[0033] The model construction module is further configured to determine a target operation model of the target virtual power plant based on the operation model of each component, each operation mode, and the corresponding risk index and resource consumption index, and the energy conversion efficiency;

[0034] A strategy determination module is configured to determine a scheduling strategy of each component of the target virtual power plant according to the target operation model of the target virtual power plant.

[0035] In the third aspect, the application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the acquisition method of the virtual power plant scheduling strategy according to any one of the embodiments of the present disclosure when executing the computer program.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. The computer program, when executed by a processor, implements the method for obtaining a virtual power plant scheduling strategy according to any one of the embodiments of the present application.

[0037] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program. The computer program, when executed by a processor, implements the method for obtaining a virtual power plant scheduling strategy according to any one of the embodiments of the present application.

[0038] The method, device, computer device, storage medium and computer program product for obtaining a virtual power plant scheduling strategy described above obtain energy parameters, historical operation data and energy conversion efficiency of power generation, energy storage, transmission, load and other components in a virtual power plant, construct component operation models according to the above data, and sample a plurality of operation modes; determine risk indexes and resource consumption indexes according to the operation mode data, and determine a target operation model in combination with the component operation models, the energy conversion efficiency and the like, and finally obtain a component scheduling strategy. This scheme can fully reflect the characteristics of each component by comprehensively collecting data and constructing accurate models; sampling a plurality of operation modes can cover various scenarios, and in combination with risk and resource consumption index evaluation, the target operation model can be more scientific, and thus the scheduling strategy can improve energy utilization efficiency while ensuring operation stability, and realize efficient and safe operation of the virtual power plant. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 An application environment diagram of the method for obtaining a virtual power plant scheduling strategy in an embodiment;

[0040] Figure 2 A flowchart of the method for obtaining a virtual power plant scheduling strategy in an embodiment;

[0041] Figure 3 A flowchart of the implementation of the method for obtaining a virtual power plant scheduling strategy in an embodiment;

[0042] Figure 4 A structural block diagram of the device for obtaining a virtual power plant scheduling strategy in an embodiment;

[0043] Figure 5 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical scheme and advantages of the present application clearer, further detailed description will be made to the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0045] The method for obtaining a virtual power plant scheduling strategy provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The terminal 102 is used to collect energy parameters of components. The server 104 analyzes the collected data by receiving the data collected by the terminal 102, and obtains a scheduling strategy of a target virtual power plant. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle-mounted device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0046] In one embodiment, as shown in Figure 2 A method for obtaining a virtual power plant scheduling strategy is provided, comprising the following steps:

[0047] In step S200, energy parameters and historical operation data, and energy conversion efficiency of each component of a target virtual power plant are obtained. The components of the virtual power plant include at least one of the following: power generation equipment, energy storage equipment, transmission equipment, and load equipment.

[0048] The target virtual power plant can refer to a power coordination management system that aggregates and optimizes DG (Distributed Generation), energy storage systems, controllable loads, electric vehicles, and other DER (Distributed Energy Resources) through advanced information communication technology and software systems, and participates in the power market and grid operation as a special power plant. The target virtual power plant can include various energy production devices (such as distributed photovoltaic power stations, wind turbines, biomass energy generation devices, etc.), energy storage devices (battery energy storage systems, flywheel energy storage, etc.), and load ends (industrial loads, commercial loads, residential loads, etc.). The energy parameters of each component can include fuel cost and start-stop cost of thermal power units, power generation, state variables of power generation, etc.; rated output power of wind turbines, cut-in and cut-out wind speed, rated wind speed, actual wind speed, etc.; average and normal distribution values of sunlight radiation of photovoltaic generators, upper and lower limits of solar radiation, photovoltaic power generation efficiency, total area of photovoltaic components, and sunlight time, etc.; energy consumption, fixed energy consumption, operating energy consumption, operating power, and amount of captured carbon dioxide of carbon capture devices, etc.; electric capacity and charging and discharging efficiency of electric energy storage devices, etc. The historical operation data can include the operating state, load change, power generation, energy storage charging and discharging record, and the influence of external environmental factors on device operation of each component in different time periods in the past, etc. The energy conversion efficiency can include the energy loss ratio in the conversion process between different energy forms, such as the efficiency of converting chemical energy into electrical energy or the efficiency of storing electrical energy into chemical energy.

[0049] In an exemplary embodiment, the specific way of obtaining the energy parameters and historical operation data of each component of the target virtual power plant, and the energy conversion efficiency can include: collecting the operating state data of the power generation equipment in real time through the sensor network, such as power generation, temperature, fuel consumption, etc.; extracting the historical charging and discharging record and charging and discharging efficiency data of the energy storage device by using the database query interface; obtaining the real-time load data and loss information of the transmission equipment through the smart meter; and exporting the demand curve and priority setting of the load equipment from the user management system. In addition, external environmental data such as weather forecast information, market price fluctuations, etc. can also be combined.

[0050] In step S202, an operating model of each component is constructed according to the energy parameters of each component of the target virtual power plant, and a plurality of operating modes of the target virtual power plant are generated by sampling according to the historical operation data.

[0051] In an exemplary embodiment, machine learning algorithms are used to analyze the historical operation data and identify typical characteristics under different operating conditions. According to these characteristics, the historical operation data is divided into several categories, and samples are randomly selected from each category to generate multiple representative initial operation modes. Subsequently, by comparing the differences in operating parameters between the initial operation modes, such as power fluctuation range, frequency of charging and discharging of energy storage devices, etc., operation modes that meet the preset similarity requirements are screened out and optimized, and finally multiple operation modes of the target virtual power plant are obtained. These operation modes can comprehensively reflect the operating state of the target virtual power plant under different operating conditions, and provide reliable basis for subsequent risk assessment and resource optimization.

