Virtual power plant operation method and device based on power distribution system constraint

Abstract

The invention discloses a virtual power plant operation method and device based on power distribution system constraints. The method comprises the following steps: receiving a first power distribution system constraint issued by a power distribution system operator; acquiring historical power distribution system constraints issued by a power distribution system operator in a historical time period, constraint information of the power distribution system and power output prediction data of the plurality of distributed energy resources; processing the historical power distribution system constraint, the constraint information and the power output prediction data by using a constraint prediction model to obtain a second power distribution system constraint; adjusting the initial resource scheduling strategy according to the second power distribution system constraint to obtain a first target resource scheduling strategy; and scheduling the plurality of distributed energy resources according to the first target resource scheduling strategy. The technical problem that the operation strategy of the virtual power plant is limited when the operation strategy of the virtual power plant is formulated due to the fact that the operation strategy of the virtual power plant depends on the power distribution system constraint issued by the power distribution system operator in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual power plants, and in particular to a method and device for operating a virtual power plant based on power distribution system constraints. Background Art

[0002] With the decarbonization, decentralization and digitalization of the power system, the transition from centralized to distributed power systems has led to the widespread dissemination of distributed energy resources in the distribution network. Virtual power plants, as an aggregation of distributed energy power traded in the power market using information and communication technology, have attracted increasing attention. However, virtual power plants that operate only based on economic feasibility may cause distribution system stability issues such as voltage violations and power congestion.

[0003] Existing virtual power plant (VPP) operation strategies are highly dependent on the distribution system constraints (DSC) information provided by the distribution system operator (DSO), which limits the flexibility and profitability of virtual power plants in the face of uncertainty. Virtual power plants are usually in a passive state, relying on the distribution system constraint information provided by the distribution system operator, rather than actively predicting the uncertainty of distribution system constraints and formulating operation strategies accordingly.

[0004] With regard to the problem in the above-mentioned related technologies that the operation strategy of the virtual power plant depends on the distribution system constraints issued by the distribution system operator, which leads to the virtual power plant being relatively restricted in formulating its operation strategy, no effective solution has been proposed so far. Summary of the invention

[0005] An embodiment of the present invention provides a virtual power plant operation method and device based on distribution system constraints, so as to at least solve the technical problem in the related art that the operation strategy of the virtual power plant depends on the distribution system constraints issued by the distribution system operator, which leads to the virtual power plant being relatively restricted in formulating operation strategies.

[0006] According to one aspect of an embodiment of the present invention, a method for operating a virtual power plant based on distribution system constraints is provided, comprising: receiving a first distribution system constraint issued by a distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to an initial resource scheduling strategy sent by the virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of the multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; obtaining historical distribution system constraints issued by the distribution system operator in a historical time period, constraint information of the distribution system, and power output prediction data of the multiple distributed energy resources; using a constraint prediction model to process the historical distribution system constraints, the constraint information, and the power output prediction data to obtain a second distribution system constraint, wherein the constraint prediction model is a set of training sets using multiple training sets. The training data is obtained by training in a machine learning manner, and each of the multiple groups of training data includes: sample input data, sample second distribution system constraints corresponding to the sample input data, and the sample input data includes: sample historical distribution system constraints, sample constraint information and sample power output prediction data; the initial resource scheduling strategy is adjusted according to the second distribution system constraints to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and does not exceed the second power constraint range under the condition that the power output value satisfies the predetermined range, the first power constraint range is the range of the total output power constrained in the first distribution system constraints, and the second power constraint range is the range of the total output power constrained in the second distribution system constraints; the multiple distributed energy resources are scheduled according to the first target resource scheduling strategy.

[0007] Optionally, before receiving the first distribution system constraint issued by the distribution system operator, the virtual power plant operation method based on the distribution system constraint also includes: evaluating the current status, available capacity and expected power output data of multiple distributed energy resources to obtain evaluation results; generating the initial resource scheduling strategy for scheduling multiple distributed energy resources based on the evaluation results; and sending the initial resource scheduling strategy to the distribution system operator.

[0008] Optionally, before sending the initial resource scheduling strategy to the distribution system operator, the virtual power plant operation method based on distribution system constraints also includes: establishing a collaborative operation framework with the distribution system operator to enable information exchange with the distribution system operator through the collaborative operation framework.

[0009] Optionally, the virtual power plant operation method based on distribution system constraints also includes: receiving penalty rules issued by the distribution system operator while receiving the first distribution system constraints issued by the distribution system operator, wherein the penalty rules are used to predict penalty penalties when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range.

[0010] Optionally, the virtual power plant operation method based on distribution system constraints also includes: constructing an operation model, wherein the operation model is used to adjust the scheduling of multiple distributed energy resources; solving the operation model using an optimization algorithm to obtain an optimal solution to the operation model, wherein the optimal solution is a solution to the objective function in the operation model when the profit of the virtual power plant is maximized; under the condition of satisfying the first distribution system constraint and the second distribution system constraint, adjusting the initial resource scheduling strategy according to the optimal solution to obtain a second target resource scheduling strategy; and scheduling multiple distributed energy resources according to the second target resource scheduling strategy.

[0011] Optionally, constructing an operation model includes: obtaining current electricity sales revenue, loss cost and penalty fine, wherein the electricity sales revenue is the difference between the revenue of transmitting electricity to the distribution system and the expenditure of purchasing the electricity from the distribution system, the loss cost is the cost of loss of multiple distributed energy resources, and the penalty fine is a penalty predicted according to a penalty rule when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range, and the penalty rule is a rule issued by the distribution system operator; based on the electricity sales revenue, the loss cost and the penalty fine, the objective function is established with profit maximization as the goal, wherein the expression of the objective function is: t represents the number of the running time, T represents the total number of the running time, w represents the number of the running scenario, W represents the total number of the running scenarios, π w represents the scene probability, C sell，t represents the electricity sales revenue, C ESS，w，t represents the loss cost, C penalty，w，t Representing the penalty fine; constraining the output state, charging state, discharging state, stop state and charge state of the energy storage system during charging and discharging, respectively, to obtain multiple constraint conditions, wherein the energy storage system is one of the multiple distributed energy resources; constructing an operation model according to the objective function and the multiple constraint conditions.

[0012] Optionally, obtaining the current electricity sales revenue, loss cost and penalty includes: obtaining the exchange power for power exchange with the power distribution system, wherein the exchange power is a net output power value when a plurality of the distributed energy resources conduct power transactions with the power distribution system, and when the net output power value is greater than zero, it indicates that the electric energy is transmitted to the power distribution system, and when the net output power value is less than zero, it indicates that the electric energy is purchased from the power distribution system; and calculating the electricity sales revenue using a first formula according to the exchange power, wherein the first formula is: C sell，t =R DA，t ×P VPP-DSO，t , R DA，t represents the electricity price of the previous operation period of the current operation period, P VPP-DSO,t represents the exchange power; obtains the charging power and the discharging power of the energy storage system; calculates the loss cost using a second formula according to the charging power and the discharging power, wherein the second formula is: C ESS，w，t =(P ESS_ch，w，t +P ESS_dch，w，t )C loss , P ESS_ch，w，t represents the charging power, P ESS_dch，w，t represents the discharge power, C loss represents the wear cost; when the total output power is not within the first power constraint range and the power output value is not within the predetermined range, determining the difference between the total output power and the upper boundary of the first power constraint range as the difference power; calculating the penalty fine according to the difference power using a third formula, wherein the third formula is: C penalty，w，t =R penalty，t ×P exceed，w，t , R penalty，t represents the penalty unit price, P exceed，w，t represents the differential power.

