Power distribution area operation regulation and control method, device, equipment and medium

Abstract

The embodiment of the invention discloses a power distribution area operation regulation and control method, device and equipment and a medium. The method comprises the following steps: acquiring load users in a power distribution area and electricity price data of each time period; determining load side resource response data of each time period based on the load user and the electricity price data of each time period; and according to the load side resource response data, determining an optimal scheduling strategy for operation of the power distribution area, so as to regulate and control the power distribution area based on the optimal scheduling strategy. According to the technical scheme, by considering the flexible resource response characteristic of the load side, the economic operation scheduling of the power distribution area under the condition of fully considering the demand response characteristic and the benefit of each main body in the power market is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network, and in particular to a method, device, equipment and medium for controlling operation of a power distribution station area. Background Art

[0002] With the continuous development of modern industry, there is a huge demand for various resources. The development of economic structure has also promoted the change of energy consumption structure. Adjustable resource power generation technology based on new technologies such as automatic control systems, advanced material technology, and flexible manufacturing processes plays an important role in load regulation and optimization. How to use adjustable resources to achieve horizontal multi-source complementarity and vertical source-grid-load-storage coordinated multi-source coordinated optimization scheduling under the distribution station area, promote the balance of power grid supply and demand, reduce the electricity bill expenditure of end users, reduce the cost of power companies, save resources, and reduce environmental pollution is of great significance.

[0003] The existing distribution substation area optimization scheduling methods mainly include: 1) Methods for establishing deterministic optimization scheduling models. This method usually uses a centralized algorithm to solve the optimization scheduling model with determined parameters. Since the uncertainty of source and load is not considered, the decision-making accuracy is not high. 2) Optimization methods that consider source and load uncertainty. This type of method has difficulty in mathematical modeling of complex uncertainties, it is difficult to preset various working conditions in advance and it is difficult to establish a general optimization equation. In addition, this type of method often finds it difficult to consider the response characteristics of flexible resources on the load side. Summary of the invention

[0004] The present invention provides a distribution station area operation control method, device, equipment and medium, which realizes economic operation scheduling of distribution station areas under the conditions of fully considering demand response characteristics and the interests of various entities in the power market by taking into account the response characteristics of flexible resources on the load side.

[0005] According to one aspect of the present invention, a method for controlling operation of a distribution station area is provided, comprising:

[0006] Obtain the load users and electricity price data of each time period within the distribution station area;

[0007] Determining load-side resource response data for each time period based on the load users and electricity price data for each time period;

[0008] An optimal scheduling strategy for the operation of the distribution substation is determined according to the load-side resource response data, so as to regulate the distribution substation based on the optimal scheduling strategy.

[0009] According to another aspect of the present invention, there is provided a distribution station area operation control device, comprising:

[0010] The data acquisition module is used to obtain the load users and electricity price data of each time period in the distribution station area;

[0011] A response data determination module, used to determine the load-side resource response data for each time period based on the load users and the electricity price data for each time period;

[0012] A scheduling strategy determination module is used to determine the optimal scheduling strategy for the operation of the distribution substation according to the load-side resource response data, so as to regulate the distribution substation based on the optimal scheduling strategy.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution station area operation control method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution station area operation control method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the load users and electricity price data of each time period in the distribution station area; determines the load-side resource response data of each time period based on the load users and electricity price data of each time period; determines the optimal scheduling strategy for the operation of the distribution station area according to the load-side resource response data, so as to regulate the distribution station area based on the optimal scheduling strategy. This technical solution, by taking into account the response characteristics of flexible resources on the load side, realizes the economic operation and scheduling of the distribution station area under the conditions of fully considering the demand response characteristics and the interests of various entities in the power market.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a distribution station area operation control method provided according to the first embodiment of the present invention;

[0022] Figure 2 is a flow chart of a distribution station area operation control method provided according to the second embodiment of the present invention;

[0023] Figure 3 It is a structural schematic diagram of a distribution station area operation control device provided according to Embodiment 3 of the present invention;

[0024] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] It should be noted that the terms "first", "second" and "target" 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.

