Energy scheduling method and device of virtual power plant, computer equipment and storage medium

Abstract

The invention relates to an energy scheduling method and device for a virtual power plant, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: establishing a virtual power plant model, taking the overall profit maximization of the virtual power plant as a target, and constructing a target function containing the income of the virtual power plant participating in an energy market, the income of the virtual power plant participating in a regulation market and the operation cost of various responsive loads; establishing a power demand model of various responsive loads in the virtual power plant model and a corresponding first constraint condition, and establishing an energy scheduling model of power generation equipment and a corresponding second constraint condition; establishing a power profit model based on different risk tendencies; and determining an energy scheduling mode of the virtual power plant according to the target function, the power demand model and the corresponding first constraint condition, and the energy scheduling model and the corresponding second constraint condition. By adopting the method, different risk preferences can be considered, and the energy scheduling accuracy of the virtual power plant is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of virtual power plants, and in particular to an energy scheduling method and device for a virtual power plant, a computer device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the growth of global electricity demand and the increasing environmental problems, distributed energy resources (DERs) such as renewable energy generation are widely used around the world.

[0003] In recent years, as a coordinated control method integrating multiple distributed energy resources, virtual power plants (VPPs) can participate in the electricity market and provide ancillary services like traditional large power plants. The scheduling optimization method of virtual power plants has gradually attracted attention. This method includes multiple subjects in a unified scheduling range, establishes different generation equipment operation models, and establishes a scheduling scheme through collaborative optimization. Current research mainly focuses on the definition, control mode, mathematical modeling and optimization scheduling of virtual power plants. However, existing research has deficiencies in VPP participation in the regulation market and coordination with the energy market. Most of them do not fully consider the potential of demand side management, and the risk impact modeling is not precise enough.

[0004] Therefore, there is an urgent need for an energy scheduling method, device, computer device, computer readable storage medium and computer program product for a virtual power plant that can consider different risk preferences and improve the accuracy of energy scheduling for virtual power plants. SUMMARY

[0005] Therefore, there is an urgent need for an energy scheduling method, device, computer device, computer readable storage medium and computer program product for a virtual power plant that can consider different risk preferences and improve the accuracy of energy scheduling for virtual power plants.

[0006] In a first aspect, the present application provides an energy scheduling method for a virtual power plant, comprising:

[0007] establishing a virtual power plant model containing generation equipment and multiple types of responsive loads, maximizing the overall profit of the virtual power plant as the target, and constructing a target function containing the income of the virtual power plant participating in the energy market, the income of participating in the regulation market and the operation cost of each type of responsive load;

[0008] establishing a power demand model of the multiple types of responsive loads in the virtual power plant model and a corresponding first constraint condition, and establishing an energy scheduling model of the generation equipment and a corresponding second constraint condition;

[0009] establishing a power profit model based on different risk inclinations;

[0010] According to the target function, the power demand model and corresponding first constraint condition, and the energy scheduling model and corresponding second constraint condition, an energy scheduling mode of the virtual power plant is determined.

[0011] In one of the embodiments, the target function comprises a virtual power plant's revenue from participating in an energy market, a revenue from participating in a regulation market, and operating costs of various types of responsive loads, and includes:

[0012] The function relationship of the target function is:

[0013]

[0014] In the formula, maxprofit represents profit maximization; ReDA E (h,s) is the virtual power plant's revenue from participating in the energy market; ReDA RS (h,s) is the virtual power plant's revenue from participating in the regulation market; Co SDG (h,s) is the operating cost of the standby power generation equipment in the virtual power plant; Co DR (h,s) is the operating cost of various types of responsive loads in the virtual power plant; π s is the probability of scenario s;

[0015] The function relationship of the virtual power plant's revenue from participating in the energy market is:

[0016] ReDA E (h,s) = PDA(h,s)·λ E (h);

[0017] In the formula, PDA(h,s) is the energy power sold by the virtual power plant in the day-ahead market at time h and in scenario s; λ E (h) is the day-ahead market energy price at time h;

[0018] The function relationship of the virtual power plant's revenue from participating in the regulation market is:

[0019] ReDA RS (h,s) = RSDA(h,s)·λ RS (h,s) + (Delreg up (h,s) - Delreg down (h,s))·RSDA(h,s)·λ spot (h);

[0020]

[0021] In the formula, λ E(h) represents the day-ahead market energy price at time h; RSDA(h,s) represents the regulating service power sold by the virtual power plant in the day-ahead market at time h and under scenario s; λ RS (h,s) represents the day-ahead market-regulated service price at time h and scenario s; Delreg up (h,s) represents the upward adjustment request issued by the system operator at time h and in scenario s; Delreg down (h,s) represents the downward adjustment request issued by the system operator at time h and in scenario s; λ spot (h) represents the spot market price at time h; p1 and p2 are random parameters used to simulate the fluctuations in the spot market price.

[0022] The functional relationship between the operating costs of various responsive loads is as follows:

[0023]

[0024] In the formula, j is the consumer serial number; N l For the number of steps in the price-quantity quote package; λ is the price for the j-th consumer in the l-th step of the energy type demand response project; pl(j) is the load reduction accepted by the j-th consumer in the l-th step; RSDR (j,h) represents the price paid by the j-th consumer at time h in the demand response project for the service type of adjustment; RSDR(j,h,s) represents the power of the adjustment service provided by the j-th consumer at time h and in scenario s.

[0025] In one embodiment, the functional relationship of the operating cost of the backup power generation equipment is as follows:

[0026]

[0027] In the formula, The startup and power generation costs of backup power generation equipment; The carbon dioxide emission penalty cost of the standby power generation equipment; a, b, and c are the production cost coefficients of the standby power generation equipment; P SDG (h,s) represents the total power generation of the backup power generation equipment at time h and in scenario s; U SDG (h,s) are binary variables representing the start-up and shutdown states of the standby power generation equipment; SUC is the start-up cost of the standby power generation equipment; U on SDG (h,s) is a binary variable representing the startup state of the backup power generation equipment at time h and in scenario s; CO2 SDG λ represents the carbon dioxide emissions per kilowatt-hour of electricity generated by the standby power generation equipment. co2 The penalty price for carbon dioxide emissions.