[0013] According to another aspect of an embodiment of the present invention, a virtual power plant operation device based on distribution system constraints is also provided, including: a first receiving unit, used to receive a first distribution system constraint issued by a distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to an initial resource scheduling strategy sent by the virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; a first acquisition unit, used to acquire historical distribution system constraints, constraint information of the distribution system, and power output forecast data of multiple distributed energy resources issued by the distribution system operator within a historical time period; a second acquisition unit, used to process the historical distribution system constraints, the constraint information, and the power output forecast data using a constraint prediction model to obtain a second distribution system constraint of the virtual power plant, wherein the constraint prediction model The prediction model is obtained by training with multiple sets of training data by machine learning, each of the multiple sets of training data includes: sample input data, sample second distribution system constraints corresponding to the sample input data, and the sample input data includes: sample historical distribution system constraints, sample constraint information and sample power output prediction data; a third acquisition unit is used to adjust the initial resource scheduling strategy according to the second distribution system constraints to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and not exceed the second power constraint range under the condition that the power output value satisfies the predetermined range, the first power constraint range is the range of the total output power constrained in the first distribution system constraints, and the second power constraint range is the range of the total output power constrained in the second distribution system constraints; a first scheduling unit is used to schedule multiple distributed energy resources according to the first target resource scheduling strategy.

[0014] Optionally, the virtual power plant operation device based on distribution system constraints also includes: a fourth acquisition unit, used to evaluate the current status, available capacity and expected power output data of multiple distributed energy resources before receiving the first distribution system constraint issued by the distribution system operator to obtain an evaluation result; a generation unit, used to generate the initial resource scheduling strategy for scheduling multiple distributed energy resources based on the evaluation result; and a sending unit, used to send the initial resource scheduling strategy to the distribution system operator.

[0015] Optionally, the virtual power plant operation device based on distribution system constraints also includes: an establishment unit, used to establish a collaborative operation framework with the distribution system operator before sending the initial resource scheduling strategy to the distribution system operator, so as to enable information interaction with the distribution system operator through the collaborative operation framework.

[0016] Optionally, the virtual power plant operation device based on distribution system constraints also includes: a second receiving unit, used to receive penalty rules issued by the distribution system operator while receiving the first distribution system constraints issued by the distribution system operator, wherein the penalty rules are used to predict penalty penalties when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range.

[0017] Optionally, the virtual power plant operation device based on distribution system constraints also includes: a construction unit, used to construct an operation model, wherein the operation model is used to adjust the scheduling of multiple distributed energy resources; a fifth acquisition unit, used to solve the operation model using an optimization algorithm to obtain an optimal solution of the operation model, wherein the optimal solution is the solution of the objective function in the operation model when the profit of the virtual power plant is maximized; a sixth acquisition unit, used to adjust the initial resource scheduling strategy according to the optimal solution under the condition of satisfying the first distribution system constraint and the second distribution system constraint to obtain a second target resource scheduling strategy; a second scheduling unit, used to schedule multiple distributed energy resources according to the second target resource scheduling strategy.

[0018] Optionally, the construction unit includes: a first acquisition module, used to obtain the current electricity sales revenue, loss cost and penalty fine, wherein the electricity sales revenue is the difference between the revenue of transmitting electricity to the distribution system and the expenditure of purchasing the electricity from the distribution system, the loss cost is the cost of loss of multiple distributed energy resources, and the penalty fine is a penalty predicted according to a penalty rule when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range, and the penalty rule is a rule issued by the distribution system operator; an establishment module, used to establish the objective function based on the electricity sales revenue, the loss cost and the penalty fine with the goal of maximizing profit, wherein the expression of the objective function is: t represents the number of the running time, T represents the total number of the running time, w represents the number of the running scenario, W represents the total number of the running scenarios, π w represents the scene probability, C sell，t represents the electricity sales revenue, CESS，w，t represents the loss cost, C penalty，w，t Represents the penalty; a second acquisition module, used to constrain the output state, charging state, discharging state, stop state and charge state of the energy storage system during charging and discharging, respectively, to obtain multiple constraints, wherein the energy storage system is one of the multiple distributed energy resources; a construction module, used to construct an operation model according to the objective function and the multiple constraints.

[0019] Optionally, the first acquisition module includes: a first acquisition submodule, used to acquire the exchange power for power exchange with the power distribution system, wherein the exchange power is a net output power value when a plurality of the distributed energy resources and the power distribution system conduct power transactions, and when the net output power value is greater than zero, it indicates that the electric energy is transmitted to the power distribution system, and when the net output power value is less than zero, it indicates that the electric energy is purchased from the power distribution system; a first calculation submodule, used to calculate the power sales revenue according to the exchange power using a first formula, wherein the first formula is: C sell，t =R DA，t ×P VPP-DSO，t , R DA，t represents the electricity price of the previous operation period of the current operation period, P VPP-DSO,t represents the exchange power; a second acquisition submodule, used to obtain the charging power and the discharging power of the energy storage system; a second calculation submodule, used to calculate the loss cost according to the charging power and the discharging power using a second formula, wherein the second formula is: C ESS，w，t =(P ESS_ch，w，t +P ES_dch，w，t )C loss , P ESS_ch，w，t represents the charging power, P ESS_dch，w，t represents the discharge power, C loss represents the wear cost; a determination submodule, used to determine that when the total output power is not within the first power constraint range and the power output value is not within the predetermined range, the difference between the total output power and the upper boundary of the first power constraint range is the difference power; a third calculation submodule, used to calculate the penalty fine according to the difference power using a third formula, wherein the third formula is: C penalty，w，t =R penalty，t ×P exceed，w，t , R penalty，t represents the penalty unit price, P exceed，w，t represents the differential power.

[0020] According to another aspect of an embodiment of the present invention, a virtual power plant operation system based on distribution system constraints is also provided. The virtual power plant operation system based on distribution system constraints uses any of the above-mentioned virtual power plant operation methods based on distribution system constraints.

[0021] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the above-mentioned virtual power plant operation methods based on distribution system constraints.

[0022] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein when the program is run, any one of the above-mentioned virtual power plant operation methods based on distribution system constraints is executed.

[0023] According to another aspect of an embodiment of the present invention, there is also provided a computer program product, comprising computer instructions, which, when executed by a processor, execute any one of the above-mentioned virtual power plant operation methods based on distribution system constraints.

[0024] In an embodiment of the present invention, a first distribution system constraint issued by a distribution system operator is received, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to an initial resource scheduling strategy sent by a virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of the multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; historical distribution system constraints, constraint information of the distribution system, and power output prediction data of multiple distributed energy resources issued by the distribution system operator in a historical time period are obtained; the historical distribution system constraints, constraint information, and power output prediction data are processed using a constraint prediction model to obtain a second distribution system constraint, wherein the constraint prediction model is a method of machine learning using multiple sets of training data. The plurality of training data are obtained by training with a formula, each of which includes: sample input data, sample second distribution system constraints corresponding to the sample input data, and the sample input data includes: sample historical distribution system constraints, sample constraint information and sample power output prediction data; the initial resource scheduling strategy is adjusted according to the second distribution system constraints to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy for making the total output power exceed the first power constraint range and not exceed the second power constraint range under the condition that the power output value satisfies a predetermined range, the first power constraint range is the range for constraining the total output power in the first distribution system constraints, and the second power constraint range is the range for constraining the total output power in the second distribution system constraints; multiple distributed energy resources are scheduled according to the first target resource scheduling strategy. Through the above technical scheme, the purpose of enabling the virtual power plant to predict the constraints of the distribution system by itself and flexibly adjust the scheduling of various distributed energy resources while maintaining the stability of the distribution system is achieved, and the technical effect of not only relying on the distribution system constraints issued by the distribution system operator for scheduling is achieved. The virtual power plant can appropriately exceed the operating range limited by the constraints issued by the distribution system operator while maintaining the stability of the distribution system, thereby improving the flexibility of the virtual power plant in formulating operating strategies, and thus solving the technical problem in related technologies that the operating strategy of the virtual power plant depends on the distribution system constraints issued by the distribution system operator, resulting in the virtual power plant being relatively restricted in formulating operating strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 It is a hardware structure block diagram of a mobile terminal of a virtual power plant operation method based on power distribution system constraints according to an embodiment of the present invention;

[0027] Figure 2 is a flow chart of a virtual power plant operation method based on power distribution system constraints according to an embodiment of the present invention;

[0028] Figure 3 is a flow chart of an optional virtual power plant operation method based on power distribution system constraints according to an embodiment of the present invention;

[0029] Figure 4 is a flowchart of another optional virtual power plant operation method based on distribution system constraints according to an embodiment of the present invention;

[0030] Figure 5 is a schematic diagram of a collaborative operation mechanism processing flow according to an embodiment of the present invention;

[0031] Figure 6 is a schematic diagram of a virtual power plant operation device based on distribution system constraints according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] As introduced in the background technology, in the related technology, since the operation strategy of the virtual power plant depends on the distribution system constraints issued by the distribution system operator, the virtual power plant is relatively limited in formulating the operation strategy. In view of the above defects, in an embodiment of the present invention, a method and device for operating a virtual power plant based on distribution system constraints are provided.