[0052] In an exemplary embodiment, the Latin hypercube sampling method can be used to obtain multiple operation modes of the virtual power plant. By stratified sampling of the historical operation data, the key characteristics of the target virtual power plant under different operating conditions can be effectively captured. In addition, combined with the Monte Carlo simulation technology, random perturbation can also be performed on the initial operation modes generated by sampling to simulate the uncertainty factors that may be encountered in actual operation. On this basis, clustering analysis algorithms are used to classify and merge the initial operation modes, eliminate redundant modes, and retain the most representative set of operation modes.

[0053] Step S204, according to the operation data of each operation mode, determines the risk index and resource consumption index of the virtual power plant under each operation mode.

[0054] The risk index can include quantitative evaluation of uncertainty factors that the operation mode may face in actual operation, such as power fluctuation of power generation equipment, charging and discharging efficiency variation of energy storage equipment, and prediction error of load demand, etc. The resource consumption index can include comprehensive consumption evaluation of virtual power plant under different operation modes in terms of energy, equipment wear and tear, etc., such as fuel consumption, battery cycle times, transmission loss, etc.

[0055] In an exemplary embodiment, the risk index can include risk avoidance strategies, and the resource consumption index can include target functions of resource consumption, etc. Specifically, IGDT (Information Gap Decision Theory) can be used to build a source-load uncertainty model to determine risk avoidance strategies and target functions, etc.

[0056] In an exemplary embodiment, the specific method of determining the risk index can include: based on historical operation data and real-time monitoring data, using statistical analysis method to calculate the fluctuation range of key parameters of each operation mode, and combining with the preset risk weight coefficient, to generate the corresponding risk score. By introducing a machine learning model, abnormal situations in the operation mode can be identified and warned, further improving the accuracy of risk assessment. For the calculation of resource consumption index, the energy consumption data and loss data of each component can be integrated to build a multi-dimensional resource consumption evaluation model. For example, for power generation equipment, its fuel consumption and power generation efficiency can be analyzed; for energy storage equipment, its life loss can be evaluated by combining its charging and discharging frequency and depth; for transmission equipment, its energy loss can be calculated according to the line impedance and current load. Finally, the resource consumption evaluation results of each component are weighted and summarized to obtain the comprehensive resource consumption index under each operation mode.

[0057] In another embodiment, a dynamic adjustment mechanism can also be introduced to update the risk index and resource consumption index in real time according to changes in the external environment. For example, when the weather conditions change dramatically, the operation risk of wind turbine generators and photovoltaic generators can be re-evaluated, and the corresponding resource consumption index can be adjusted.

[0058] Step S206, based on the operation model of each component, each operation mode, and the corresponding risk index and resource consumption index, and the energy conversion efficiency, the target operation model of the target virtual power plant is determined.

[0059] In an exemplary embodiment, the determination process of the target operation model can include comprehensive optimization of each component operation model. The operation model of each component is matched with the corresponding operation mode to analyze the synergistic effect of each component under different modes. Combined with the risk index and resource consumption index, a multi-objective optimization function is constructed, which needs to consider key indicators such as operation stability, energy utilization efficiency and economy. By introducing intelligent optimization algorithms such as genetic algorithm or particle swarm optimization algorithm, the multi-objective optimization function is solved to obtain a set of optimal solutions. Based on the preset decision rule, the target operation model that best meets the actual demand is selected from the optimal solution set, etc.

[0060] In another exemplary embodiment, the construction of the target operation model can also combine real-time data feedback mechanism, and continuously optimize the model parameters through online learning. For example, using reinforcement learning algorithm, according to the actual operation performance of the virtual power plant, the weight coefficient in the model is dynamically adjusted to better adapt to the changes in external environment and fluctuations in internal operation state, etc.

[0061] Step S208, according to the target operation model of the target virtual power plant, the scheduling strategy of each component of the target virtual power plant is determined.

[0062] In an exemplary embodiment, the determination of the scheduling strategy needs to comprehensively consider various parameters and indicators in the target operation model. First, according to the synergistic effect of each component in the target operation model, a preliminary scheduling framework is formulated. This framework needs to clearly define the priority and responsibility division of each component in different operation modes, such as the start-stop timing of power generation equipment, the charging and discharging plan of energy storage equipment, and the demand response arrangement of load equipment, etc. Subsequently, combined with the risk index and resource consumption index, the preliminary scheduling framework is optimized and adjusted to ensure the efficient use of resources while reducing the operation risk.

[0063] In an exemplary embodiment, a hierarchical optimization method can be used to refine the scheduling strategy. The first layer optimization focuses on the overall energy distribution, and the energy flow direction and proportion between components are determined by a global optimization algorithm; the second layer optimization focuses on local details, and a personalized scheduling scheme is designed for the specific operation characteristics of each component. For example, for power generation equipment, the output power can be dynamically adjusted according to its fuel consumption curve and power generation efficiency; for energy storage equipment, the charging and discharging cycle can be planned in advance by predicting future load demand, to prolong the service life of the equipment and improve economic benefits.

[0064] In an exemplary embodiment, the scheduling strategy can also have certain flexibility and robustness. By introducing real-time data monitoring and feedback mechanisms, the scheduling scheme can be dynamically adjusted to quickly adapt to changes in the external environment. For example, in the case of sudden changes in weather conditions or market price fluctuations, the scheduling strategy can automatically adjust the operation state of the power generation equipment or the charging and discharging plan of the energy storage equipment, thereby ensuring the overall operation stability of the virtual power plant. At the same time, artificial intelligence technologies such as deep learning or reinforcement learning can be combined to further improve the intelligent level of the scheduling strategy, enabling it to make better decisions in complex and variable operating scenarios.