[0028] In one embodiment, the power demand model of the multiple types of responsive loads and the functional relationship of the corresponding first constraint conditions include:

[0029]

[0030] In the formula, pl(j) is the load reduction amount accepted by the j-th consumer in step l; Pl(j) is the maximum load reduction amount of the j-th consumer in step l; PDR(j,h,s) is the energy power provided by the j-th consumer through demand response at time h and scenario s; RSDR(j,h,s) is the regulation service power provided by the j-th consumer at time h and scenario s; and PMax(j) is the maximum demand response potential of the j-th consumer.

[0031] In one embodiment, the functional relationship between the energy dispatch model of the power generation equipment and the corresponding second constraint includes:

[0032]

[0033] RS SDG (h,s)≤P SDG (h,s);

[0034] In the formula, P SDG (h,s) represents the energy dispatch power of the standby power equipment; PWT(h,s) is the output power of wind power at time h and scenario s; PDR(j,h,s) is the energy power provided by the j-th consumer through demand response at time h and scenario s; PDA(h,s) is the energy power sold by the virtual power plant in the day-ahead market at time h and scenario s; Delreg up (h,s) represents the upward adjustment request issued by the system operator at time h and in scenario s; Delreg down (h,s) represents the downward adjustment request issued by the system operator at time h and scenario s; RSDA(h,s) represents the adjustment service power sold by the virtual power plant in the day-ahead market at time h and scenario s; RS SDG (h,s) is the regulation service power provided by the standby power generation equipment at time h and scenario s; RSDR(j,h,s) is the regulation service power provided by the j-th consumer at time h and scenario s.

[0035] In one embodiment, the risk propensity type includes risk-averse and risk-seeking;

[0036] The robustness function of a risk-averse virtual power plant includes the following functional relationships:

[0037]

[0038] The opportunity function of a risk-seeking virtual power plant includes the following functional relationships:

[0039]

[0040] In the formula, α* represents a risk-averse target; P represents power; π s The probability of scenario s; ReDA E (h,s) represents the revenue of a virtual power plant participating in the energy market; ReDA RS (h,s) represents the revenue of the virtual power plant participating in the market regulation; Co SDG (h,s) represents the operating cost of the standby power generation equipment in the virtual power plant; Co DR (h,s) represents the operating costs of various responsive loads of the virtual power plant; RC represents the minimum profit level set by the virtual power plant; RN represents the risk-neutral expected profit; σ represents the profit deviation factor, and (1-σ)RN represents the virtual power plant's tolerance for profit decline. λ is the benchmark electricity price at time h, α is an uncertainty parameter representing the fluctuation range of the electricity price relative to the benchmark price; E (h) represents the day-ahead market energy price at time h; β* represents the risk-seeking target; RO represents the target profit level of the virtual power plant; RN represents the risk-neutral expected profit; σ represents the profit deviation factor, and (1+σ)RN represents the virtual power plant's expectation of profit growth.

[0041] Secondly, this application also provides an energy dispatching device for a virtual power plant, comprising:

[0042] The model building module is used to build a virtual power plant model that includes power generation equipment and various types of responsive loads. It takes maximizing the overall profit of the virtual power plant as the objective and constructs an objective function that includes the revenue of the virtual power plant participating in the energy market, the revenue of participating in the regulation market, and the operating costs of various types of responsive loads.

[0043] The model building module is also used to build the power demand model and corresponding first constraints of multiple types of responsive loads in the virtual power plant model, as well as to build the energy dispatch model and corresponding second constraints of the power generation equipment.

[0044] The model building module is used to build electricity profit models based on different risk propensities;

[0045] The energy dispatch module is used to determine the energy dispatch mode of the virtual power plant based on the objective function, the power demand model and the corresponding first constraint, and the energy dispatch model and the corresponding second constraint.

[0046] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0047] A virtual power plant model is established, which includes power generation equipment and various types of responsive loads. The overall profit of the virtual power plant is maximized as the objective. An objective function is constructed that includes the revenue of the virtual power plant participating in the energy market, the revenue of participating in the regulation market, and the operating costs of various types of responsive loads.

[0048] Establish power demand models and corresponding first constraints for various types of responsive loads in the virtual power plant model, and establish energy dispatch models and corresponding second constraints for power generation equipment;

[0049] Establish electricity profit models based on different risk propensities;

[0050] Based on the objective function, the power demand model and the corresponding first constraint, and the energy dispatch model and the corresponding second constraint, the energy dispatch mode of the virtual power plant is determined.

[0051] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0052] A virtual power plant model is established, which includes power generation equipment and various types of responsive loads. The overall profit of the virtual power plant is maximized as the objective. An objective function is constructed that includes the revenue of the virtual power plant participating in the energy market, the revenue of participating in the regulation market, and the operating costs of various types of responsive loads.

[0053] Establish power demand models and corresponding first constraints for various types of responsive loads in the virtual power plant model, and establish energy dispatch models and corresponding second constraints for power generation equipment;

[0054] Establish electricity profit models based on different risk propensities;

[0055] Based on the objective function, the power demand model and the corresponding first constraint, and the energy dispatch model and the corresponding second constraint, the energy dispatch mode of the virtual power plant is determined.

[0056] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0057] A virtual power plant model is established, which includes power generation equipment and various types of responsive loads. The overall profit of the virtual power plant is maximized as the objective. An objective function is constructed that includes the revenue of the virtual power plant participating in the energy market, the revenue of participating in the regulation market, and the operating costs of various types of responsive loads.