[0027] Embodiment 1

[0028] Figure 1 This is a flow chart of a method for controlling the operation of a distribution substation according to the first embodiment of the present invention. This embodiment is applicable to the case of controlling the operation of a distribution substation. The method can be executed by a distribution substation operation control device. The distribution substation operation control device can be implemented in the form of hardware and / or software. The distribution substation operation control device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S110, obtaining load users in the distribution station area and electricity price data for each time period.

[0030] Among them, the distribution station area may refer to the power supply range or area of ​​the distribution transformer. Load users can be understood as load users refer to groups of electricity users with different power demands on the power system within the distribution station area. Load users may include but are not limited to industrial users, commercial users, residential users, and agricultural users. Users in different industries have different electricity consumption characteristics and needs. The electricity price data for each time period may be electricity price data corresponding to different time periods and different user types. In this embodiment, different electricity price standards are set for different load users, electricity consumption, seasons and other factors. For example, the residential electricity price is divided into different levels according to the electricity consumption, and the electricity price for each level is different. The electricity prices for industrial and commercial electricity are usually more complicated, involving multiple systems such as time-of-use electricity prices, peak electricity prices, and valley electricity prices.

[0031] In this embodiment, various types of load users within the distribution station area and the electricity prices corresponding to the load users in various time periods can be obtained.

[0032] S120: Determine load-side resource response data for each time period based on load users and electricity price data for each time period.

[0033] Among them, the load-side resource response data may refer to the flexible resource response data on the power load side. In this embodiment, the load-side resource response data refers to the response of power users to the dispatching instructions issued by the power system by adjusting their own power consumption behavior or adopting energy-saving technologies according to the needs of the power system operation. These resources include but are not limited to industrial loads, commercial loads, residential loads, and adjustable energy storage devices. In this embodiment, the load-side resource response data may include load resources such as electric vehicles or residential electricity, and the resource response data on the load side may be regarded as a whole load resource. In this embodiment, the load-side resource response data may be the load transfer caused by the impact of the load on the electricity price data, that is, the load data of each user transferred to other time periods during the current time period.

[0034] In this embodiment, under the incentive of electricity price changes, load electricity users will adjust the response behavior of each time period according to the electricity price of different time periods, that is, the load has shifted according to the electricity price situation. In order to solve the load transfer situation under the incentive of electricity price, a load-side optimization model can be constructed based on the load users and the electricity price data corresponding to each time period, so as to obtain the load transfer situation under the incentive of electricity price in different time periods by solving the load-side optimization model, that is, the load-side flexible resource response data of each time period.

[0035] S130. Determine the optimal dispatching strategy for the operation of the distribution substation according to the load-side resource response data, so as to regulate the distribution substation based on the optimal dispatching strategy.

[0036] Among them, the optimal dispatching strategy can be understood as the optimal power generation dispatching strategy to ensure the stability of power supply and economic operation of the distribution substation area. In this embodiment, after solving the load-side flexible resource response data, the total load demand of the distribution substation area can be obtained according to the load-side resource response data, and the output data of each distributed power source and energy storage in the distribution substation area can be further determined according to the total load demand of the distribution substation area, so as to determine the optimal dispatching strategy for the operation of the distribution substation area, so as to adjust the power generation dispatching strategy of the distribution substation area based on the optimal dispatching strategy.

[0037] The technical solution of the embodiment of the present invention obtains the load users and electricity price data of each time period in the distribution station area; determines the load-side resource response data of each time period based on the load users and electricity price data of each time period; determines the optimal dispatching strategy for the operation of the distribution station area according to the load-side resource response data, so as to regulate the distribution station area based on the optimal dispatching strategy. This technical solution, by considering the response characteristics of flexible resources on the load side, realizes the economic operation dispatch of the distribution station area under the conditions of fully considering the demand response characteristics and the interests of various entities in the power market.