[0035] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0036] The method embodiments provided in the embodiments of the present invention can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of a virtual power plant operation method based on power distribution system constraints according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0037] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the virtual power plant operation method based on distribution system constraints in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific network example may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0038] According to an embodiment of the present invention, a method embodiment of a virtual power plant operation method based on distribution system constraints is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] Figure 2 is a flow chart of a virtual power plant operation method based on power distribution system constraints according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0040] Step S202, receiving the first distribution system constraint issued by the distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to the initial resource scheduling strategy sent by the virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources. The distribution system operator is used to constrain the total output power of multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range.

[0041] Optionally, the above-mentioned distributed energy resources (DERs) may include but are not limited to: photovoltaic systems, wind power systems, energy storage systems, small hydropower systems, fuel cells, microturbines, biomass power generation and demand side management (DSM), etc.

[0042] These distributed energy resources can be used individually or in combination to form a virtual power plant (VPP), which can be centrally managed and optimized through information and communication technology to improve energy utilization efficiency, reduce costs, and enhance grid stability and flexibility. In a virtual power plant, these resources can be dispatched according to market demand and grid operating conditions to maximize economic and environmental benefits.

[0043] In this embodiment, the virtual power plant can receive the first distribution system constraint issued by the distribution system operator, and dispatch each distributed energy resource according to the first distribution system constraint to ensure the stability of the distribution system.

[0044] It should be noted that the constraints imposed by the distribution system operator on the virtual power plant are reflected in multiple aspects. In this embodiment, the constraints are mainly imposed on the total output power of the distributed energy resources in the virtual power plant, that is, the electric energy transmitted by the virtual power plant to the distribution system. The constraints in other aspects are similar in principle and will not be elaborated here. Whether the distribution system is stable can also be judged comprehensively from multiple aspects. In this embodiment, the specific judgment is whether the power supply output of the distribution system can meet the user needs, that is, whether the power output of the distribution system can meet the preset requirements.

[0045] Step S204, obtaining historical distribution system constraints, distribution system constraint information, and power output forecast data of multiple distributed energy resources issued by the distribution system operator within a historical time period.

[0046] In this embodiment, the distribution system operator (DSO) mainly calculates the first distribution system constraint from the perspective of ensuring the stability and safety of the distribution system to ensure that the power grid operates within a safe range. Therefore, the distribution system is usually calculated in a conservative manner, which causes the virtual power plant to always be in a passive state, relying on the first distribution system constraint issued by the distribution system operator to formulate an operation plan for each distributed energy resource. However, in the actual operation process, these constraints may change. Therefore, in order to better adapt to the uncertainty of changes in the first distribution system constraint, the virtual power plant can obtain historical distribution system constraints issued by the distribution system operator within a historical time period, distribution system constraint information and power output forecast data of multiple distributed energy resources, so as to actively predict the distribution system's own constraints, and formulate corresponding operation strategies based on the prediction results, so that the virtual power plant can make better use of its resources without violating the DSO regulations, that is, on the premise of ensuring the stability of the distribution system.

[0047] Step S206, using the constraint prediction model to process the historical power distribution system constraints, constraint information and power output prediction data to obtain the second power distribution system constraints, wherein the constraint prediction model is trained using multiple sets of training data through machine learning, and each of the multiple sets of training data includes: sample input data, and sample second power distribution system constraints corresponding to the sample input data, and the sample input data includes: sample historical power distribution system constraints, sample constraint information and sample power output prediction data.

[0048] Optionally, the above-mentioned historical distribution system constraints refer to the constraint data sent by the distribution system operator to the virtual power plant during the historical time period.

[0049] Optionally, the above constraint information refers to the constraint information that the distribution system may face currently and in the future, provided by the distribution system operator based on factors such as the current grid operation status, predicted load demand, and power generation capacity.

[0050] Optionally, the above-mentioned power output prediction data refers to the prediction data of the output power of each distributed energy resource connected to the virtual power plant in the future.

[0051] In this embodiment, the virtual power plant can use the constraint prediction model to process the acquired historical distribution system constraints, constraint information and power output prediction data to actively predict the distribution system's own constraints and obtain the second distribution system constraints.

[0052] Step S208, adjust the initial resource scheduling strategy according to the second distribution system constraint to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and do not exceed the second power constraint range under the condition that the power output value satisfies a predetermined range, the first power constraint range is the range for constraining the total output power in the first distribution system constraint, and the second power constraint range is the range for constraining the total output power in the second distribution system constraint.

[0053] In this embodiment, since the first distribution system constraint issued by the distribution system operator has certain limitations for the virtual power plant, the virtual power plant may predict a more relaxed operating environment in some cases. Therefore, on this basis, the virtual power plant can adjust its initial operating plan (i.e., the initial resource scheduling strategy) according to the second distribution system constraint obtained by its own prediction, so that the virtual power plant can appropriately exceed the constraint range specified by the first distribution constraint while ensuring the stability of the distribution system. This will not affect the stability of the distribution system, but also enable the virtual power plant to make better use of its resources, thereby improving the flexibility of the virtual power plant in formulating operating strategies (strategies for scheduling various resources).

[0054] Of course, the virtual power plant no longer simply chooses to follow the first distribution system constraints issued by the distribution system operator, nor does it only execute the operation strategy based on the second distribution system constraints predicted by itself. Instead, it will comprehensively consider the first distribution system constraints issued by the distribution system operator and the second distribution system constraints predicted by itself. When the second distribution system constraints predicted by itself are looser than the first distribution system constraints issued by the distribution system operator, it will not directly violate the constraints of the DSO, but will try to find a balance between the two. This balance point must not only ensure the stability of the distribution system, but also maximize the economic benefits of the virtual power plant.

[0055] Step S210: scheduling multiple distributed energy resources according to a first target resource scheduling strategy.

[0056] In this embodiment, multiple distributed energy resources connected to the virtual power plant can be scheduled according to the first target resource scheduling strategy obtained by adjusting the initial resource scheduling strategy of the virtual power plant to better adapt to market changes and power grid demands.