[0058] Establish power demand models and corresponding first constraints for various types of responsive loads in the virtual power plant model, and establish energy dispatch models and corresponding second constraints for power generation equipment;

[0059] Establish electricity profit models based on different risk propensities;

[0060] Based on the objective function, the power demand model and the corresponding first constraint, and the energy dispatch model and the corresponding second constraint, the energy dispatch mode of the virtual power plant is determined.

[0061] The aforementioned virtual power plant's energy dispatching methods, devices, computer equipment, computer-readable storage media, and computer program products maximize the virtual power plant's revenue in the energy and regulation markets through precise market participation strategies, while effectively reducing various operating costs. Through optimized dispatching, the virtual power plant can efficiently sell electricity during peak electricity price periods and rationally adjust generation and energy storage strategies during off-peak periods, thereby increasing energy market revenue. Furthermore, by providing regulation services such as frequency regulation and reserve capacity, the virtual power plant can obtain additional market revenue, further enhancing overall profits. Simultaneously, optimized dispatching reduces unnecessary generation and energy storage operations, lowering maintenance costs for generation equipment and charging / discharging costs for energy storage equipment. Secondly, the model strictly satisfies various constraints by establishing power demand models for multiple types of responsive loads and energy dispatching models for generation equipment. Load-side operational safety and user comfort are guaranteed; reasonable load reduction and transfer strategies avoid overload and underload situations while meeting user electricity needs. Generation-side operational safety is also guaranteed; by considering constraints such as the ramp rate and minimum start-up / shutdown time of generation equipment, excessive wear and tear and failures are avoided. Furthermore, by introducing profit models based on different risk propensities, virtual power plants can maintain high system reliability under uncertain conditions and reduce risks in extreme situations. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1This is an application environment diagram of the energy dispatching method for a virtual power plant in one embodiment;

[0064] Figure 2 This is a flowchart illustrating the energy dispatching method for a virtual power plant in one embodiment;

[0065] Figure 3 This is a structural block diagram of the energy dispatching device of a virtual power plant in one embodiment;

[0066] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0068] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0069] The energy dispatching method for virtual power plants provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server.

[0070] Server 104 is used to establish a virtual power plant model that includes power generation equipment and various types of responsive loads. The goal is to maximize the overall profit of the virtual power plant. An objective function is constructed that includes the revenue from the virtual power plant's participation in the energy market, the revenue from participating in the regulation market, and the operating costs of various responsive loads. Power demand models and corresponding first constraints for various types of responsive loads in the virtual power plant model are established, as well as an energy dispatch model for the power generation equipment and corresponding second constraints. Electricity profit models based on different risk propensities are also established. Server 104 is used to control terminal 102 to determine the energy dispatch method of the virtual power plant based on the objective function, the power demand model and corresponding first constraints, and the energy dispatch model and corresponding second constraints.

[0071] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. The server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0072] In one exemplary embodiment, such as Figure 2 As shown, an energy dispatching method for a virtual power plant is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S202 to S208. Wherein:

[0073] Step S202: Establish a virtual power plant model that includes power generation equipment and various types of responsive loads. With the goal of maximizing the overall profit of the virtual power plant, construct an objective function that includes the revenue of the virtual power plant participating in the energy market, the revenue of participating in the regulation market, and the operating costs of various types of responsive loads.

[0074] Specifically, power generation equipment includes wind turbines, diesel generators, and solar panels, which provide electricity. Multi-type responsive loads include residential, commercial, and industrial loads, which can be regulated through demand response mechanisms, such as price signals or incentives, to guide users to adjust their electricity consumption behavior.

[0075] The model aims to maximize the overall profit of the virtual power plant, which consists of several components: Energy market revenue: revenue obtained by selling electricity in the energy market; Regulation market revenue: revenue obtained by providing regulation services such as frequency regulation and reserve capacity; Operating costs: including the operating costs of generation equipment, the charging and discharging costs of energy storage equipment, and the regulation costs of responsive loads.

[0076] Step S204: Establish the power demand model and corresponding first constraint conditions for multiple types of responsive loads in the virtual power plant model, and establish the energy dispatch model and corresponding second constraint conditions for the power generation equipment.

[0077] Specifically, when constructing a virtual power plant model, it is necessary to establish power demand models for multiple types of responsive loads and energy dispatch models for power generation equipment, and set corresponding constraints for each model. These models and constraints together form the basis for the optimized dispatch of the virtual power plant, ensuring that the virtual power plant can operate safely and reliably while pursuing profit maximization and meeting user needs.

[0078] Power demand models mathematically describe the electricity consumption behavior and characteristics of various types of responsive loads (such as residential, commercial, and industrial loads). These models typically include: Load characteristics: describing the load's power demand, consumption patterns (such as peak and off-peak hours), and adjustable range; Demand response mechanisms: describing how the load responds to price signals or incentives, such as by reducing or shifting electricity consumption in response to price changes; and User behavior models: considering user comfort and behavioral habits to ensure that responding to demand does not excessively disrupt users' normal lives or production activities.

[0079] The first constraint is the limitation in the power demand model, ensuring the safe operation of the load and user comfort. These constraints include: Power upper and lower limits: The load's power demand cannot exceed its maximum value or fall below its minimum value. Duration constraints: Some loads may need to operate continuously for a certain period of time, such as industrial production lines. User comfort constraints: For example, the temperature regulation range of an air conditioning load cannot exceed the user's acceptable range. Response rate constraints: The rate of change of the load's power cannot exceed its physical limits to avoid equipment damage or user discomfort.

[0080] Energy dispatch models mathematically describe the operating characteristics of power generation equipment (such as wind turbines, solar panels, and diesel generators). These models typically include: Power generation characteristics: describing the power output range, efficiency, start-up and shutdown times of the power generation equipment. Energy storage characteristics: if the power generation equipment includes an energy storage system, the charging and discharging characteristics and capacity limitations of the energy storage system must also be described. Market participation strategies: describing how the power generation equipment participates in and regulates the energy market, for example, by adjusting power generation in response to market price signals.