[0065] In the above method for obtaining a virtual power plant scheduling strategy, the energy parameters, historical operation data, and energy conversion efficiency of the power generation, energy storage, transmission, and load components in the virtual power plant are obtained, based on which the operation models of each component are constructed, and multiple operation modes are generated by sampling; the risk index and resource consumption index are determined according to the data of each operation mode, and the target operation model is determined in combination with the component operation model, energy conversion efficiency, etc., and finally the scheduling strategy of each component is obtained. This scheme can fully reflect the characteristics of each component by comprehensively collecting data and constructing accurate models; the generation of multiple operation modes can cover various scenarios, and the evaluation of risk and resource consumption index can make the target operation model more scientific, thereby enabling the scheduling strategy to ensure operation stability (reduce risk) while improving energy utilization efficiency (optimize resource consumption), and achieving efficient and safe operation of the virtual power plant.

[0066] In one embodiment, the step of sampling and generating multiple operating modes of the target virtual power plant based on the historical operating data includes:

[0067] By using the Latin hypercube sampling strategy, the historical operating data are processed to obtain multiple initial operating modes of the target virtual power plant.

[0068] By comparing the differences between the initial operating modes, the initial operating modes whose differences meet the preset requirements are merged to obtain multiple operating modes of the target virtual power plant.

[0069] In one exemplary embodiment, a clustering analysis algorithm is used to classify the initial operating modes. By calculating the similarity index between each mode, a representative set of operating modes is identified. Specifically, hierarchical clustering or K-means clustering methods can be used to group the initial operating modes with high similarity into one class, and the mode with the most typical characteristics is selected as the final operating mode. Furthermore, the clustering results can be manually verified and adjusted by incorporating the experience and knowledge of domain experts to remove modes that do not conform to actual operating patterns.

[0070] In one exemplary embodiment, a method combining Latin hypercube sampling can be used to extract wind and solar power processing scenes. Specifically, this may include extracting wind and solar power output scenes by combining Latin hypercube sampling with the description of current market uncertainty. The extracted sample scenes are then reduced, with the following specific steps: similar scenes are reduced using scene distance calculations, taking into account the average scene distance, i.e.:

[0071] (1)

[0072] In the formula, X represents the average distance of the scene. iw and X jw These are the sample values ​​for each scenario. The nearest sample is removed from the scene set. In the formula, For the scene The probability of occurrence For the scene and scene The distance between them. Update the probability of the sample appearing. In the formula, To reduce the number of scenes. Repeat the above process of reducing similar scenes, removing the nearest sample, and updating the probability of the sample's occurrence until the number of scenes is reduced to [number missing]. The day-ahead load forecast uses a point forecasting method. The actual load value consists of the point forecast value and the day-ahead forecast error value that conforms to a normal distribution with a mean of 0. In the formula, for actual value of the load in the time period, predicted value of the load in the time period, predicted value of the load in the time period, predicted value of the load in the time period, predicted error value of the load in the time period. The load prediction value is also subjected to Latin hypercube sampling and scenario reduction processing, that is, the load samples are subjected to similar scenario reduction, removal of the nearest sample, and updating of the probability of occurrence of the sample until the number of scenarios of the load prediction is reduced to .

[0073] In this embodiment, by combining the above methods, the number of scenarios can be effectively reduced while retaining key features, thereby improving the efficiency and accuracy of the generated operation mode. In addition, by introducing a normal distribution model of the load prediction error, the ability to characterize uncertainty can be further enhanced, making the generated operation mode more close to the actual operation situation. This method not only applies to the dispatching needs of the day-ahead market, but also can be extended to real-time dispatching scenarios to cope with more complex dynamic changes.

[0074] In one embodiment, determining the scheduling strategy of each component of the target virtual power plant according to the target operation model of the target virtual power plant comprises:

[0075] Obtaining the upper and lower limit parameters of the operating power of the power generation equipment, the charging and discharging power and capacity parameters of the energy storage equipment, and the transmission capacity parameters of the transmission equipment.

[0076] Establishing a power generation equipment constraint condition according to the upper and lower limit parameters of the operating power of the power generation equipment, establishing an energy storage equipment constraint condition according to the charging and discharging power and capacity parameters of the energy storage equipment, and establishing a transmission equipment constraint condition according to the transmission capacity parameters of the transmission equipment.

[0077] Solving the target operation model of the target virtual power plant according to the power generation equipment constraint condition, the energy storage equipment constraint condition, and the transmission equipment constraint condition to obtain the scheduling strategy of each component of the target virtual power plant.

[0078] In an exemplary embodiment, the target operation model can be further solved by combining an optimization algorithm. For example, a mixed integer linear programming method is used to find the optimal energy distribution scheme under the premise of meeting the constraint conditions of each component. By defining the objective function, multi-dimensional indicators such as operation stability, energy utilization efficiency, and economy are considered in the scope of consideration to achieve global optimization. In the solving process, a dynamic weight adjustment mechanism can also be introduced to update the weight coefficients in the objective function in real time according to the changes in the external environment, to ensure the adaptability and robustness of the scheduling strategy.