[0038] Embodiment 2

[0039] Figure 2 This is a flow chart of a distribution substation operation control method provided according to the second embodiment of the present invention. This embodiment is optimized based on the above embodiment. The specific optimization is: based on the load users and the electricity price data of each time period, determine the load side resource response data of each time period, including: based on the load users and the electricity price data of each time period, determine the load response model of each time period; based on the load response model and the reinforcement learning algorithm, determine the load side resource response data of each time period. Figure 2 As shown, the method includes:

[0040] S210: Obtain the load users and electricity price data of each time period within the distribution station area.

[0041] S220: Determine a load response model for each time period based on load users and electricity price data for each time period.

[0042] The load response model may be composed of an objective function and constraints. In this embodiment, an objective function may be constructed based on different load data of load users in different time periods, and constraints corresponding to the load data may be set, and a load response model for each time period may be constructed based on the objective function and constraints.

[0043] In this embodiment, optionally, the load response model for each time period is determined based on the load users and the electricity price data for each time period, including: determining the load change data of the load users under the influence of the electricity price data for each time period; constructing a first objective function based on the load change data, and determining a first constraint condition based on the load change data; determining the load response model for each time period based on the first objective function and the first constraint condition.

[0044] The load change data can be understood as the load transfer situation of the load in different time periods under the stimulation of electricity price data. The first objective function can be constructed based on the load transfer situation of the load users in the distribution station area under the stimulation of electricity price data in different time periods. The first constraint condition can be set according to actual needs. In this embodiment, corresponding constraints can be set for the load change data in different time periods.

[0045] In this embodiment, since the total load demand is unchanged, it is nothing more than consuming the load in different time periods. The electricity prices in different time periods will be different, so the load consumption strategy will change according to the electricity price. Therefore, in this embodiment, under the incentive of electricity price changes, load electricity users will adjust the response behavior of each time period according to the electricity prices in different time periods, that is, determine the load change data of load users under the influence of electricity price data in each time period.

[0046] In this embodiment, the first objective function is constructed according to the load transfer situation of the load users in the distribution station area in different time periods under the incentive of electricity price data, which can be specifically:

[0047]

[0048] In this embodiment, the first constraint condition can be determined based on the load transfer situation of load users in the distribution station area in different time periods under the incentive of electricity price data:

[0049]

[0050] Where N is the set of load users in the distribution area, m is the user index, and t i and T represent the time period index and total duration respectively, γ t and Represent the electricity price and the consumer from time period t i Migrate to t j The load, and represent the minimum and maximum outbound loads in time period i, respectively. and are the minimum and maximum in-migration loads in time period j, M mis a specific real number, which represents the total load demand of user m in all time periods, and g(·) represents a differentiable decreasing function, which describes the relationship between the total load demand and the electricity price.

[0051] In this embodiment, the objective function constructed according to the load transfer situation of the load users in the distribution station area in different time periods under the incentive of electricity price data and the corresponding first constraint conditions set for the load change data in different time periods can be used to obtain the load response model for each time period.

[0052] In this embodiment, by such a setting, the load response model affected by electricity prices in different time periods is determined, so that the flexible resource response characteristics on the user side are taken into account in the economic optimization operation and regulation of the distribution station area, so as to determine the appropriate scheduling strategy for the distribution station area.

[0053] S230. Determine the load-side resource response data for each time period based on the load response model and the reinforcement learning algorithm.

[0054] Among them, the reinforcement learning algorithm is one of the paradigms and methodologies of machine learning, which is used to describe and solve the problem of an agent learning a strategy to maximize returns or achieve a specific goal during the interaction with the environment. In this embodiment, the reinforcement learning framework elements may include state, action, reward, policy, and evaluation function. The state can describe the key state variables of the entire load response model. The state represents the current situation of the environment, the action is the operation that the agent can perform, and the reward is the feedback that the agent obtains from the environment after performing the action. The reward function is a function decomposed according to the first objective function in the load response model. The strategy is the rule for the agent to select an action, and the evaluation function evaluates the expected return of taking a specific strategy under a specific state.