[0081] The second constraint is the limiting condition in the energy dispatch model, ensuring the safe operation of power generation equipment and compliance with market rules. These constraints include: Power limits: The power output of power generation equipment cannot exceed its maximum value or fall below its minimum value. Ramp-up rate: The rate of power change of power generation equipment cannot exceed its physical limits to avoid equipment damage. Minimum start-stop time: Some power generation equipment (such as diesel generators) needs to meet minimum start-stop time requirements to avoid damage caused by frequent start-stop operations. Market rule constraints: The operation of power generation equipment must comply with the rules of the energy market and regulatory market, such as price signals and trading rules.

[0082] Step S206: Establish an electricity profit model based on different risk propensities.

[0083] Specifically, risk propensity refers to the degree to which decision-makers accept risk, and is usually divided into risk-neutral, risk-seeking, and risk-averse.

[0084] Risk-neutral refers to decision-makers focusing solely on expected profit, disregarding risk. In this case, the model maximizes only expected profit. Risk-averse refers to decision-makers being cautious about risk, willing to accept lower expected profits in exchange for lower risk. In this case, the model introduces risk measures, such as Conditional Value at Risk (CVaR) or variance, to control risk. Risk-seeking refers to decision-makers willing to take on higher risks in exchange for higher expected profits. In this case, the model may relax risk controls, pursuing higher potential returns.

[0085] The electricity profit model includes an objective function, constraints, and uncertainty handling. The objective function is the core of the electricity profit model and is typically expressed as maximizing profit. Constraints include power balance constraints, equipment operation constraints, market rule constraints, and responsive load constraints.

[0086] Among these, electricity profit models typically need to handle uncertainties, such as:

[0087] Uncertainties in wind speed and solar energy: addressed through predictive models and scene generation techniques.

[0088] Market price uncertainty: addressed through predictive models and risk measures such as Conditional Value at Risk (CVaR).

[0089] Uncertainty in load forecasting: addressed through forecasting models and demand response mechanisms.

[0090] Step S208: Determine the energy dispatch mode of the virtual power plant based on the objective function, power demand model and corresponding first constraint, and energy dispatch model and corresponding second constraint.

[0091] Specifically, based on the aforementioned objective function, power demand model and its first constraint, and energy dispatch model and its second constraint, the energy dispatch method for the virtual power plant is determined through an optimization algorithm. The specific steps are as follows:

[0092] The objective function, power demand model and its constraints, and energy dispatch model and its constraints are integrated into a unified optimization model. Based on the model's complexity, an appropriate optimization algorithm is selected, such as linear programming (LP), mixed-integer linear programming (MILP), nonlinear programming (NLP), or mixed-integer nonlinear programming (MINLP). The selected optimization algorithm is used to solve the optimization model to obtain the optimal dispatch strategy. This includes: the optimal output of each generating unit at each time step, the optimal charging / discharging rate of each energy storage unit at each time step, and the optimal adjustment amount of each responsive load at each time step. The solution results are verified to ensure that all constraints are met; adjustments are made if necessary to ensure the model's feasibility and practicality.

[0093] The aforementioned energy dispatch method for virtual power plants maximizes their revenue in both the energy and regulation markets through precise market participation strategies, while effectively reducing various operating costs. Through optimized dispatch, virtual power plants can efficiently sell electricity during peak electricity price periods and rationally adjust generation and storage strategies during off-peak periods, thereby increasing energy market revenue. Furthermore, by providing regulation services such as frequency regulation and reserve capacity, virtual power plants can obtain additional market revenue, further enhancing overall profits. Simultaneously, optimized dispatch reduces unnecessary generation and storage operations, lowering maintenance costs for power generation equipment and charging / discharging costs for energy storage equipment. Secondly, the model strictly satisfies various constraints by establishing power demand models for multiple types of responsive loads and energy dispatch models for power generation equipment. Load-side operational safety and user comfort are guaranteed; reasonable load reduction and transfer strategies avoid overload and underload situations while meeting user electricity needs. Generation-side operational safety is also guaranteed; by considering constraints such as the ramp rate and minimum start-stop time of power generation equipment, excessive wear and tear and failures are avoided. Furthermore, by introducing profit models based on different risk propensities, virtual power plants can maintain high system reliability under uncertain conditions and reduce risks in extreme situations.

[0094] In one embodiment, an objective function is constructed that includes the revenue from virtual power plants participating in the energy market, the revenue from participating in the regulation market, and the operating costs of various responsive loads, including:

[0095] The functional relationship of the objective function is:

[0096]

[0097] In the formula, maxprofit represents profit maximization; ReDA E (h,s) represents the revenue of a virtual power plant participating in the energy market; ReDA RS (h,s) represents the revenue of the virtual power plant participating in the market regulation; Co SDG(h,s) represents the operating cost of the standby power generation equipment in the virtual power plant; Co DR (h,s) represents the operating costs of various responsive loads in the virtual power plant; π s Let be the probability of scenario s;

[0098] The functional relationship between the returns of virtual power plants participating in the energy market is as follows:

[0099] ReDA E (h,s)=PDA(h,s)·λ E (h);

[0100] In the formula, PDA(h,s) represents the energy output sold by the virtual power plant in the day-ahead market at time h and scenario s; λ E (h) represents the day-ahead market energy price at time h;

[0101] The functional relationship between the returns of virtual power plants participating in market regulation is as follows:

[0102] ReDA RS (h,s)=RSDA(h,s)·λ RS (h,s)+(Delreg up (h,s)-Delreg down (h,s))·RSDA(h,s)·λ spot (h);

[0103]

[0104] In the formula, λ E (h) represents the day-ahead market energy price at time h; RSDA(h,s) represents the regulating service power sold by the virtual power plant in the day-ahead market at time h and under scenario s; λ RS (h,s) represents the day-ahead market-regulated service price at time h and scenario s; Delreg up (h,s) represents the upward adjustment request issued by the system operator at time h and in scenario s; Delreg down (h,s) represents the downward adjustment request issued by the system operator at time h and in scenario s; λ spot (h) represents the spot market price at time h; p1 and p2 are random parameters used to simulate the fluctuations in the spot market price.