[0079] In an example embodiment, the constraints can include system power balance, unit operation constraints, system reserve capacity constraints, carbon capture device operation constraints, and market transaction power constraints, and the specific acquisition can include system power balance ; wherein, represents the active power output of the thermal power unit; represents the active power output of the wind power unit; represents the active power output of the photovoltaic unit; represents the real-time load of the virtual power plant; is the power consumption of the carbon capture device. Unit operation constraints: unit output constraints ; , are the upper and lower limits of the thermal power unit output. The wind power and photovoltaic power output constraints are the same. Thermal power unit ramping constraints ; , are the ramping constraints of the thermal power unit power; System reserve capacity constraints ; wherein, is the load demand of the system at time t, is the reserve demand of the system at time t, is the line loss rate of the system, is the unit self-consumption rate, is the maximum unit output of the unit at time t. Carbon capture device operation constraints ; ; wherein, and are the minimum and maximum output upper limits of the carbon capture device; is the ramping rate constraint of the carbon capture device. Market transaction power constraints and the like.

[0080] In this embodiment, by introducing the above-mentioned various constraints, the target operation model can fully consider the actual operation constraints of each component in the virtual power plant and the requirements of the external environment during the solving process. This not only helps to improve the feasibility of the dispatching strategy, but also effectively avoids the operation risks caused by ignoring key constraints.

[0081] In one embodiment, the risk index and resource consumption index of the virtual power plant in each operation mode are determined according to the operation data of each operation mode, comprising:

[0082] According to the historical operation data of each component of the target virtual power plant, the prediction data of each operation mode is obtained.

[0083] Based on the difference between the operation data and the corresponding prediction data of the operation mode, the risk index is determined.

[0084] According to the energy consumption data and loss data of each component of the target virtual power plant, a resource consumption index is determined.

[0085] In an exemplary embodiment, various methods can be employed to calculate the risk index and the resource consumption index to ensure the comprehensiveness and accuracy of the evaluation. For the calculation of the risk index, a bias analysis model can be introduced to quantify the degree of difference between the operation data and the predicted data. For example, statistical indicators such as root mean square error or mean absolute percentage error can be used to quantitatively evaluate the potential risks under each operation mode. At the same time, combined with the sensitivity analysis method, the key factors that have the greatest impact on the risk are identified, thereby providing a basis for subsequent optimization. For the determination of the resource consumption index, the energy consumption characteristics and loss of each component need to be considered comprehensively. Specifically, a weighted evaluation model of resource consumption can be constructed based on parameters such as unit energy consumption, equipment operation efficiency, and energy conversion loss. By setting different weight coefficients, the importance distribution of various resources in the overall operation is reflected. In addition, life cycle analysis methods can be introduced to consider the long-term loss and maintenance cost of the equipment, further improving the scientificity and practicality of resource consumption evaluation.

[0086] In an exemplary embodiment, the calculation results of the risk index and the resource consumption index can be used as important input parameters of the multi-objective optimization function. Through the dynamic weighting of the two, the construction of the target operation model and the formulation of the scheduling strategy can be better guided, thereby achieving the dual goals of safety and economy of virtual power plant operation.

[0087] In an exemplary embodiment, multi-objective optimization algorithms can be used to comprehensively evaluate the risk index and the resource consumption index. For example, the Pareto optimality theory can be used to find a balance point between reducing operation risk and reducing resource consumption. By constructing a double-objective optimization model, the risk index and the resource consumption index are used as optimization objectives, and corresponding constraint conditions are set to ensure the feasibility and practicality of the model. In the solving process, genetic algorithms or particle swarm optimization algorithms can be introduced to generate a series of non-inferior solution schemes for decision-makers to select the optimal scheduling strategy according to actual needs. In addition, fuzzy logic methods can be combined to perform fuzzy evaluation of the risk and resource consumption under different operation modes, further improving the flexibility and adaptability of the optimization results. This comprehensive evaluation method can provide more scientific and reasonable scheduling basis for virtual power plants in complex and variable operating environments.

[0088] In an exemplary embodiment, the risk index and resource consumption index can also be obtained by using the IGDT algorithm: Specifically, in the real-time operation of the virtual power plant, the wind and light output and the load are subject to abnormal changes due to actual weather and other factors, so the IGDT is used to build a source-load uncertainty model. The envelope constraint model is used to model the wind power, photovoltaic power and load uncertainty set respectively, as follows:

[0089] (2)

[0090] In the formula, is the actual power generation of wind power; is the historical data of wind power output in the dispatching period; is the fluctuation range (uncertainty) of wind power output, which is a dimensionless value, reflecting the maximum degree of deviation of wind power output from historical data. Similarly, the uncertainty of photovoltaic power generation can be expressed by the envelope constraint model as , and the uncertainty of load can be expressed by the envelope constraint model as . The system comprehensive uncertainty can be expressed as In the formula, is the system comprehensive uncertainty level; , and are the weights of wind power, photovoltaic and load uncertainty respectively. The weights can be determined by objective weighting method, etc. In real-time operation, there is a certain deviation between the predicted value and the actual value, and combined with the IGDT theory, there are two strategies of risk aversion and opportunity seeking. In the risk aversion strategy, the deviation generated in the operation of the virtual power plant is regarded as risk, at this time the virtual power plant will reduce the energy trading with the main grid to ensure the stable operation of the internal; in the opportunity seeking strategy, the deviation generated in the operation of the virtual power plant is regarded as opportunity, that is, the prediction accuracy is high, and the operation optimization can be carried out according to the prediction curve. In the risk aversion strategy:

[0091] (3)

[0092] In the formula, is the robustness deviation factor, the larger the value is, the stronger the robustness and risk resistance of the system are; is the objective function of the deterministic model, that is, the cost minimization of the virtual power plant. is the optimization target reference value, that is, when the wind, light and load are all historical data, the cost size obtained by solving the model; is the expected cost of the model under the risk aversion decision; , and are the uncertainty of wind, light and load under the risk aversion decision respectively. The superscript The historical data is represented. The opportunity-seeking decision has a more optimistic expectation for system uncertainty, and considers that the actual operation will be better than the historical data, so as to seek the solution under the minimum uncertainty. In the objective function established in the application, such a decision can be expressed as:

[0093] (4)

[0094] In the formula, is the system comprehensive uncertainty of the opportunity-seeking model, is the opportunity bias factor, The greater, the smaller the total cost of the virtual power plant, but the greater the risk it faces; is the expected cost under this scenario, 、 and are the uncertainties of wind, light and load under the opportunity-seeking decision.