[0055] In this embodiment, the three elements of the corresponding reinforcement learning framework, such as state, action, and reward, can be defined according to the load response model, and then the functional relationship between the intelligent agent in the reinforcement learning algorithm and the defined state, action, and reward can be solved to obtain the load-side resource response data for each time period.

[0056] In this embodiment, optionally, the load-side resource response data for each time period is determined based on the load response model and the reinforcement learning algorithm, including: defining the state variables, action variables and reward functions in the reinforcement learning algorithm based on the load response model; using a neural network to fit the functional relationship between the state variables, action variables and reward functions based on the historical operation data of the distribution station area, and determining the simulation environment of the reinforcement learning agent based on the neural network; wherein the historical operation data includes historical state variables and historical action variables; and determining the load-side resource response data for each time period based on the simulation environment and the reinforcement learning agent.

[0057] The state variable can be represented as the sum of the load demands of all load users in the current period. The action variable can be represented as the load data of each load user transferred to other periods in the current period. The reward function can be a reward function of the intelligent agent defined to maximize the benefit of load transfer.

[0058] Specifically, in this embodiment, the three elements of the corresponding reinforcement learning framework defined based on the load response model can be: state variable S: defined as the sum of the load demands of all load users in the current period of the distribution station area Action A: defined as the load of each load user in the distribution area transferred to other time periods in the current time period A(t) = {L q，m，t，1 , L q，m，t，2 , ..., L q，m，t，T}; Reward function R: In order to maximize the load transfer benefit, the reward function of the agent is defined as:

[0059] Among them, the historical operation data can be the load conditions and electricity price data of each time period in the normal operating state of the distribution station area. In this embodiment, the historical operation data includes historical state variables and historical action variables. That is, the real data of the historical time period corresponding to the state variable S and action variable A defined in the reinforcement learning framework. The historical state variable can be the sum of the load demands of all load users in the distribution station area during the historical period. The historical action variable can be the load data of each load user in the distribution station area transferred to other time periods during the historical period. In this embodiment, the neural network model can be a long short-term memory network (Long Short-Term Memory, LSTM). In this embodiment, the simulation environment mainly fits the factor relationship between the current state variable and the current strategy and the next state variable, that is, the current state S t With action A t These two variables, together with the next state variable S t+1d The relationship between.

[0060] In this embodiment, the LSTM neural network can be used to fit the functional relationship between state variables, action variables and reward functions according to the load conditions and electricity price data of the distribution station area in each time period under normal operation, and the neural network can be used as the simulation environment of the reinforcement learning agent; then, by interacting the current policy network of the reinforcement learning agent with the simulation environment for a set number of times, the network parameters of the policy network are determined according to the real data of the state variables and action variables, and then the load-side resource response data of each time period is determined.

[0061] Through such a setting in this embodiment, the load migration problem is optimized through the enhanced algorithm, and the dynamic interaction between electricity price and consumer behavior is taken into account. Not only the optimization of the power generation side is considered, but also the optimization of the load demand side is considered, and the uncertainty of the load is fully considered, so that the final scheduling strategy is more accurate.

[0062] In this embodiment, optionally, the load-side resource response data for each time period is determined based on the simulation environment and the reinforcement learning agent, including: initializing the network parameters of the policy network and the evaluation network of the reinforcement learning agent; setting the number of times that the reinforcement learning agent interacts with the simulation environment through the current policy network to obtain a sampling trajectory; determining the feedback data based on the sampling trajectory, and updating the network parameters of the policy network and the evaluation network through the feedback data; and determining the load-side resource response data for each time period based on the network parameters.