[0105] The functional relationship between the operating costs of various responsive loads is as follows:

[0106]

[0107] In the formula, j is the consumer serial number; N l For the number of steps in the price-quantity quote package; λ is the price for the j-th consumer in the l-th step of the energy type demand response project; pl(j) is the load reduction accepted by the j-th consumer in the l-th step; RSDR (j,h) represents the price paid by the j-th consumer at time h in the demand response project for the service type of adjustment; RSDR(j,h,s) represents the power of the adjustment service provided by the j-th consumer at time h and in scenario s.

[0108] In this embodiment, a precise market participation strategy maximizes the revenue of the virtual power plant in both the energy and regulation markets, while effectively reducing various operating costs. Optimized scheduling enables the virtual power plant to efficiently sell electricity during peak electricity price periods and rationally adjust generation and storage strategies during off-peak periods, thereby increasing energy market revenue. Furthermore, by providing regulation services such as frequency regulation and reserve capacity, the virtual power plant can obtain additional market revenue. By optimizing the operating costs of responsive loads, the virtual power plant can fully utilize the flexibility resources on the load side. The demand response mechanism guides users to reduce electricity consumption during peak electricity price periods and increase electricity consumption during off-peak periods, thereby improving the load-side responsiveness and enhancing the system's flexibility and adaptability. By introducing scenario probabilities and stochastic parameters, the model can effectively handle uncertainties such as market price fluctuations, helping the virtual power plant make scientific and rational decisions in complex market environments and reducing operational risks.

[0109] In one exemplary embodiment, the functional relationship of the operating cost of the standby power generation equipment is as follows:

[0110]

[0111] In the formula, The startup and power generation costs of backup power generation equipment; The carbon dioxide emission penalty cost of the standby power generation equipment; a, b, and c are the production cost coefficients of the standby power generation equipment; P SDG (h,s) represents the total power generation of the backup power generation equipment at time h and in scenario s; U SDG (h,s) are binary variables representing the start-up and shutdown states of the standby power generation equipment; SUC is the start-up cost of the standby power generation equipment; U on SDG (h,s) is a binary variable representing the startup state of the backup power generation equipment at time h and in scenario s; CO2 SDG λ represents the carbon dioxide emissions per kilowatt-hour of electricity generated by the standby power generation equipment. co2 The penalty price for carbon dioxide emissions.

[0112] Specifically, by accurately modeling the start-up and generation costs of backup power generation equipment, virtual power plants can optimize the start-up and shutdown strategies of backup equipment, reducing unnecessary operating costs. Simultaneously, by rationally allocating the generation capacity of backup equipment, it ensures that power demand is met while minimizing generation costs, thereby improving overall economic efficiency. Introducing carbon dioxide emission penalty costs incentivizes virtual power plants to prioritize environmental protection during operation. Optimized dispatch reduces carbon dioxide emissions from backup power generation equipment, lowering the penalty costs associated with carbon emissions and enhancing the environmental friendliness and sustainability of the virtual power plant. The start-up and shutdown status of backup power generation equipment is modeled using binary variables, ensuring rapid startup when needed and providing reliable backup power. Furthermore, optimized dispatch strategies improve the operational flexibility of backup equipment, enabling it to better cope with fluctuations and uncertainties in power demand.

[0113] In an exemplary embodiment, the power demand model for multiple types of responsive loads and the functional relationship of the corresponding first constraints include:

[0114]

[0115] In the formula, pl(j) is the load reduction amount accepted by the j-th consumer in step l; Pl(j) is the maximum load reduction amount of the j-th consumer in step l; PDR(j,h,s) is the energy power provided by the j-th consumer through demand response at time h and scenario s; RSDR(j,h,s) is the regulation service power provided by the j-th consumer at time h and scenario s; and PMax(j) is the maximum demand response potential of the j-th consumer.

[0116] In this embodiment,

[0117] In an exemplary embodiment, the functional relationship between the energy dispatch model of the power generation equipment and the corresponding second constraint includes:

[0118]

[0119] RS SDG (h,s)≤P SDG (h,s);

[0120] In the formula, P SDG (h,s) represents the energy dispatch power of the standby power equipment; PWT(h,s) is the output power of wind power at time h and scenario s; PDR(j,h,s) is the energy power provided by the j-th consumer through demand response at time h and scenario s; PDA(h,s) is the energy power sold by the virtual power plant in the day-ahead market at time h and scenario s; Delreg up (h,s) represents the upward adjustment request issued by the system operator at time h and in scenario s; Delregdown (h,s) represents the downward adjustment request issued by the system operator at time h and scenario s; RSDA(h,s) represents the adjustment service power sold by the virtual power plant in the day-ahead market at time h and scenario s; RS SDG (h,s) is the regulation service power provided by the standby power generation equipment at time h and scenario s; RSDR(j,h,s) is the regulation service power provided by the j-th consumer at time h and scenario s.

[0121] In this embodiment, by modeling the load reduction amounts and maximum reduction amounts for each consumer at different steps, the virtual power plant can accurately schedule responsive loads, improving the flexibility and adjustment capabilities on the load side. This allows the virtual power plant to adjust loads more flexibly in the face of electricity demand fluctuations, reducing reliance on traditional power generation equipment. Constraints ensure that each consumer's load reduction amount does not exceed its maximum load reduction amount, while also considering the user's demand response potential in different scenarios. This not only improves the scheduling flexibility of the virtual power plant but also guarantees users' electricity needs and comfort, avoiding disruption to users' normal lives and production activities due to excessive load reduction. Through precise modeling and constraints, the virtual power plant can ensure that the provision of load reduction and adjustment services is within a safe and reliable range at any given time, enhancing the overall operational reliability of the virtual power plant and reducing system failures that may result from improper load management.