[0057] It can be seen from the above steps that the technical solution provided by the above embodiments of the present invention can receive the first distribution system constraint issued by the distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to the initial resource scheduling strategy sent by the virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources. The distribution system operator is used to constrain the total output power of multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; obtain the historical distribution system constraints, the constraint information of the distribution system and the power output prediction data of multiple distributed energy resources issued by the distribution system operator in the historical time period; use the constraint prediction model to process the historical distribution system constraints, the constraint information and the power output prediction data to obtain the second distribution system constraint, wherein the constraint prediction model is trained by using multiple sets of training data through machine learning, and each of the multiple sets of training data includes: sample input data, and a sample second distribution system constraint corresponding to the sample input data. The sample input data includes: sample historical distribution system constraints, constraint information and power output prediction data. system constraints, sample constraint information and sample power output prediction data; the initial resource scheduling strategy is adjusted according to the second distribution system constraint to obtain the first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy for making the total output power exceed the first power constraint range and not exceed the second power constraint range under the condition that the power output value satisfies the predetermined range, the first power constraint range is the range for constraining the total output power in the first distribution system constraint, and the second power constraint range is the range for constraining the total output power in the second distribution system constraint; multiple distributed energy resources are scheduled according to the first target resource scheduling strategy, so that the virtual power plant can predict the constraints of the distribution system by itself, and flexibly adjust the scheduling of each distributed energy resource under the premise of maintaining the stability of the distribution system, and realize the technical effect of not only relying on the distribution system constraints issued by the distribution system operator for scheduling, so that the virtual power plant can appropriately exceed the operating range limited by the constraints issued by the distribution system operator under the premise of maintaining the stability of the distribution system, thereby improving the flexibility of the virtual power plant in formulating operating strategies.

[0058] Therefore, the technical solution provided by the above-mentioned embodiments of the present invention solves the technical problem in the related technology that the operating strategy of the virtual power plant depends on the distribution system constraints issued by the distribution system operator, which makes the virtual power plant relatively restricted in formulating operating strategies.

[0059] Combine the following Figure 3 , Figure 4 and Figure 5 The above embodiments of the present invention are described in detail Figure 3 is a flow chart of an optional virtual power plant operation method based on power distribution system constraints according to an embodiment of the present invention; Figure 4 is a flowchart of another optional virtual power plant operation method based on distribution system constraints according to an embodiment of the present invention; Figure 5 It is a schematic diagram of the processing flow of the collaborative operation mechanism according to an embodiment of the present invention.

[0060] According to the above-mentioned embodiment of the present invention, before receiving the first distribution system constraint issued by the distribution system operator, the virtual power plant operation method based on the distribution system constraint also includes: evaluating the current status, available capacity and expected power output data of multiple distributed energy resources to obtain evaluation results; generating an initial resource scheduling strategy for scheduling multiple distributed energy resources based on the evaluation results; and sending the initial resource scheduling strategy to the distribution system operator.

[0061] As above Figure 3 As shown in the figure, the virtual power plant can first evaluate each distributed energy resource to preliminarily formulate an operation plan for distributed energy resources (i.e., the initial resource scheduling strategy); specifically, the virtual power plant can first conduct a comprehensive evaluation of the distributed energy resources it manages (such as solar photovoltaic, wind energy, energy storage system, etc.) to understand the current status, available capacity, expected output and other information of these resources; then analyze the demand and price fluctuations in the power market, predict the power demand and market price in different time periods, and determine the best time and price for selling electricity; then use historical data, meteorological information, load forecasting models and other tools to predict the output of distributed energy resources, and establish a mathematical model of power demand and supply; then, based on resource evaluation, market analysis and forecasting results, the virtual power plant formulates a preliminary operation plan. This plan needs to consider maximizing economic benefits, while ensuring that it can meet the supply and demand balance of the power market, and adjust the operation plan in combination with relevant industry rules and standards; finally, the preliminarily formulated operation plan is sent to the distribution system operator (DSO).

[0062] In an optional embodiment of the present invention, before sending the initial resource scheduling strategy to the distribution system operator, the virtual power plant operation method based on distribution system constraints also includes: establishing a collaborative operation framework with the distribution system operator to enable information exchange with the distribution system operator through the collaborative operation framework.

[0063] As above Figure 3 and Figure 4 As shown, a collaborative operation mechanism that takes distribution system constraints into consideration can be constructed, so that within the collaborative operation framework of the distribution system operator and the virtual power plant, after receiving the initial resource scheduling strategy sent by the virtual power plant, the distribution system operator calculates the first distribution system constraint based on the received initial resource scheduling strategy, and sends it to the virtual power plant, so that the virtual power plant schedules its resources based on these constraints, with the aim of maximizing profits while ensuring the stability of the distribution system.

[0064] Regarding the interaction between distribution system operators and virtual power plants, Figure 5 The specific interaction process is shown in FIG.

[0065] In a specific embodiment of the present invention, the virtual power plant operation method based on distribution system constraints also includes: while receiving the first distribution system constraints issued by the distribution system operator, receiving the penalty rules issued by the distribution system operator, wherein the penalty rules are used to predict the penalty fine when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within a predetermined range.

[0066] As above Figure 4 And Figure 5As shown, when the distribution system operator issues the first distribution system constraint to the virtual power plant, it will also send the penalty rules simultaneously. The first distribution system constraint is mainly to constrain the operation of the virtual power plant to ensure the stability of the distribution system. Here we take the total output power of multiple distributed energy resources in the virtual power plant as an example to explain: Assuming that the constraint range of the total output power of the virtual power plant in the first distribution system constraint is the first power constraint range, if the virtual power plant fails to comply with the first distribution system constraint, that is, the total output power of the virtual power plant exceeds the first power constraint range, it may cause the distribution system to have to make additional load cuts or power generation adjustments. This is what the distribution system operator will do to the virtual The power plant will be subject to economic penalties; on the contrary, if the virtual power plant abides by the first distribution system constraints, the distribution system operator may provide economic rewards to encourage such compliance behavior, which reflects the dual role of rewards and punishments in ensuring that the distribution system constraints are met; and here the distribution system issues such penalty rules to the virtual power plant, which is beneficial for the virtual power plant to predict the possible penalties according to the penalty rules when making adjustments according to the second distribution system constraints predicted by itself. This allows the virtual power plant to flexibly adjust its operating strategy and pursue profit maximization while also considering the importance of complying with the first distribution system constraints, because this is directly related to its economic benefits and the safe operation of the system.

[0067] The key to this cooperation mechanism lies in the information sharing and coordination between virtual power plants and distribution system operators, which aims to balance economic benefits and system stability. While pursuing maximum profits, virtual power plants must also consider the importance of complying with distribution system constraints. Through this two-way incentive and constraint mechanism, virtual power plants and distribution system operators can jointly promote a more efficient and reliable power distribution system.

[0068] It should be noted that the penalty mechanism between the virtual power plant and the distribution system operator is that when the power supply of the virtual power plant exceeds the constraints of the distribution system, it may cause instability in the distribution system, so the virtual power plant will face economic penalties from the distribution system operator; however, if there are no stability problems in the distribution system, even if the virtual power plant outputs power in excess of demand, the virtual power plant will not suffer economic losses.

[0069] In addition, when the total output power of the virtual power plant exceeds the first power constraint range, that is, the output power value is greater than the appropriate power value required to maintain the stability of the distribution system, this may cause voltage violations or power congestion in the distribution system, thereby affecting the stability of the system; and when the total output power of the virtual power plant does not meet the first power constraint range, that is, the output power value is less than the appropriate power value required to maintain the stability of the distribution system, this may result in failure to meet system requirements, which will also affect the stability of the system; so no matter which of the above situations, the virtual power plant may be subject to economic penalties; in an embodiment of the present invention, the economic penalty is mainly described as an example when the total output power of the virtual power plant exceeds the first power constraint range, and the other situation is similar to this and will not be repeated.

[0070] In a preferred embodiment of the present invention, the virtual power plant operation method based on distribution system constraints also includes: constructing an operation model, wherein the operation model is used to adjust the scheduling of multiple distributed energy resources; solving the operation model using an optimization algorithm to obtain an optimal solution to the operation model, wherein the optimal solution is a solution to the objective function in the operation model when the profit of the virtual power plant is maximized; under the condition of satisfying the first distribution system constraint and the second distribution system constraint, adjusting the initial resource scheduling strategy according to the optimal solution to obtain a second target resource scheduling strategy; and scheduling multiple distributed energy resources according to the second target resource scheduling strategy.