[0063] Among them, the policy network and the evaluation network are two key components in the agent, which are responsible for generating actions and evaluating the value of the state respectively. In this embodiment, in reinforcement learning, the agent needs to learn the best behavior strategy through interaction with the environment. In order to effectively train the two networks, the policy network and the evaluation network, it is necessary to set reasonable initial parameters for them. These initial parameters will serve as the starting point of network learning and affect the efficiency and effect of the entire training process. The set number of times can be a pre-set number. In this embodiment, the set number of times can be set according to the time period of a day by considering the cost value of a day. The sampling trajectory can be the trajectory information generated during the interaction process obtained by the reinforcement learning agent interacting with the simulation environment 24 times through the current policy network.

[0064] Specifically, in this embodiment, the agent obtains the current state observation from the simulation environment. This state observation can be the complete state of the environment or a partial observation. The agent then selects an action to execute based on the action probability distribution output by the policy network. This process can be random or deterministic (such as directly selecting the action with the highest probability). The agent sends the selected action to the simulation environment, and the environment updates the state based on this action, and gives the corresponding reward and the next state observation. The agent records this series of state observations, actions, and rewards to form a sampling trajectory. The agent repeats the above interaction process a set number of times to obtain a sufficient number of sampling trajectories. These sampling trajectories can be used to evaluate the performance of the policy network and update the parameters of the policy network through optimization algorithms such as gradient descent.

[0065] Among them, the reward data can be a reward value calculated based on the currently generated sampling trajectory. In this embodiment, the specific method of updating the network parameters of the policy network and the evaluation network through the reward data can be to calculate the update gradient of the policy network parameters and the update gradient of the evaluation network according to the reward value calculated based on the currently generated sampling trajectory, and then update the network parameters of the policy network and the evaluation network based on the update gradient of the policy network parameters and the update gradient of the evaluation network respectively.

[0066] In this embodiment, during the training process, the reward value R of each time period and the total reward value R will eventually tend to a stable value. In this embodiment, if the reward value R tends to be stable, the training will be considered completed, and then a policy network and an evaluation network will be obtained. Then the policy network can be directly used to make a decision on the problem of our load-side resource response. When it is determined that the reward R tends to be stable, the value corresponding to the policy network is the final load flexible resource response strategy for each time period, that is, the load-side resource response data for each time period.

[0067] Exemplarily, in this embodiment, the network parameters θ and φ of the agent's policy network π(A|S,θ) and the evaluation network V(S|φ) are initialized; then the agent interacts with the simulation environment 24 times through the current policy network to generate the following sampling trajectory:

[0068] S t ,A t ,R t ,S t+1 ,A t+1 ,R t1 ,…,S t+23 ,A t+23 ,R t+23 ,S t+24 ;

[0069] According to the currently generated sampling trajectory, calculate the return value Gt :

[0070]

[0071] Among them, γ is the discount factor, which is used to adjust the weight of future returns and determines the foresight ability of the strategy obtained by the agent training.

[0072] Then calculate the difference D between the current reward value and the output value of the evaluation network t The specific method is:

[0073] D t =G t -V(S t |φ);

[0074] The specific method of calculating the update gradient of the policy network parameters in this embodiment is:

[0075]

[0076] The specific method of calculating the update gradient of the evaluation network parameters in this embodiment is:

[0077]

[0078] This embodiment updates the parameters of the policy network and the evaluation network:

[0079] θ=θ+ξdθ,φ=φ+ζdφ;

[0080] Among them, ξ and ζ are the learning rates for updating the parameters of the policy network and the evaluation network, respectively.

[0081] Then, in this embodiment, the step of causing the agent to interact with the simulation environment through the current policy network to update the parameters of the policy network and the evaluation network can be repeated until the number of training rounds reaches a preset upper limit.

[0082] In this embodiment, through such a setting, a training environment for a reinforcement learning agent is constructed through an LSTM neural network, without the need for interactive training in a real environment, and the data acquisition cost is lower and the training cost is low.

[0083] S240. Determine the optimal dispatching strategy for the operation of the distribution substation according to the load-side resource response data, so as to regulate the distribution substation based on the optimal dispatching strategy.