[0095] In this embodiment, the influence of various factors on the operation of the virtual power plant is comprehensively considered, which can more accurately evaluate the feasibility and economy of each operation mode. At the same time, by using advanced data processing and analysis methods, the accuracy of the calculation of the risk index and the resource consumption index is improved, which provides a reliable basis for subsequent determination of the target operation model.

[0096] In one embodiment, the power generation equipment includes thermal power generating units, wind power generating units, and photovoltaic power generating units; and an operation model of the power generation equipment is constructed, including:

[0097] The power generation power and start-up resource consumption of the thermal power generating units, the power generation power and wind speed prediction data of the wind power generating units, and the light intensity prediction data and power generation power of the photovoltaic power generating units are obtained.

[0098] The operation model of the thermal power generating units is constructed according to the power generation power and start-up resource consumption of the thermal power generating units.

[0099] The operation model of the wind power generating units is constructed according to the power generation power and wind speed prediction data of the wind power generating units.

[0100] The operation model of the photovoltaic power generating units is constructed according to the light intensity prediction data and power generation power of the photovoltaic power generating units.

[0101] In an exemplary embodiment, the operation model of the thermal power unit can further consider factors such as fuel consumption, emission control, and thermal efficiency, etc. to improve its performance in multi-objective optimization. The operation model of the wind power unit can quantify the uncertainty of its output by introducing the probability distribution function of wind speed fluctuation, and dynamically correct it combined with historical data. The operation model of the photovoltaic power unit can construct a time-of-use power output prediction curve based on the time series characteristics of the light intensity, while considering the influence weight of weather type on light intensity. In addition, the charging and discharging characteristics of the energy storage device can also be included in the overall operation model, to balance the power generation and load demand, and improve the flexibility and stability of the system, etc.

[0102] In an exemplary embodiment, the thermal power unit model, the wind power unit model, the photovoltaic power unit model, the physical operation principle of carbon capture device, the electric energy storage operation model, and the carbon quota trading market and green certificate trading, etc. can be included, which can be obtained as follows: (1.1.1) thermal power unit physical model, the thermal power unit output model is, ; ; in the formula, and represent the fuel cost and start-stop cost of the thermal power unit. , and are the energy consumption coefficients of the thermal power unit. is the power generation power of the thermal power unit. is the state variable of the thermal power unit, a 0-1 variable, 1 represents that the thermal power unit is in operation, and 0 represents that the thermal power unit is in shutdown state. represents the start-up cost of the thermal power unit, which is related to the cold start and hot start state of the thermal power unit. At the same time, the carbon dioxide emission formula of the thermal power unit is as follows: in the formula, is the carbon dioxide emission of the thermal power unit, is the unit carbon dioxide emission of the thermal power unit. The physical model of the wind power unit: natural wind has strong randomness, and the output power of the wind power unit fluctuates with the wind speed. The Weibull distribution is combined to simulate the natural wind speed, and the probability density function is as follows, ; in the formula, represents the natural wind speed, and represent the shape and scale parameters of the distribution function. When the wind speed is within the range that the unit can withstand, the unit power increases with the increase of the wind speed, but if it exceeds the range, that is, the wind speed is too low or too high, the wind power unit will not start to avoid damage to the body. The functional relationship between wind power output and wind speed is as follows:

[0103] (5)

[0104] where, is the available output of wind turbine j at time t; gf is the rated output power of wind turbine; v i,w , v o,w are the cut-in and cut-out wind speed, respectively; vr,w is the rated wind speed; is the actual wind speed at time t. The output curve of photovoltaic system generally satisfies Beta distribution. The following is satisfied:

[0105] (6)

[0106] where, are the shape parameters of Beta distribution, respectively, is the irradiance correlation coefficient, which is introduced to calculate the parameters of Beta by the mean and standard deviation of irradiance: ; ; where, is the mean and normal distribution value of solar radiation, is the upper and lower limit of solar radiation . where, is the power generation efficiency of photovoltaic, is the total area of photovoltaic components, is the time of photovoltaic receiving sunlight. The physical operation principle of carbon capture device: carbon capture is mainly divided into three processes: absorption, regeneration and compression. The flue gas generated after the combustion of fuel in the thermal power unit is sucked into the absorption tower to produce rich liquid; through the heat exchanger, CO2 in the rich liquid is separated into the regeneration tower, and the remaining rich liquid containing a small amount of CO2 enters the lean liquid storage; the CO2 in the regeneration tower is compressed by the compressor for convenient transportation and storage. In the virtual power plant, the energy consumption of the carbon capture device is mainly provided by the thermal power unit. The energy consumption of the carbon capture device can be expressed as, ; ; where, is the energy consumption of the carbon capture device at time; is the fixed energy consumption of the carbon capture device at time, which is a constant value, with the unit of kW; is the operating energy consumption of the carbon capture device at time t, with the unit of kW, because the energy consumption of the carbon capture device is provided by the thermal power unit, therefore, , is the power provided by the thermal power unit to the carbon capture device at time. And the amount of CO2 captured by the carbon capture device at time is, where, is the amount of CO2 captured by the carbon capture device; ​The operation energy consumption of the carbon capture device for processing unit CO2. The energy storage operation model: the power of the energy storage is generally related to the charging and discharging power and capacity, which can be expressed as: In the formula, represents the electric capacity of the energy storage at time; and are the charging and discharging efficiencies of the energy storage, respectively; and are the charging and discharging powers of the energy storage, and since the energy storage cannot charge and discharge at the same time, there is , that is, when one of them is a non-zero positive number, the other must be 0. In addition, in order to ensure the low carbon nature of the virtual power plant, the carbon market transaction cost and the "offset" of the green value of new energy to the power generation cost are added. Carbon quota trading market: in the carbon trading market, the patent combines the carbon quota mechanism, and based on the installed capacity and power generation, the carbon quota that the virtual power plant can obtain can be expressed as:

[0107] (7)

[0108] (8)

[0109] (9)

[0110] In the formula, is the carbon quota that the virtual power plant can obtain, which is the weighted result of the carbon quota based on the capacity allocation method and the carbon quota based on the power generation allocation method. is the carbon quota that the virtual power plant can obtain based on the capacity allocation method; is the carbon quota that the virtual power plant can obtain based on the power generation allocation method. , are different weighting coefficients, and . is a correction coefficient. is the number of virtual power plants containing thermal power. is the thermal power installed capacity of the virtual power plant , is the thermal power generation of the virtual power plant . The virtual power plant makes a decision to buy or sell carbon quotas by the difference between the carbon quotas it obtains and the actual carbon emissions.

[0111] (10)

[0112] (11)

[0113] In the formula, represents the virtual power plant The carbon quota transaction income in a transaction cycle, the value is positive, which means that the virtual power plant sold the remaining carbon quota, the value is negative, which means that the virtual power plant i purchased carbon quota. represents the real-time price of carbon quota, represents the virtual power plant The actual carbon emissions in period. is the virtual power plant The thermal power generation in period, is the virtual power plant The carbon dioxide emission coefficient of thermal power unit in virtual power plant i. Green certificate transaction: green power certificate transaction is the embodiment of the environmental value of new energy power generation in virtual power plant. The income of green certificate is proportional to the new energy power generation, which is represented as In the formula, is the virtual power plant The number of green certificates that can be converted from new energy power generation in virtual power plant i. is the virtual power plant The wind power generation in period, is the virtual power plant The photovoltaic power generation in period. Virtual power plant Itself can guarantee its own consumption proportion, corresponding to the consumption responsibility weight, the actual number of green certificates that can be sold by virtual power plant is:

[0114] (12)

[0115] In the formula, is the virtual power plant The actual number of green certificates that can be sold, is the consumption responsibility weight of non-water renewable energy. Thus, the green certificate income of virtual power plant can be expressed as:

[0116] (13)

[0117] In the formula, is the green certificate income of virtual power plant i, is the green certificate price.

[0118] In this embodiment, by constructing the operation model of each component, the actual operation state and performance characteristics of each device inside the target virtual power plant can be accurately reflected. At the same time, combined with the multiple operation modes generated by the historical operation data, the operation scenes of the virtual power plant under different working conditions can be comprehensively covered. By analyzing the risk index and resource consumption index of these operation modes, the overall operation efficiency of the target virtual power plant is further optimized. In addition, based on the adjustment of the energy conversion efficiency of the target operation model, the scientificity and economy of the scheduling strategy are ensured.

[0119] In one embodiment, the operation model of the energy storage device is constructed, including:

[0120] The electric capacity and the charging and discharging power of the energy storage device are obtained.

[0121] According to the electric capacity and the charging and discharging power of the energy storage device, the operation model of the energy storage device is constructed.

[0122] In an exemplary embodiment, the operation model of the energy storage device can further consider the influence of the ambient temperature on the charging and discharging efficiency. Specifically, when the ambient temperature is lower than a certain threshold, the charging and discharging efficiency of the energy storage device will show a nonlinear downward trend, at which time a temperature correction coefficient needs to be introduced to adjust the model accuracy. The temperature correction coefficient can be obtained by fitting experimental data and dynamically updated combined with the actual operation conditions. In addition, the life consumption of the energy storage device is closely related to its charging and discharging depth, so a life evaluation module based on the charging and discharging depth needs to be added to the model. This module estimates the remaining service life of the energy storage device by statistically analyzing the depth distribution of each charging and discharging cycle, and optimizes the charging and discharging strategy accordingly, thereby prolonging the service period of the device while ensuring the operation efficiency.

[0123] In this embodiment, by constructing the operation model of each component, the operation logic of the internal devices of the virtual power plant is further refined. In the operation model of the energy storage device, in addition to considering the electric capacity and the charging and discharging power, the influence of the ambient temperature on the performance of the device is also introduced. The temperature correction coefficient obtained by fitting experimental data can dynamically adjust the model parameters, thereby improving the prediction accuracy.