[0071] As above Figure 4 As shown in the figure, in order to ensure the stability of the distribution system while also pursuing maximum profit, the virtual power plant can construct an operation model to combine with the operation model to achieve the goal of maximizing the economic benefits of the virtual power plant while ensuring the stability of the distribution system; the operation model is a model obtained by establishing an objective function with the goal of maximizing the profit of the virtual power plant under the constraints of the energy storage system.

[0072] In a specific embodiment of the present invention, an operation model is constructed, including: obtaining current electricity sales revenue, loss cost and penalty fines, wherein the electricity sales revenue is the difference between the revenue of transmitting electricity to the distribution system and the expenditure of purchasing electricity from the distribution system, the loss cost is the cost of loss of multiple distributed energy resources, and the penalty fine is a penalty predicted according to a penalty rule when the total output power of multiple distributed energy resources is not within a first power constraint range and the power output value is not within a predetermined range, and the penalty rule is a rule issued by the distribution system operator; based on the electricity sales revenue, loss cost and penalty fines, an objective function is established with profit maximization as the goal, wherein the expression of the objective function is: t represents the number of running time, T represents the total number of running time, w represents the number of running scenarios, W represents the total number of running scenarios, π w represents the scene probability, C sell，t represents the revenue from electricity sales, C ESS，w，t represents the loss cost, C penalty，w，t represents a penalty; constrains the output state, charging state, discharging state, stop state and charge state of the energy storage system during charging and discharging, respectively, to obtain multiple constraint conditions, wherein the energy storage system is one of the multiple distributed energy resources; and constructs an operation model based on the objective function and multiple constraint conditions.

[0073] In the above embodiment of the present invention, obtaining the current electricity sales revenue, loss cost and penalty fine includes: obtaining the exchange power for power exchange with the power distribution system, wherein the exchange power is the net output power value when multiple distributed energy resources and the power distribution system conduct power transactions, and when the net output power value is greater than zero, it indicates that electric energy is transmitted to the power distribution system, and when the net output power value is less than zero, it indicates that electric energy is purchased from the power distribution system; and calculating the electricity sales revenue according to the exchange power using the first formula, wherein the first formula is: C sell，t =R DA，t ×P VPP-DSO，t , R DA，t represents the electricity price of the previous operation period of the current operation period, P VPP-DSO，t represents the exchange power; obtains the charging power and discharging power of the energy storage system; calculates the loss cost using the second formula according to the charging power and the discharging power, wherein the second formula is: C ESS，w，t =(P ESS_ch，w，t +P ESS_dch，w，t )C loss , P ESS_ch，w，t Indicates charging power, P ESS_dch，w，t Indicates discharge power, C loss represents the wear cost; when the total output power is not within the first power constraint range and the power output value is not within the predetermined range, the difference between the total output power and the upper boundary of the first power constraint range is determined to be the difference power; the penalty is calculated according to the difference power using the third formula, wherein the third formula is: C penalty，w，t =R penalty，t ×P exceed，w，t , R penalty，t represents the penalty unit price, P exceed，w，t Indicates the differential power.

[0074] Specifically, a profit maximization operation model of a virtual power plant with a photovoltaic power generation system and an energy storage system can be constructed. The objective function is established with the profit maximization of the virtual power plant as the goal. The expression of the objective function is as shown in formula (1). The objective function is composed of the electricity sales revenue Csell，t , loss cost caused by the operation of energy storage system C ESS，w，t and the penalty C for the expected penalty of cooperative operation penalty，w，t The specific formula can be expressed as follows: C sell，t =R DA，t ×P VPP-DSO，t (2) P VPP-DSO,t =P PV，t +P ESS_dchw，t -P ESS_ch，w，t (3) C ESS，w，t =(P ESS_ch，w，t +P ESS_dch，w，t )C loss (4) C penalty，w，t =R penalty，t ×P exceed，w，t (6), where T represents the total number of running times, w represents the number of running scenarios, W represents the total number of running scenarios, and π w represents the scene probability, C sell，t represents the electricity sales revenue, and the calculation method is shown in formula (2), P VPP-DSO，t It represents the exchange power delivered by the virtual power plant to the distribution system. When it is a positive value, it means selling electricity; when it is a negative value, it means purchasing electricity. VPP-DSO，t It can be calculated by the photovoltaic power generation and the discharge power and charging power of the energy storage system, as shown in formula (3). PV，t Represents photovoltaic power generation, P ESS_dch，w，t Represents the discharge power of the energy storage system, P ESS_ch，w，t Represents the charging power of the energy storage system, C ESS，w，t represents the loss cost, which is calculated based on the number of charge and discharge times of the energy storage system, as shown in formula (4), C loss represents the wear cost of the energy storage system, which can be calculated by formula (5), C ESS represents the unit price of the energy storage system, Represents the cycle of the energy storage system, ESS DOD represents the discharge depth of the energy storage system, and formula (6) represents the expected penalty penalty C penalty，w，t , which is expressed by the amount of power generation exceeding the rated value when the penalty is imposed exceed，w，t (i.e., differential power) is calculated, R penalty，t Indicates the penalty unit price.

[0075] The constraints of the energy storage system are composed of formula (7)_formula (11), where the output constraints of the energy storage system during charging and discharging can be expressed by formula (7) and formula (8) respectively; formula (9) represents the state constraints of the energy storage system, which determines the charging, discharging and stopping states; formula (10) represents the state of charge (SOC); formula (11) represents the constraints of the energy storage system termination, which can be specifically expressed as follows: I ESS_dch，w，t P min ≤P ESS_dch，w，t ≤I ESS_dch，w，t P max (7) I ESS_ch，w，t P min ≤P ESS_ch，w，t ≤I ESS_ch，w，t P max (8) I ESS_ch，w，t +I ESS_dch，w，t ≤1 (9), SOC min，w ≤SOC init，w +SOC w，t ≤SOC max，w (11), where P min Represents the minimum value transmitted by the energy storage system, P max Indicates the maximum value of the energy storage system transmission, I ESS_ch，w，t and I ESS_dch，w，t Represents the state variable of the energy storage system, expressed in binary, SOC w，t Indicates the state of charge of the energy storage system, SOC init，w represents the initial charge state of the energy storage system, η ch Represents the charging efficiency of the energy storage system, η dch Indicates the discharge efficiency of the energy storage system, SOC min，w Indicates the minimum state of charge of the energy storage system, SOC max，w Indicates the maximum state of charge of the energy storage system.

[0076] In addition, as above Figure 4 As shown in the figure, it is also necessary to construct constraints for the power over-expectation calculation of the virtual power plant. The virtual power plant determines P by calculating the power sales revenue and penalties. VPP-DSO，t , P exceed，w，trepresents the excess output power when problems occur in the distribution system. The calculation formula is (12)-(15). If the power sales of the virtual power plant is more than the first distribution system constraint issued by the distribution system operator, and there is no problem with the distribution system, then the distribution system operator does not need to impose any penalty on the virtual power plant; however, if there is any problem with the distribution system and the distribution system operator controls some resources in the distribution system, then the virtual power plant should be responsible for the excess power provided.

[0077] The virtual power plant uses its own predicted distribution system constraints and the distribution system constraints provided by the distribution system operator to calculate P exceed，w，t , because the actual distribution system constraints are unknown, the expected penalty is calculated using the distribution system constraints predicted by the virtual power plant. The purpose of formula (12) is to ensure that P exceed，w，t The value of will not exceed the maximum possible value of the excess power determined by the second distribution system constraint predicted by the virtual power plant and the first distribution system constraint provided by the distribution system operator, that is, to ensure that the excess power calculated by the virtual power plant does not exceed the actual excess power that may occur in any given situation; when the distribution system constraint predicted by the virtual power plant is greater than the distribution system constraint provided by the distribution system operator, P exceed，w，t The power beyond the distribution system constraints predicted by the virtual power plant is calculated using formula (13). When the distribution system constraints provided by the distribution system operator are greater than the distribution system constraints predicted by the virtual power plant, P exceed，w，t It is to calculate the power exceeding the distribution system constraints provided by the distribution system operator, using the constraints of formula (14); in addition, since the excess power of the acceptable power of the distribution system cannot be negative, formula (15) imposes relevant constraints on this.