[0122] In one exemplary embodiment, the risk orientation types include risk-averse and risk-seeking;

[0123] The robustness function of a risk-averse virtual power plant includes the following functional relationships:

[0124]

[0125] The opportunity function of a risk-seeking virtual power plant includes the following functional relationships:

[0126]

[0127] In the formula, α* represents a risk-averse target; P represents power; π s The probability of scenario s; ReDA E (h,s) represents the revenue of a virtual power plant participating in the energy market; ReDA RS (h,s) represents the revenue of the virtual power plant participating in the market regulation; Co SDG (h,s) represents the operating cost of the standby power generation equipment in the virtual power plant; Co DR(h,s) represents the operating costs of various responsive loads of the virtual power plant; RC represents the minimum profit level set by the virtual power plant; RN represents the risk-neutral expected profit; σ represents the profit deviation factor, and (1-σ)RN represents the virtual power plant's tolerance for profit decline. λ is the benchmark electricity price at time h, α is an uncertainty parameter representing the fluctuation range of the electricity price relative to the benchmark price; E (h) represents the day-ahead market energy price at time h; β* represents the risk-seeking target; RO represents the target profit level of the virtual power plant; RN represents the risk-neutral expected profit; σ represents the profit deviation factor, and (1+σ)RN represents the virtual power plant's expectation of profit growth.

[0128] In this embodiment, by defining risk-averse and risk-seeking objective functions, virtual power plants can choose appropriate dispatch strategies based on their own risk preferences. The risk-averse objective function ensures the virtual power plant can achieve robust operation under uncertain conditions by setting a minimum profit level and a profit deviation factor. The risk-seeking objective function, on the other hand, incentivizes the virtual power plant to pursue higher returns during market fluctuations by setting a target profit level and expected profit growth.

[0129] Among them, the risk-seeking objective function allows virtual power plants to obtain higher profits by taking on certain risks when market conditions are favorable. This strategy helps virtual power plants seize opportunities and maximize profits in volatile market environments. Conversely, the risk-averse objective function, by setting a minimum profit level and a profit deviation factor, ensures that virtual power plants can still operate robustly under uncertain conditions. This strategy helps virtual power plants maintain stable returns during market fluctuations and reduces the risks arising from market uncertainty.

[0130] By introducing scenario probability and uncertainty parameters, the model can effectively handle uncertainties such as market price fluctuations, helping virtual power plants make scientific and rational decisions in complex market environments.

[0131] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0132] Based on the same inventive concept, this application also provides an energy dispatching device for a virtual power plant to implement the energy dispatching method for the virtual power plant described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of the one or more embodiments of the energy dispatching device for virtual power plants provided below can be found in the limitations of the energy dispatching method for virtual power plants described above, and will not be repeated here.

[0133] In one exemplary embodiment, such as Figure 3 As shown, an energy dispatching device for a virtual power plant is provided, comprising:

[0134] The model building module 302 is used to build a virtual power plant model that includes power generation equipment and multiple types of responsive loads. It takes maximizing the overall profit of the virtual power plant as the objective and constructs an objective function that includes the revenue of the virtual power plant participating in the energy market, the revenue of participating in the regulation market, and the operating costs of various types of responsive loads.

[0135] The model building module 302 is also used to build the power demand model and corresponding first constraint conditions for multiple types of responsive loads in the virtual power plant model, as well as to build the energy dispatch model and corresponding second constraint conditions for the power generation equipment.

[0136] The model building module 302 is also used to build electricity profit models based on different risk propensities;

[0137] The energy dispatch module 304 is used to determine the energy dispatch mode of the virtual power plant based on the objective function, the power demand model and the corresponding first constraint, and the energy dispatch model and the corresponding second constraint.

[0138] In an exemplary embodiment, the functional relationship of the objective function is as follows:

[0139]

[0140] In the formula, maxprofit represents profit maximization; ReDA E (h,s) represents the revenue of a virtual power plant participating in the energy market; ReDA RS (h,s) represents the revenue of the virtual power plant participating in the market regulation; Co SDG (h,s) represents the operating cost of the standby power generation equipment in the virtual power plant; Co DR (h,s) represents the operating costs of various responsive loads in the virtual power plant; π s Let be the probability of scenario s;

[0141] The functional relationship between the returns of virtual power plants participating in the energy market is as follows:

[0142] ReDAE (h,s)=PDA(h,s)·λ E (h);

[0143] In the formula, PDA(h,s) represents the energy output sold by the virtual power plant in the day-ahead market at time h and scenario s; λ E (h) represents the day-ahead market energy price at time h;

[0144] The functional relationship between the returns of virtual power plants participating in market regulation is as follows:

[0145] ReDA RS (h,s)=RSDA(h,s)·λ RS (h,s)+(Delreg up (h,s)-Delreg down (h,s))·RSDA(h,s)·λ spot (h);

[0146]

[0147] In the formula, λ E (h) represents the day-ahead market energy price at time h; RSDA(h,s) represents the regulating service power sold by the virtual power plant in the day-ahead market at time h and under scenario s; λ RS (h,s) represents the day-ahead market-regulated service price at time h and scenario s; Delreg up (h,s) represents the upward adjustment request issued by the system operator at time h and in scenario s; Delreg down (h,s) represents the downward adjustment request issued by the system operator at time h and in scenario s; λ spot (h) represents the spot market price at time h; p1 and p2 are random parameters used to simulate the fluctuations in the spot market price.

[0148] The functional relationship between the operating costs of various responsive loads is as follows:

[0149]

[0150] In the formula, j is the consumer serial number; N l For the number of steps in the price-quantity quote package; λ is the price for the j-th consumer in the l-th step of the energy type demand response project; pl(j) is the load reduction accepted by the j-th consumer in the l-th step; RSDR (j,h) represents the price paid by the j-th consumer at time h in the demand response project for the service type of adjustment; RSDR(j,h,s) represents the power of the adjustment service provided by the j-th consumer at time h and in scenario s.