[0084] In this embodiment, optionally, the optimal scheduling strategy for the operation of the distribution substation is determined based on the load-side resource response data, including: determining the total load demand of the distribution substation based on the load-side resource response data; determining the power generation data of the power generation side of the distribution substation based on the total load demand; and determining the optimal scheduling strategy for the distribution substation based on the power generation data.

[0085] Among them, the power generation data includes the power generation data of each distributed power source and energy storage device in the distribution station area. In this embodiment, after solving the load-side flexible resource response data, that is, obtaining the load of each load user transferred to other time periods in the current time period, the response data of the load-side resources can be aggregated according to the station area to obtain the total load demand of the distribution station area, and then further control the output of each distributed power source and energy storage device in the distribution station area according to the total load demand of the distribution station area, and then regulate according to the power generation situation of each device on each power generation side, and control the power generation situation of each device to minimize the economic operation cost, so as to obtain the optimal scheduling strategy for the distribution station area.

[0086] Through such a setting in this embodiment, it can be widely applied to the optimal scheduling of various distribution station areas, and does not depend on the model parameters of the station area. Only sufficient historical data is needed to obtain the optimal scheduling strategy of the distribution station area.

[0087] In this embodiment, optionally, the optimal scheduling strategy for the distribution station area is determined based on the power generation data, including: constructing a corresponding second objective function based on the power generation data, and determining a second constraint condition corresponding to the second objective function; and determining the optimal scheduling strategy for the distribution station area based on the second objective function and the second constraint condition.

[0088] Among them, the second objective function can be a function constructed by minimizing the power generation cost determined by the power generation data. The second constraint condition can be a constraint condition set by parameters such as the power generation data in the second objective function, and can be set according to actual needs. The second constraint condition in this embodiment may include but is not limited to generator output constraints, generator minimum start and stop time constraints, spinning reserve constraints, energy storage charging and discharging constraints, and power balance constraints.

[0089] Specifically, in this embodiment, according to the power generation data of each distributed power source and energy storage in the distribution station area, the second objective function constructed to obtain the lowest power generation cost is:

[0090]

[0091] Among them, α 1i , α 2i iα 3i , α 4i , α 5i is the coefficient of power generation cost, P ci，min Indicates the minimum output, γ e， represents the charge and discharge conversion cost of energy storage, U ek Indicates the charge and discharge status of energy storage (0 for charging, 1 for discharging), P ci Indicates generator output, N c 、N e Represent the collection of generators and energy storage respectively.

[0092] In this embodiment, the second constraint condition corresponding to the second objective function may be specifically determined as follows:

[0093] In this embodiment, the generator output constraint may be:

[0094]

[0095] Among them, P ci，max Indicates maximum output, Ram up，i , Ram down，i Indicates the output limit for climbing landslide.

[0096] In this embodiment, the minimum start and stop time constraint of the generator can be:

[0097]

[0098] in, and represent the continuous online and offline time of generator i until time period t-1, and Represent the minimum online and offline time, τ ci，t Indicates the on / off status of the generator.

[0099] In this embodiment, the spinning reserve constraint may be:

[0100]

[0101] Among them, the set N eu It can be expressed as {k|k∈N e And U ek =1}, r j represents an adjustable hyperparameter, and They represent the maximum and minimum output of the uncertain part of intermittent energy resources respectively.

[0102] In this embodiment, the energy storage charge and discharge constraints may be:

[0103]

[0104] in, is the storage capacity of the kth energy storage, ΔT is the length of the time period, the default value is 1, and are the minimum and maximum storage capacity of the kth energy storage, represents the discharge / charge power of the kth energy storage, and are the power in the discharge and charge states respectively, and are the maximum discharge and charge powers of energy storage, τk ∈(0,1] is the energy storage charging and discharging efficiency.