[0078] The above formulas (12)-(15) can be specifically expressed as follows: DSC VPP，w，t -DSC DSO，t ≤MI PC，w，t (13) DSC DSO，t _DSC VPP，w，t ≤M(1-I PC，w，t ) (14) 0≤P exceed，w，t (15), where DSC VPP，w，t represents the distribution system constraints predicted by the virtual power plant itself, DSC DSO，t I represents the distribution system constraints provided by the distribution system operator; PC，w，tA state variable indicating whether the distribution system constraints predicted by the virtual power plant itself exceed the distribution system constraints provided by the distribution system operation. If so, it is 1, otherwise it is 0; M represents a sufficiently large constant.

[0079] The second distribution system constraint predicted by the virtual power plant itself can be expressed by formula (16) and formula (17), expressed in the form of distribution. Formula (16) indicates that the distribution system constraint predicted by the virtual power plant itself is normally distributed, which is specifically expressed as follows: Among them, μ t represents the mean, represents the standard deviation, when The smaller it is, the better the virtual power plant's prediction effect on the constraints of the actual distribution system is.

[0080] As above Figure 3 As shown, after the virtual power plant adjusts the operation plan of each distributed energy resource according to the first distribution system constraint issued by the distribution system operator and the self-predicted Hill distribution system constraint, the virtual power plant dispatches the distributed energy resources according to the adjusted operation plan, and the distribution system operator manages the distribution system independently. The virtual power plant sends the operation results to the distribution system operator. When problems occur in the distribution system, the distribution system operator checks whether the virtual power plant violates the first distribution system constraint. If problems occur in the distribution system for any reason, including over-generation of the virtual power plant, the distribution system operator will solve the problem and calculate the fine based on the operation results of the virtual power plant. The distribution system operator imposes a fine on the virtual power plant. After the operation, the distribution system operator will announce the operation results of the virtual power plant and the fine settlement history to improve the transparency of the operation of the distribution system based on the distribution system constraints.

[0081] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0082] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0083] According to an embodiment of the present invention, a virtual power plant operation device based on power distribution system constraints for implementing the above-mentioned virtual power plant operation method based on power distribution system constraints is also provided. Figure 6 is a schematic diagram of a virtual power plant operation device based on power distribution system constraints according to an embodiment of the present invention, such as Figure 6 As shown, the device includes: a first receiving unit 61, a first obtaining unit 63, a second obtaining unit 65, a third obtaining unit 67 and a first dispatching unit 69. The virtual power plant operation device based on power distribution system constraints is described in detail below.

[0084] The first receiving unit 61 is used to receive the first distribution system constraint issued by the distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to the initial resource scheduling strategy sent by the virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources. The distribution system operator is used to constrain the total output power of multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range.

[0085] The first acquisition unit 63 is used to acquire historical distribution system constraints, distribution system constraint information, and power output forecast data of multiple distributed energy resources issued by the distribution system operator within a historical time period.

[0086] The second acquisition unit 65 is used to use the constraint prediction model to process the historical distribution system constraints, constraint information and power output prediction data to obtain the second distribution system constraints of the virtual power plant, wherein the constraint prediction model is trained by machine learning using multiple sets of training data, and each of the multiple sets of training data includes: sample input data, and sample second distribution system constraints corresponding to the sample input data, and the sample input data includes: sample historical distribution system constraints, sample constraint information and sample power output prediction data.

[0087] The third acquisition unit 67 is used to adjust the initial resource scheduling strategy according to the second distribution system constraint to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and do not exceed the second power constraint range under the condition that the power output value satisfies a predetermined range, the first power constraint range is the range of the total output power constrained in the first distribution system constraint, and the second power constraint range is the range of the total output power constrained in the second distribution system constraint.

[0088] The first scheduling unit 69 is used to schedule multiple distributed energy resources according to a first target resource scheduling strategy.

[0089] It should be noted here that the above-mentioned first receiving unit 61, first acquisition unit 63, second acquisition unit 65, third acquisition unit 67 and first scheduling unit 69 correspond to steps S202 to S210 in the above-mentioned embodiments, and the five units have the same instances and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0090] As can be seen from the above, in the scheme recorded in the above-mentioned embodiment of the present invention, a first receiving unit can be used to receive a first distribution system constraint issued by a distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to an initial resource scheduling strategy sent by a virtual power plant, and the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; then a first acquisition unit is used to obtain historical distribution system constraints, constraint information of the distribution system, and power output prediction data of multiple distributed energy resources issued by the distribution system operator within a historical time period; then a second acquisition unit is used to process the historical distribution system constraints, constraint information, and power output prediction data using a constraint prediction model to obtain a second distribution system constraint of the virtual power plant, wherein the constraint prediction model is obtained by training using multiple sets of training data by machine learning, and each of the multiple sets of training data includes: sample input data, and a sample second distribution system constraint corresponding to the sample input data, and the sample input data includes: sample history distribution system constraints, sample constraint information and sample power output prediction data; then, the third acquisition unit is used to adjust the initial resource scheduling strategy according to the second distribution system constraints to obtain the first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and does not exceed the second power constraint range under the condition that the power output value satisfies the predetermined range, the first power constraint range is the range of the total output power constraint in the first distribution system constraints, and the second power constraint range is the range of the total output power constraint in the second distribution system constraints; finally, the first scheduling unit is used to schedule multiple distributed energy resources according to the first target resource scheduling strategy, so as to achieve the purpose of self-predicting the constraints of the distribution system by the virtual power plant, and flexibly adjusting the scheduling of each distributed energy resource under the premise of maintaining the stability of the distribution system, and realizing the technical effect of not only relying on the distribution system constraints issued by the distribution system operator for scheduling, so that the virtual power plant can appropriately exceed the operating range limited by the constraints issued by the distribution system operator under the premise of maintaining the stability of the distribution system, thereby improving the flexibility of the virtual power plant in formulating operating strategies.

[0091] Therefore, the technical solution provided by the above-mentioned embodiments of the present invention solves the technical problem in the related technology that the operating strategy of the virtual power plant depends on the distribution system constraints issued by the distribution system operator, which makes the virtual power plant relatively restricted in formulating operating strategies.

[0092] Optionally, the virtual power plant operation device based on distribution system constraints also includes: a fourth acquisition unit, used to evaluate the current status, available capacity and expected power output data of multiple distributed energy resources to obtain an evaluation result before receiving the first distribution system constraint issued by the distribution system operator; a generation unit, used to generate an initial resource scheduling strategy for scheduling multiple distributed energy resources based on the evaluation result; and a sending unit, used to send the initial resource scheduling strategy to the distribution system operator.

[0093] Optionally, the virtual power plant operation device based on distribution system constraints also includes: an establishment unit, used to establish a collaborative operation framework with the distribution system operator before sending the initial resource scheduling strategy to the distribution system operator, so as to enable information interaction with the distribution system operator through the collaborative operation framework.

[0094] Optionally, the virtual power plant operation device based on distribution system constraints also includes: a second receiving unit, used to receive penalty rules issued by the distribution system operator while receiving the first distribution system constraints issued by the distribution system operator, wherein the penalty rules are used to predict penalty penalties when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within a predetermined range.

[0095] Optionally, the virtual power plant operation device based on distribution system constraints also includes: a construction unit, used to construct an operation model, wherein the operation model is used to adjust the scheduling of multiple distributed energy resources; a fifth acquisition unit, used to solve the operation model using an optimization algorithm to obtain the optimal solution of the operation model, wherein the optimal solution is the solution of the objective function in the operation model when the profit of the virtual power plant is maximized; a sixth acquisition unit, used to adjust the initial resource scheduling strategy according to the optimal solution under the condition of satisfying the first distribution system constraint and the second distribution system constraint, to obtain a second target resource scheduling strategy; a second scheduling unit, used to schedule multiple distributed energy resources according to the second target resource scheduling strategy.