[0124] In an exemplary embodiment, the construction of the target function can also construct the cost of the virtual power plant, including: the operation cost of the thermal power unit, the power generation cost of the wind power and photovoltaic power unit, the carbon capture cost, the carbon trading cost, the main grid trading income, the energy storage operation cost, and the cost acquisition can specifically include: the operation cost of the thermal power unit is referenced:

[0125] (14)

[0126] (15)

[0127] (16)

[0128] Considering the recovery of investment costs during the operating period, the power generation cost of wind and solar power generators is the product of the cost per kilowatt-hour of new energy (the price per kilowatt-hour at which investment costs are recovered under a fixed rate of return) and the amount of electricity generated, which can be expressed as: In the formula, , These are the unit cost of electricity for wind power and solar power, respectively. , Wind power and solar power, respectively The power generation capacity at any given time. Carbon capture cost: The cost of carbon capture mainly considers energy consumption. Since carbon capture power plants need to supply energy to the carbon capture system during operation, this portion of electricity can be sold for profit compared to when there is no carbon capture device. Therefore, the energy consumption cost of carbon capture can be expressed as... In the formula, P t For virtual power plants The electricity price at any given time. Carbon trading costs: When representing the carbon allowance revenue of a virtual power plant, there can be positive and negative revenue; the negative revenue represents the cost of purchasing the carbon allowance. Therefore, the carbon trading cost can be expressed as: (17)

[0129] The cost "offsetting" of green certificates takes into account the green value of renewable energy units within the virtual power plant. This is used to offset a portion of the power generation costs of the virtual power plant. Mainnet transaction revenue:

[0130] (18)

[0131] (19)

[0132] In the formula, Market-based revenue from selling electricity from virtual power plants to the main grid. for Electricity sold at any time Real-time price for electricity sold by the virtual power plant. Energy storage operating costs:

[0133] (20)

[0134] (twenty one)

[0135] (twenty two)

[0136] In the formula, This indicates the operating cost of the energy storage system; and Represent The power of the energy storage system during discharge and charging at all times; with respectively represent the price of discharging and charging of the energy storage system at time t; with represent the energy conversion efficiency of the energy storage system; C s represent the loss cost of the energy storage system output; and represent the state variable of charging and discharging of the energy storage system; represent the start-stop cost of the energy storage system. The low-carbon economic operation objective function of the virtual power plant aims to minimize the internal cost of the virtual power plant, and the optimization operation model is constructed as:

[0137] (23)

[0138] In an exemplary embodiment, the output plan of the virtual power plant can also be adjusted in real time in combination with the risk preference of the virtual power plant to obtain the clearing result. In real-time clearing, the day-ahead scheduling result needs to be taken as a boundary condition, and the real-time wind, light, and load prediction results are adjusted. From the perspective of different strategies, the real-time clearing result of the virtual power plant is described. In the real-time market, in order to be consistent with the optimization target of the day-ahead market operation, the target function of the real-time market is also set to minimize the system operation cost,

[0139] (24)

[0140] In the formula, the adjustment cost in the real-time market is uniformly represented as the income of electric energy in the real-time market. Specifically, the robust uncertainty of the three fluctuation parameters is taken as the lower bound of fluctuation, and the opportunity uncertainty is taken as the upper bound of fluctuation, so that

[0141] (25)

[0142] (26)

[0143] (27)

[0144] By using a mixed integer programming model for solution, the operation plan that can be adopted by the virtual power plant between the risk-averse and opportunity-seeking strategies can be obtained.

[0145] In an exemplary embodiment, the method for obtaining the virtual power plant scheduling strategy can be implemented as shown in the schematic diagram Figure 3 , and specifically includes:

[0146] In step S300, the internal component constitution and operation model of the virtual power plant are determined. Specifically, the internal component constitution of the virtual power plant is determined. Specifically, the virtual power plant includes power sources, loads and flexible resources. The power sources include thermal power units and renewable energy units, the loads mainly include residential loads, and the flexible resources include carbon capture devices and electric energy storage, etc. Meanwhile, the operation model of each component is determined.

[0147] In step S302, the uncertainty model of the virtual power plant in the day-ahead market and the real-time market is constructed. Specifically, the uncertainty model of the virtual power plant in the day-ahead market and the real-time market is constructed. On one hand, the source-load bilateral uncertainty in the day-ahead market is considered, the Latin hypercube sampling method is used to form multiple wind and light output scenarios, and the mean method is used to reduce the multiple scenarios; on the other hand, in the real-time power market, the envelope model is used to construct the uncertainty set model of wind and light output and load.

[0148] In step S304, the cost minimization optimization operation model of the virtual power plant in the day-ahead market is constructed. Specifically, the cost minimization optimization operation model of the virtual power plant in the day-ahead market is constructed. The operation cost of the virtual power plant is considered, including fuel cost, unit operation cost, and income from the sale of excess electricity (which can be regarded as negative cost), etc.

[0149] In step S306, the risk preference of the virtual power plant is described, and the output plan of the virtual power plant is adjusted to obtain the clearing result. Specifically, the output plan of the virtual power plant is adjusted in real time to obtain the clearing result according to the risk preference of the virtual power plant. The real-time market clearing of the virtual power plant takes the day-ahead dispatching result as the boundary condition, and adjusts the output value of each unit in the virtual power plant according to the real-time prediction result of wind, light and load. Considering the risk resistance and opportunity preference strategies, the real-time clearing result of the virtual power plant is expressed respectively.

[0150] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiment of the present application further provides a virtual power plant scheduling strategy acquisition device for implementing the virtual power plant scheduling strategy acquisition method. The implementation scheme of the device for solving the problem is similar to the implementation scheme described in the above method, so the specific limitations in one or more virtual power plant scheduling strategy acquisition device embodiments provided below can refer to the limitations of the virtual power plant scheduling strategy acquisition method in the above text, which will not be repeated here.

[0152] In one embodiment, as shown in Figure 4 A virtual power plant scheduling strategy acquisition device 400 is provided, comprising a data acquisition module 401, a model construction module 403 and a strategy determination module 405, wherein:

[0153] The data acquisition module is configured to acquire energy parameters and historical operation data of each component of a target virtual power plant and energy conversion efficiency, wherein the components of the virtual power plant comprise at least one of the following: power generation equipment, energy storage equipment, transmission equipment and load equipment.