[0105] In this embodiment, the power balance constraint may be:

[0106]

[0107] In this embodiment, the second objective function and the second constraint condition are determined as the optimization model of the power generation side. By solving the optimization model of the power generation side through the algorithm, the economic operation strategy of each power source and energy storage in the substation under the condition of determined demand response can be obtained, that is, the optimal scheduling strategy of the distribution substation.

[0108] Through such a setting in this embodiment, an economic operation dispatching strategy for distribution station areas can be implemented under the conditions of fully considering the demand response characteristics and the interests of various entities in the power market.

[0109] The technical solution of the embodiment of the present invention obtains the load users and electricity price data of each time period in the distribution station area; determines the load response model of each time period based on the load users and electricity price data of each time period; determines the load-side resource response data of each time period based on the load response model and reinforcement learning algorithm; determines the optimal scheduling strategy for the operation of the distribution station area according to the load-side resource response data, so as to regulate the distribution station area based on the optimal scheduling strategy. This technical solution, by taking into account the response characteristics of flexible resources on the load side, realizes the economic operation and scheduling of the distribution station area under the conditions of fully considering the demand response characteristics and the interests of various entities in the power market.

[0110] Embodiment 3

[0111] Figure 3 Schematic diagram of the structure of a distribution station area operation control device provided according to the third embodiment of the present invention. Figure 3 As shown, the device comprises:

[0112] The data acquisition module 310 is used to obtain the load users and electricity price data of each time period in the distribution station area;

[0113] A response data determination module 320, for determining load-side resource response data for each time period based on load users and electricity price data for each time period;

[0114] The dispatch strategy determination module 330 is used to determine the optimal dispatch strategy for the operation of the distribution substation according to the load-side resource response data, so as to regulate the distribution substation based on the optimal dispatch strategy.

[0115] Optionally, the response data determination module 320 includes:

[0116] A load response model determination unit, used to determine the load response model for each time period based on load users and electricity price data for each time period;

[0117] The load-side resource response data determination unit is used to determine the load-side resource response data of each time period based on the load response model and the reinforcement learning algorithm.

[0118] Optionally, a load response model determination unit is used to:

[0119] Determine the load change data of load users under the influence of electricity price data in each period;

[0120] constructing a first objective function according to the load change data, and determining a first constraint condition based on the load change data;

[0121] The load response model for each time period is determined according to the first objective function and the first constraint condition.

[0122] Optionally, the load-side resource response data determination unit includes:

[0123] Define subunits for defining state variables, action variables, and reward functions in reinforcement learning algorithms based on load response models;

[0124] A simulation environment determination subunit is used to fit the functional relationship between state variables, action variables and reward functions using a neural network based on historical operation data of the distribution station area, and determine the simulation environment of the reinforcement learning agent based on the neural network; wherein the historical operation data includes historical state variables and historical action variables;

[0125] The data determination subunit is used to determine the load-side resource response data of each time period based on the simulation environment and the reinforcement learning agent.

[0126] Optionally, a data determination subunit is specifically used to:

[0127] Initialize the network parameters of the policy network and evaluation network of the reinforcement learning agent;

[0128] The reinforcement learning agent interacts with the simulation environment through the current policy network for a set number of times to obtain a sampling trajectory;

[0129] Determine the reward data based on the sampling trajectory, and update the network parameters of the strategy network and the evaluation network through the reward data;

[0130] Determine the load-side resource response data for each time period based on network parameters.

[0131] Optionally, the scheduling strategy determination module 330 includes:

[0132] A load demand determination unit, used to determine the total load demand of the distribution station area according to the load-side resource response data;

[0133] A power generation data determination unit, used to determine the power generation data of the power generation side of the distribution station area according to the total load demand; wherein the power generation data includes the power generation data of the distributed power sources and energy storage in the distribution station area;

[0134] The optimal strategy determination unit is used to determine the optimal dispatching strategy of the distribution station area according to the power generation data.