[0096] Optionally, the construction unit includes: a first acquisition module, which is used to obtain the current electricity sales revenue, loss cost and penalty fine, wherein the electricity sales revenue is the difference between the revenue of transmitting electricity to the distribution system and the expenditure of purchasing electricity from the distribution system, the loss cost is the cost of loss of multiple distributed energy resources, and the penalty fine is a penalty predicted according to the penalty rule when the total output power of the multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range, and the penalty rule is a rule issued by the distribution system operator; a building module is used to establish an objective function based on the electricity sales revenue, loss cost and penalty fine with the goal of maximizing profit, wherein the expression of the objective function is: t represents the number of running time, T represents the total number of running time, w represents the number of running scenarios, W represents the total number of running scenarios, π w represents the scene probability, C sell，t represents the revenue from electricity sales, C ESS，w，t represents the loss cost, C penalty，w，t Indicates a penalty; a second acquisition module is used to constrain the output state, charging state, discharging state, stop state and charge state of the energy storage system during charging and discharging, respectively, to obtain multiple constraints, wherein the energy storage system is one of multiple distributed energy resources; a construction module is used to construct an operation model according to the objective function and multiple constraints.

[0097] Optionally, the first acquisition module includes: a first acquisition submodule, used to acquire the exchange power for power exchange with the power distribution system, wherein the exchange power is the net output power value when multiple distributed energy resources and the power distribution system conduct power transactions, and when the net output power value is greater than zero, it indicates that electric energy is transmitted to the power distribution system, and when the net output power value is less than zero, it indicates that electric energy is purchased from the power distribution system; a first calculation submodule, used to calculate the power sales revenue according to the exchange power using a first formula, wherein the first formula is: C sell，t =R DA，t ×P VPP-DSO，t , R DA，t represents the electricity price of the previous operation period of the current operation period, P VPP-DSO，t represents the exchange power; a second acquisition submodule, used to obtain the charging power and the discharging power of the energy storage system; a second calculation submodule, used to calculate the loss cost according to the charging power and the discharging power using the second formula, wherein the second formula is: C ESS，w，t =(P ESS_ch，w，t +P ESS_dch，w，t )C loss , P ESS_ch，w，t Indicates charging power, P ESS_dch，w，t Indicates discharge power, C loss represents the wear cost; a determination submodule, used to determine that the difference between the total output power and the upper boundary of the first power constraint range is the difference power when the total output power is not within the first power constraint range and the power output value is not within the predetermined range; a third calculation submodule, used to calculate the penalty according to the difference power using a third formula, wherein the third formula is: C penalty，w，t =R penalty，t ×P exceed，w，t , R penalty，t represents the penalty unit price, P exceed，w，t Indicates the differential power.

[0098] According to another aspect of an embodiment of the present invention, a virtual power plant operation system based on distribution system constraints is also provided. The virtual power plant operation system based on distribution system constraints uses any of the above-mentioned virtual power plant operation methods based on distribution system constraints.

[0099] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium comprising a stored program, wherein the program executes any one of the above-mentioned virtual power plant operation methods based on distribution system constraints.

[0100] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the communication devices in a communication device group.

[0101] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: receiving a first distribution system constraint issued by a distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator based on an initial resource scheduling strategy sent by a virtual power plant, the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; obtaining historical distribution system constraints, distribution system constraint information, and power output forecast data of multiple distributed energy resources issued by the distribution system operator within a historical time period; using a constraint prediction model to process the historical distribution system constraints, constraint information, and power output forecast data to obtain a second distribution system constraint, wherein the constraint prediction model is used The resource scheduling strategy is obtained by training with multiple sets of training data through machine learning, and each set of the multiple sets of training data includes: sample input data, sample second distribution system constraints corresponding to the sample input data, and the sample input data includes: sample historical distribution system constraints, sample constraint information and sample power output prediction data; the initial resource scheduling strategy is adjusted according to the second distribution system constraints to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and does not exceed the second power constraint range under the condition that the power output value meets the predetermined range, the first power constraint range is the range of the total output power constrained in the first distribution system constraints, and the second power constraint range is the range of the total output power constrained in the second distribution system constraints; multiple distributed energy resources are scheduled according to the first target resource scheduling strategy.

[0102] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: evaluating the current status, available capacity, and expected power output data of multiple distributed energy resources to obtain evaluation results; generating an initial resource scheduling strategy for scheduling multiple distributed energy resources based on the evaluation results; and sending the initial resource scheduling strategy to the distribution system operator.

[0103] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: establishing a collaborative operation framework with a distribution system operator, so as to perform information exchange with the distribution system operator through the collaborative operation framework.

[0104] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: while receiving a first distribution system constraint issued by a distribution system operator, receiving a penalty rule issued by the distribution system operator, wherein the penalty rule is used to predict a penalty penalty when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within a predetermined range.

[0105] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: constructing an operation model, wherein the operation model is used to adjust the scheduling of multiple distributed energy resources; solving the operation model using an optimization algorithm to obtain an optimal solution to the operation model, wherein the optimal solution is a solution to the objective function in the operation model when the profit of the virtual power plant is maximized; under the condition of satisfying the first distribution system constraints and the second distribution system constraints, adjusting the initial resource scheduling strategy according to the optimal solution to obtain a second target resource scheduling strategy; and scheduling multiple distributed energy resources according to the second target resource scheduling strategy.

[0106] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining current electricity sales revenue, loss cost and penalty fines, wherein the electricity sales revenue is the difference between the revenue of transmitting electricity to the distribution system and the expenditure of purchasing electricity from the distribution system, the loss cost is the cost of loss of multiple distributed energy resources, and the penalty fine is a penalty predicted according to a penalty rule when the total output power of the multiple distributed energy resources is not within the first power constraint range and the power output value is not within a predetermined range, and the penalty rule is a rule issued by the distribution system operator; based on the electricity sales revenue, loss cost and penalty fines, an objective function is established with profit maximization as the goal, wherein the expression of the objective function is: t represents the number of running time, T represents the total number of running time, w represents the number of running scenarios, W represents the total number of running scenarios, πw represents the scene probability, C sell，t represents the revenue from electricity sales, C ESS，w，t represents the loss cost, C penalty，w，t represents a penalty; constrains the output state, charging state, discharging state, stop state and charge state of the energy storage system during charging and discharging, respectively, to obtain multiple constraint conditions, wherein the energy storage system is one of the multiple distributed energy resources; and constructs an operation model based on the objective function and multiple constraint conditions.

[0107] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining exchange power for power exchange with the power distribution system, wherein the exchange power is a net output power value when multiple distributed energy resources and the power distribution system conduct power transactions, and when the net output power value is greater than zero, it indicates that electric energy is delivered to the power distribution system, and when the net output power value is less than zero, it indicates that electric energy is purchased from the power distribution system; and calculating the power sales revenue using a first formula according to the exchange power, wherein the first formula is: C sell，t =R DA，t ×P VPP-DSO，t , R DA，t represents the electricity price of the previous operation period of the current operation period, P VPP-DSO，t represents the exchange power; obtains the charging power and discharging power of the energy storage system; calculates the loss cost using the second formula according to the charging power and the discharging power, wherein the second formula is: C ESS，w，t =(P ESS_ch，w，t +P ESS_dch，w，t )C loss , P ESS_ch，w，t Indicates charging power, P ESS_dch，w，t Indicates discharge power, C loss represents the wear cost; when the total output power is not within the first power constraint range and the power output value is not within the predetermined range, the difference between the total output power and the upper boundary of the first power constraint range is determined to be the difference power; the penalty is calculated according to the difference power using the third formula, wherein the third formula is: C penalty，w，t =R penalty，t ×P exceed，w，t , R penalty，t represents the penalty unit price, P exceed，w，t Indicates the differential power.