[0154] The model construction module is configured to construct an operation model of each component according to the energy parameters of each component of the target virtual power plant, and sample a plurality of operation modes of the target virtual power plant according to the historical operation data.

[0155] The data acquisition module is further configured to determine a risk index and a resource consumption index of the virtual power plant in each operation mode according to operation data of each operation mode.

[0156] The model construction module is further configured to determine a target operation model of the target virtual power plant based on the operation model of each component, each operation mode, the corresponding risk index and resource consumption index, and the energy conversion efficiency.

[0157] The strategy determination module is configured to determine a scheduling strategy of each component of the target virtual power plant according to the target operation model of the target virtual power plant.

[0158] Each module in the above virtual power plant scheduling strategy acquisition device can be realized by software, hardware and a combination thereof in whole or in part. Each module described above can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to call and execute the operations corresponding to each module by a processor.

[0159] In one embodiment, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. Wireless mode can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a virtual power plant scheduling strategy acquisition method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device. It can also be an external keyboard, touchpad or mouse, etc.

[0160] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0161] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties. The collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0162] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0163] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0164] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for obtaining a virtual power plant scheduling strategy, characterized in that, The method includes: The energy parameters, historical operating data, and energy conversion efficiency of each component of the target virtual power plant are obtained; wherein, each component of the virtual power plant includes at least one of the following: power generation equipment, energy storage equipment, transmission equipment, and load equipment; Based on the energy parameters of each component of the target virtual power plant, an operation model for each component is constructed; and based on the historical operation data, multiple operation modes of the target virtual power plant are sampled and generated. Based on the operational data of each of the aforementioned operational modes, determine the risk index and resource consumption index of the virtual power plant under each of the aforementioned operational modes; Based on the operating models of each component, the operating modes, the corresponding risk indices, the resource consumption indices, and the energy conversion efficiency, the target operating model of the target virtual power plant is determined. Based on the target operation model of the target virtual power plant, the scheduling strategy for each component of the target virtual power plant is determined.

2. The method according to claim 1, characterized in that, The step of sampling and generating multiple operating modes of the target virtual power plant based on the historical operating data includes: By using the Latin hypercube sampling strategy, the historical operating data are processed to obtain multiple initial operating modes of the target virtual power plant; By comparing the differences between the initial operating modes, the initial operating modes whose differences meet the preset requirements are merged to obtain multiple operating modes of the target virtual power plant.

3. The method according to claim 1, characterized in that, The step of determining the scheduling strategy for each component of the target virtual power plant based on the target operation model of the target virtual power plant includes: Obtain the upper and lower limits of the operating power of the power generation equipment, the charging and discharging power and capacity parameters of the energy storage equipment, and the transmission capacity parameters of the transmission equipment; Based on the upper and lower limits of the operating power of the power generation equipment, establish constraints for the power generation equipment; based on the charging and discharging power and capacity parameters of the energy storage equipment, establish constraints for the energy storage equipment; based on the transmission capacity parameters of the transmission equipment, establish constraints for the transmission equipment. Based on the constraints of the power generation equipment, the energy storage equipment, and the transmission equipment, the target operation model of the target virtual power plant is solved to obtain the scheduling strategy of each component of the target virtual power plant.

4. The method according to claim 1, characterized in that, The step of determining the risk index and resource consumption index of the virtual power plant under each of the aforementioned operating modes based on the operating data includes: Based on the historical operating data of each component of the target virtual power plant, the predicted data for each of the aforementioned operating modes are obtained; The risk index is determined based on the difference between the operational data and the corresponding predicted data of the described operational mode. Based on the energy consumption data and loss data of each component of the target virtual power plant, the resource consumption index is determined.

5. The method according to claim 1, characterized in that, The power generation equipment includes thermal power units, wind power units, and photovoltaic power units; the operation model of the power generation equipment is constructed, including: Acquire power generation and startup resource consumption of thermal power units; power generation and wind speed prediction data of wind turbine units; and solar irradiance prediction data and power generation of photovoltaic power units. Based on the power generation capacity and start-up resource consumption of thermal power units, an operation model for thermal power units is constructed; Based on the power generation and wind speed prediction data of wind turbine units, an operation model of the wind turbine units is constructed; Based on the predicted irradiance and power generation data of the photovoltaic generator set, an operation model for the photovoltaic generator set is constructed.

6. The method according to claim 1, characterized in that, Constructing an operational model for energy storage devices includes: Obtain the electrical capacity and charging / discharging power of energy storage devices; Based on the energy storage device's capacity and charging / discharging power, an operational model for the energy storage device is constructed.

7. A device for acquiring virtual power plant scheduling strategies, characterized in that, The device includes: The data acquisition module is used to acquire the energy parameters and historical operating data, and energy conversion efficiency of each component of the target virtual power plant; wherein, each component of the virtual power plant includes at least one of the following: power generation equipment, energy storage equipment, transmission equipment, and load equipment; The model building module is used to construct the operation model of each component based on the energy parameters of each component of the target virtual power plant; and to sample and generate multiple operation modes of the target virtual power plant based on the historical operation data. The data acquisition module is also used to determine the risk index and resource consumption index of the virtual power plant under each of the operating modes based on the operating data of each operating mode. The model building module is also used to determine the target operating model of the target virtual power plant based on the operating models of each component, each operating mode, the corresponding risk index and resource consumption index, and the energy conversion efficiency. The strategy determination module is used to determine the scheduling strategy of each component of the target virtual power plant based on the target operation model of the target virtual power plant.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images