[0151] In one exemplary embodiment, the functional relationship of the operating cost of the standby power generation equipment is as follows:

[0152]

[0153] In the formula, The startup and power generation costs of backup power generation equipment; The carbon dioxide emission penalty cost of the standby power generation equipment; a, b, and c are the production cost coefficients of the standby power generation equipment; P SDG (h,s) represents the total power generation of the backup power generation equipment at time h and in scenario s; U SDG (h,s) are binary variables representing the start-up and shutdown states of the standby power generation equipment; SUC is the start-up cost of the standby power generation equipment; U on SDG (h,s) is a binary variable representing the startup state of the backup power generation equipment at time h and in scenario s; CO2 SDG λ represents the carbon dioxide emissions per kilowatt-hour of electricity generated by the standby power generation equipment. co2 The penalty price for carbon dioxide emissions.

[0154] In an exemplary embodiment, the power demand model for multiple types of responsive loads and the functional relationship of the corresponding first constraints include:

[0155]

[0156] In the formula, pl(j) is the load reduction amount accepted by the j-th consumer in step l; Pl(j) is the maximum load reduction amount of the j-th consumer in step l; PDR(j,h,s) is the energy power provided by the j-th consumer through demand response at time h and scenario s; RSDR(j,h,s) is the regulation service power provided by the j-th consumer at time h and scenario s; and PMax(j) is the maximum demand response potential of the j-th consumer.

[0157] In an exemplary embodiment, the functional relationship between the energy dispatch model of the power generation equipment and the corresponding second constraint includes:

[0158]

[0159] RS SDG (h,s)≤P SDG (h,s);

[0160] In the formula, P SDG(h,s) represents the energy dispatch power of the standby power equipment; PWT(h,s) is the output power of wind power at time h and scenario s; PDR(j,h,s) is the energy power provided by the j-th consumer through demand response at time h and scenario s; PDA(h,s) is the energy power sold by the virtual power plant in the day-ahead market at time h and scenario s; Delreg up (h,s) represents the upward adjustment request issued by the system operator at time h and in scenario s; Delreg down (h,s) represents the downward adjustment request issued by the system operator at time h and scenario s; RSDA(h,s) represents the adjustment service power sold by the virtual power plant in the day-ahead market at time h and scenario s; RS SDG (h,s) is the regulation service power provided by the standby power generation equipment at time h and scenario s; RSDR(j,h,s) is the regulation service power provided by the j-th consumer at time h and scenario s.

[0161] In one exemplary embodiment, the risk orientation types include risk-averse and risk-seeking;

[0162] The robustness function of a risk-averse virtual power plant includes the following functional relationships:

[0163]

[0164] The opportunity function of a risk-seeking virtual power plant includes the following functional relationships:

[0165]

[0166] In the formula, α* represents a risk-averse target; P represents power; π s The probability of scenario s; ReDA E (h,s) represents the revenue of a virtual power plant participating in the energy market; ReDA RS (h,s) represents the revenue of the virtual power plant participating in the market regulation; Co SDG (h,s) represents the operating cost of the standby power generation equipment in the virtual power plant; Co DR (h,s) represents the operating costs of various responsive loads of the virtual power plant; RC represents the minimum profit level set by the virtual power plant; RN represents the risk-neutral expected profit; σ represents the profit deviation factor, and (1-σ)RN represents the virtual power plant's tolerance for profit decline. λ is the benchmark electricity price at time h, α is an uncertainty parameter representing the fluctuation range of the electricity price relative to the benchmark price; E(h) represents the day-ahead market energy price at time h; β* represents the risk-seeking target; RO represents the target profit level of the virtual power plant; RN represents the risk-neutral expected profit; σ represents the profit deviation factor, and (1+σ)RN represents the virtual power plant's expectation of profit growth.

[0167] The various modules in the energy dispatching device of the aforementioned virtual power plant can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0168] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements an energy dispatching method for a virtual power plant.

[0169] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0170] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0171] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0172] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0173] 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 used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0174] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0175] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0176] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An energy scheduling method of a virtual power plant, characterized by, The method comprises: establishing a virtual power plant model comprising power generation equipment and multiple types of responsive loads, taking maximizing the overall profit of the virtual power plant as a target, and constructing a target function comprising the income of the virtual power plant participating in an energy market, the income of the virtual power plant participating in a regulation market, and the operation cost of each type of responsive load; establishing a power demand model of the multiple types of responsive loads in the virtual power plant model and corresponding first constraint conditions, and establishing an energy scheduling model of the power generation equipment and corresponding second constraint conditions; establishing an electricity profit model based on different risk inclinations; determining an energy scheduling mode of the virtual power plant according to the target function, the power demand model and the corresponding first constraint conditions, and the energy scheduling model and the corresponding second constraint conditions.

2. The method of claim 1, wherein, The target function comprises the income of the virtual power plant participating in the energy market, the income of the virtual power plant participating in the regulation market, and the operation cost of each type of responsive load. The function relationship of the target function is: where maxprofit denotes the profit maximization; ReDA E (h,s) is the revenue of the virtual power plant participating in the energy market; ReDA RS (h,s) is the revenue of the virtual power plant participating in the regulation market; Co SDG (h,s) is the operation cost of the standby power generation equipment in the virtual power plant; Co DR (h,s) is the operation cost of various responsive loads of the virtual power plant; π s is the probability of scenario s; The function relationship of the income of the virtual power plant participating in the energy market is: ReDA E (h,s) = PDA(h,s) · λ E (h); In the formula, PDA(h,s) is the energy power sold by the virtual power plant in the day-ahead market at time h and in scenario s; λ E (h) is the day-ahead market energy price at time h. The function relationship of the income of the virtual power plant participating in the regulation market is: ReDA RS (h,s) = RSDA(h,s) · λ RS (h,s) + Delreg up (h,s) - Delreg down (h,s) · RSDA(h,s) · λ spot (h); where λ E (h) is the day-ahead market energy price at time h; RSDA(h, s) is the virtual power plant’s (VPP’s) adjusted service power sold in the day-ahead market at time h and scenario s; λ RS (h, s) is the day-ahead market adjusted service price at time h and scenario s; Delreg up (h, s) is the up-regulation request issued by the system operator at time h and scenario s; Delreg down (h, s) is the down-regulation request issued by the system operator at time h and scenario s; λ spot (h) is the spot market price at time h; p1 and p2 are random parameters used to simulate the fluctuation of the spot market price; The function relationship of the operation cost of each type of responsive load is: where j is the consumer index; N l is the step number in the price-quantity offer package; is the price of the jth consumer at the lth step in the energy type demand response program; pl(j) is the load curtailment accepted by the jth consumer at the lth step; λ RSDR (j, h) is the price of the jth consumer at time h in the regulation service type demand response program; RSDR(j, h, s) is the regulation service power provided by the jth consumer at time h under scenario s.