[0108] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein when the program is run, any one of the above-mentioned virtual power plant operation methods based on distribution system constraints is executed.

[0109] According to another aspect of an embodiment of the present invention, a computer program product is also provided, comprising computer instructions, which, when executed by a processor, execute any one of the above-mentioned virtual power plant operation methods based on distribution system constraints.

[0110] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0111] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0114] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0115] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0116] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A virtual power plant operation method based on power distribution system constraints, characterized in that: include: Receive a first distribution system constraint issued by a distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to an initial resource scheduling strategy sent by a virtual power plant, the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of the multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; Obtaining historical distribution system constraints, constraint information of the distribution system, and power output forecast data of a plurality of distributed energy resources issued by the distribution system operator within a historical time period; The historical power distribution system constraint, the constraint information and the power output prediction data are processed by using a constraint prediction model to obtain a second power distribution system constraint, wherein the constraint prediction model is trained by using multiple sets of training data in a machine learning manner, and each of the multiple sets of training data includes: sample input data, and a sample second power distribution system constraint corresponding to the sample input data, and the sample input data includes: sample historical power distribution system constraints, sample constraint information and sample power output prediction data; The initial resource scheduling strategy is adjusted according to the second power distribution system constraint to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed the first power constraint range and does not exceed the second power constraint range under the condition that the power output value satisfies the predetermined range, the first power constraint range is the range in which the total output power is constrained in the first power distribution system constraint, and the second power constraint range is the range in which the total output power is constrained in the second power distribution system constraint; The plurality of distributed energy resources are scheduled according to the first target resource scheduling strategy.

2. The method for operating a virtual power plant based on power distribution system constraints according to claim 1, characterized in that: Before receiving the first distribution system constraint issued by the distribution system operator, the method further includes: Evaluate the current status, available capacity and expected power output data of the plurality of distributed energy resources to obtain an evaluation result; Generate the initial resource scheduling strategy for scheduling the plurality of distributed energy resources based on the evaluation result; The initial resource scheduling strategy is sent to the distribution system operator.

3. The method for operating a virtual power plant based on power distribution system constraints according to claim 2, characterized in that: Before sending the initial resource scheduling strategy to the distribution system operator, the method further includes: A collaborative operation framework is established with the distribution system operator, so that information is exchanged with the distribution system operator through the collaborative operation framework.

4. The method for operating a virtual power plant based on power distribution system constraints according to claim 1, characterized in that: Also includes: While receiving the first distribution system constraint issued by the distribution system operator, the penalty rule issued by the distribution system operator is received, wherein the penalty rule is used to predict the penalty penalty when the total output power of multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range.

5. The method for operating a virtual power plant based on power distribution system constraints according to claim 1, characterized in that: Also includes: Constructing an operation model, wherein the operation model is used to adjust the scheduling of the plurality of distributed energy resources; Solving the operation model using an optimization algorithm to obtain an optimal solution to the operation model, wherein the optimal solution is a solution to an objective function in the operation model when maximizing the profit of the virtual power plant; Under the condition that the first power distribution system constraint and the second power distribution system constraint are satisfied, adjusting the initial resource scheduling strategy according to the optimal solution to obtain a second target resource scheduling strategy; The plurality of distributed energy resources are scheduled according to the second target resource scheduling strategy.

6. The method for operating a virtual power plant based on power distribution system constraints according to claim 5, characterized in that: Build and run the model, including: Obtaining the current electricity sales revenue, loss cost and penalty fine, wherein the electricity sales revenue is the difference between the revenue of transmitting electric energy to the distribution system and the expenditure of purchasing the electric energy from the distribution system, the loss cost is the cost of loss of multiple distributed energy resources, and the penalty fine is a penalty predicted according to a penalty rule when the total output power of the multiple distributed energy resources is not within the first power constraint range and the power output value is not within the predetermined range, and the penalty rule is a rule issued by the distribution system operator; Based on the electricity sales revenue, the loss cost and the penalty, the objective function is established with the goal of maximizing profit, wherein the expression of the objective function is: t represents the number of the running time, T represents the total number of the running time, w represents the number of the running scenario, W represents the total number of the running scenarios, π w represents the scene probability, C sell，t represents the electricity sales revenue, C ESS，w，t represents the loss cost, C penalty，w，t Indicates the penalty amount; Constraining the output state, charging state, discharging state, stop state and charged state of the energy storage system during charging and discharging respectively to obtain a plurality of constraint conditions, wherein the energy storage system is one of the plurality of distributed energy resources; An operation model is constructed according to the objective function and the plurality of constraint conditions.

7. The method for operating a virtual power plant based on power distribution system constraints according to claim 6, characterized in that: Obtain current electricity sales revenue, loss costs, and penalties, including: Acquire the exchange power for power exchange with the power distribution system, wherein the exchange power is the net output power value when the plurality of distributed energy resources conduct power trading with the power distribution system, and when the net output power value is greater than zero, it indicates that the electric energy is transmitted to the power distribution system, and when the net output power value is less than zero, it indicates that the electric energy is purchased from the power distribution system; The electricity sales revenue is calculated according to the exchange power using a first formula, wherein the first formula is: C sell，t =R DA，t ×P VPP-DSO，t , R DA，t represents the electricity price of the previous operation period of the current operation period, P VPP-DSO,t represents the exchange power; Obtaining charging power and discharging power of the energy storage system; The loss cost is calculated using a second formula according to the charging power and the discharging power, wherein the second formula is: C ESS，w，t =(P ESS_ch，w，t +P ESS_dch，w，t )C loss , P ESS_ch，w，t represents the charging power, P ESS_dch，w，t represents the discharge power, C loss represents the wear cost; When the total output power is not within the first power constraint range and the power output value is not within the predetermined range, determining the difference between the total output power and the upper boundary of the first power constraint range as the differential power; The penalty is calculated according to the difference power using a third formula, wherein the third formula is: C penalty，w，t =R penalty，t ×P exceed，w，t , R penalty，t represents the penalty unit price, P exceed，w，t represents the differential power.

8. A virtual power plant operation device based on power distribution system constraints, characterized in that: include: A first receiving unit is used to receive a first distribution system constraint issued by a distribution system operator, wherein the first distribution system constraint is a constraint condition calculated by the distribution system operator according to an initial resource scheduling strategy sent by a virtual power plant, the initial resource scheduling strategy is a strategy for scheduling multiple distributed energy resources, and the distribution system operator is used to constrain the total output power of the multiple distributed energy resources so that the power output value of the distribution system is within a predetermined range; A first acquisition unit is used to acquire historical distribution system constraints issued by the distribution system operator within a historical time period, constraint information of the distribution system, and power output forecast data of a plurality of distributed energy resources; a second acquisition unit, configured to process the historical power distribution system constraints, the constraint information and the power output prediction data using a constraint prediction model to obtain a second power distribution system constraint of the virtual power plant, wherein the constraint prediction model is obtained by training using multiple sets of training data in a machine learning manner, each of the multiple sets of training data comprising: sample input data, and a sample second power distribution system constraint corresponding to the sample input data, wherein the sample input data comprises: sample historical power distribution system constraints, sample constraint information and sample power output prediction data; a third acquisition unit, configured to adjust the initial resource scheduling strategy according to the second power distribution system constraint to obtain a first target resource scheduling strategy, wherein the first target resource scheduling strategy is a strategy that makes the total output power exceed a first power constraint range and does not exceed a second power constraint range under the condition that the power output value satisfies the predetermined range, the first power constraint range is a range in which the total output power is constrained in the first power distribution system constraint, and the second power constraint range is a range in which the total output power is constrained in the second power distribution system constraint; The first scheduling unit is used to schedule the plurality of distributed energy resources according to the first target resource scheduling strategy.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the virtual power plant operation method based on distribution system constraints as described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the virtual power plant operation method based on distribution system constraints as described in any one of claims 1 to 7 is performed.

Images