[0135] Optionally, the optimal strategy determination unit is specifically used to:

[0136] constructing a corresponding second objective function based on the power generation data, and determining a second constraint condition corresponding to the second objective function;

[0137] An optimal scheduling strategy for the distribution station area is determined based on the second objective function and the second constraint condition.

[0138] A distribution station area operation control device provided in an embodiment of the present invention can execute a distribution station area operation control method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0139] Embodiment 4

[0140] Figure 4 1 is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0141] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0142] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0143] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a distribution station area operation control method.

[0144] In some embodiments, the distribution station area operation control method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the distribution station area operation control method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the distribution station area operation control method in any other appropriate manner (for example, by means of firmware).

[0145] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0147] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0149] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0150] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0151] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0152] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling the operation of a distribution station area, characterized in that: include: Obtain the load users and electricity price data of each time period within the distribution station area; Determining load-side resource response data for each time period based on the load users and electricity price data for each time period; An optimal scheduling strategy for the operation of the distribution substation is determined according to the load-side resource response data, so as to regulate the distribution substation based on the optimal scheduling strategy.

2. The method according to claim 1, characterized in that Determining the load-side resource response data for each time period based on the load users and the electricity price data for each time period includes: Determine a load response model for each time period based on the load users and the electricity price data for each time period; The load-side resource response data for each time period is determined based on the load response model and the reinforcement learning algorithm.

3. The method according to claim 2, characterized in that Determining a load response model for each time period based on the load users and the electricity price data for each time period includes: Determine load change data of the load user under the influence of electricity price data in each time period; constructing a first objective function according to the load change data, and determining a first constraint condition based on the load change data; The load response model for each time period is determined according to the first objective function and the first constraint condition.

4. The method according to claim 2, characterized in that: Determining the load side resource response data for each time period based on the load response model and the reinforcement learning algorithm includes: Defining state variables, action variables, and reward functions in a reinforcement learning algorithm based on the load response model; Based on the historical operation data of the distribution station area, a neural network is used to fit the functional relationship between the state variable, the action variable and the reward function, and a simulation environment of the reinforcement learning agent is determined based on the neural network; wherein the historical operation data includes historical state variables and historical action variables; Based on the simulation environment and the reinforcement learning agent, load-side resource response data for each time period is determined.

5. The method according to claim 4, characterized in that Determining load-side resource response data for each time period based on the simulation environment and the reinforcement learning agent includes: Initialize the network parameters of the policy network and evaluation network of the reinforcement learning agent; The reinforcement learning agent interacts with the simulation environment through the current policy network a set number of times to obtain a sampling trajectory; Determine reward data according to the sampling trajectory, and update network parameters of the strategy network and the evaluation network through the reward data; The load-side resource response data for each time period is determined according to the network parameters.

6. The method according to claim 1, characterized in that Determining the optimal dispatching strategy for the operation of the distribution substation area according to the load-side resource response data includes: Determine the total load demand of the distribution station area according to the load-side resource response data; Determine the power generation data of the power generation side of the distribution station area according to the total load demand; wherein the power generation data includes the power generation data of the distributed power sources and energy storage in the distribution station area; An optimal dispatching strategy for the distribution station area is determined based on the power generation data.

7. The method according to claim 6, characterized in that Determining the optimal dispatching strategy of the distribution substation area according to the power generation data includes: constructing a corresponding second objective function based on the power generation data, and determining a second constraint condition corresponding to the second objective function; An optimal scheduling strategy for the distribution station area is determined according to the second objective function and the second constraint condition.

8. A distribution station area operation control device, characterized in that: include: The data acquisition module is used to obtain the load users and electricity price data of each time period in the distribution station area; A response data determination module, used to determine the load-side resource response data for each time period based on the load users and the electricity price data for each time period; A scheduling strategy determination module is used to determine the optimal scheduling strategy for the operation of the distribution substation according to the load-side resource response data, so as to regulate the distribution substation based on the optimal scheduling strategy.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution station area operation control method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the distribution station area operation control method according to any one of claims 1 to 7 when executed.

Images