3. The method of claim 2, wherein, The function relationship of the operation cost of the standby power generation equipment is: wherein, is the start-up and power generation cost of the backup power generation equipment; is the carbon dioxide emission penalty cost of the backup power generation equipment;a, b, c are the production cost coefficients of the backup power generation equipment;P SDG (h, s) is the total power generation of the backup power generation equipment at time h and scenario s;U SDG (h, s) is a binary variable of the start-stop state of the backup power generation equipment;SUCis the start-up cost of the backup power generation equipment;U on SDG (h, s) is a binary variable of the start-stop state of the backup power generation equipment at time h and scenario s;CO2 SDG is the carbon dioxide emission amount corresponding to each kilowatt-hour of power generation of the backup power generation equipment;λ co2 is the penalty price of carbon dioxide emission.

4. The method of claim 1, wherein, The function relationship of the power demand model of the multiple types of responsive loads and the corresponding first constraint conditions comprises: 0≤pl(j)≤Pl(j),l=1 0 < pl(j) < Pl(j) - Pl(j-1), l = 2, 3,..., N l PDR(j,h,s)+RSDR(j,h,s)≤PMax(j) RSDR(j,h,s)≤PDR(j,h,s); In the formula, pl(j) is the load reduction amount accepted by the jth consumer at the lth step, Pl(j) is the maximum load reduction amount of the jth consumer at the lth step, PDR(j,h,s) is the energy power provided by the jth consumer through demand response at h time and in scenario s, RSDR(j,h,s) is the regulation service power provided by the jth consumer at h time and in scenario s, and PMax(j) is the maximum demand response potential of the jth consumer.

5. The method of claim 1, wherein, The function relationship of the energy scheduling model of the power generation equipment and the corresponding second constraint conditions comprises: RS SDG (h,s)≤P SDG (h,s) where P SDG (h,s) is the energy power of the energy dispatch of the backup power equipment; PWT(h,s) is the output of the wind power at time h and scenario s; PDR(j,h,s) is the energy power provided by the jth consumer through demand response at time h and scenario s; PDA(h,s) is the energy power sold by the virtual power plant in the day-ahead market at time h and scenario s; Delreg up (h,s) is the up-regulation adjustment request issued by the system operator at time h and scenario s; Delreg down (h,s) is the down-regulation adjustment request issued by the system operator at time h and scenario s; RSDA(h,s) is the adjustment service power sold by the virtual power plant in the day-ahead market at time h and scenario s; RS SDG (h,s) is the adjustment service power provided by the backup power equipment at time h and scenario s; RSDR(j,h,s) is the adjustment service power provided by the jth consumer at time h and scenario s.

6. The method of claim 1, wherein, The type of the risk inclination comprises risk-averse type and risk-pursuit type. The function relationship of the robustness function of the virtual power plant of the risk-averse type comprises: α * (P; RC) = max α s.t. The function relationship of the opportunity function of the virtual power plant of the risk-pursuit type comprises: β * (P; RO) = min α s.t. where α* is the target of risk-averse type; P is power; π s P is the probability of scenario s; ReDA E (h, s) is the revenue of the virtual power plant participating in the energy market; ReDA RS (h, s) is the revenue of the virtual power plant participating in the regulation market; Co SDG (h, s) is the operating cost of the standby power generation equipment in the virtual power plant; Co DR (h, s) is the operating cost of various responsive loads in the virtual power plant; RC is the minimum profit level set by the virtual power plant; RN is the risk-neutral expected profit; σ is the profit deviation factor, (1-σ)RN represents the tolerance of the virtual power plant to profit decline; is the benchmark electricity price at time h, α is the uncertainty parameter, representing the fluctuation range of the electricity price relative to the benchmark electricity price; λ E (h) is the day-ahead market energy price at time h; β* is the target of risk-seeking type; RO is the target profit level of the virtual power plant; RN is the risk-neutral expected profit; σ is the profit deviation factor, (1+σ)RN represents the expectation of the virtual power plant to profit growth.

7. An energy scheduling device of a virtual power plant, characterized by, The device comprises: a model establishing module configured to establish a virtual power plant model comprising power generation equipment and multiple types of responsive loads, take maximizing the overall profit of the virtual power plant as a target, and construct a target function comprising the income of the virtual power plant participating in an energy market, the income of the virtual power plant participating in a regulation market, and the operation cost of each type of responsive load; the model establishing module is further configured to establish a power demand model of the multiple types of responsive loads in the virtual power plant model and corresponding first constraint conditions, and establish an energy scheduling model of the power generation equipment and corresponding second constraint conditions; the model establishing module is configured to establish an electricity profit model based on different risk inclinations; the model establishing module is configured to determine an energy scheduling mode of the virtual power plant according to the target function, the power demand model and the corresponding first constraint conditions, and the energy scheduling model and the corresponding second constraint conditions. An energy dispatching module is configured to determine an energy dispatching mode of the virtual power plant according to the target function, the power demand model and corresponding first constraint conditions, and the energy dispatching model and corresponding second constraint conditions.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 6.

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

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

Images