Self-adaptive regulation and control method, device, equipment and system for load in power distribution area

Abstract

The invention discloses a power distribution area load adaptive regulation and control method, device, equipment and system, and belongs to the technical field of electric power, and the method comprises the steps: obtaining the electric power operation data of a power distribution area micro-grid system in a preset time period, and the power distribution area micro-grid system comprises an energy storage system and a distributed photovoltaic power generation system; preprocessing the power operation data to obtain an operation data set; according to the operation data set, determining a load regulation and control strategy by using an adaptive dynamic programming algorithm; and sending a control instruction to the energy storage system and the distributed photovoltaic power generation system, wherein the control instruction carries the load regulation and control strategy. According to the invention, the self-adaptive regulation and control of the load of the power distribution area are realized, and the energy utilization efficiency and the stability of the low-voltage power distribution network in the operation process can be improved.

Description

Technical Field

[0001] The present application belongs to the field of electric power technology, and in particular, relates to a method, device, equipment and system for adaptively controlling loads in a distribution station area. Background Art

[0002] In related technologies, when photovoltaic and energy storage systems are connected to a low-voltage distribution network together, the system power flow reverses and the distributed photovoltaic inverters are subject to randomness and volatility due to the intensity of solar radiation, resulting in instability in the low-voltage distribution network during operation and low energy utilization. Summary of the invention

[0003] The present application proposes a method, device, equipment and system for adaptively controlling load in a distribution station area to solve the problems of instability and low energy utilization rate in the operation of low-voltage distribution networks existing in the related art.

[0004] In a first aspect, the present application provides a method for adaptively controlling loads in a distribution station area, the method comprising:

[0005] Acquire power operation data of a microgrid system in a distribution substation area within a preset time period, wherein the microgrid system in the distribution substation area includes an energy storage system and a distributed photovoltaic power generation system;

[0006] Preprocessing the power operation data to obtain an operation data set;

[0007] Determine a load control strategy using an adaptive dynamic programming algorithm according to the operating data set;

[0008] A control instruction is sent to the energy storage system and the distributed photovoltaic power generation system, wherein the control instruction carries the load regulation strategy.

[0009] The method for adaptively controlling the load in a distribution station area provided in the embodiment of the present application obtains the power operation data of the microgrid system in the distribution station area within a preset time period, pre-processes the power operation data, obtains an operation data set, and determines the load control strategy based on the operation data set using an adaptive dynamic programming algorithm. The load control strategy is sent to the energy storage system and the distributed photovoltaic power generation system, thereby realizing adaptive control of the load in the distribution station area, achieving optimal scheduling of resources, improving energy utilization efficiency, balancing fluctuations in renewable energy power generation, and quickly responding to load changes or fluctuations in power demand, thereby improving the stability of the low-voltage distribution network during operation.

[0010] According to an embodiment of the present application, determining a load regulation strategy based on the operating data set using an adaptive dynamic programming algorithm includes:

[0011] Determine the optimization problem model of the distribution station area microgrid system;

[0012] According to the operating data set, an adaptive dynamic programming algorithm is used to iteratively calculate the optimization problem model to obtain a load regulation strategy.

[0013] According to one embodiment of the present application, determining the optimization problem model of the distribution station area microgrid system includes:

[0014] Determine the energy balance equation and optimal performance index parameter expression of the distribution station area microgrid system;

[0015] The energy balance equation and the optimal performance index parameter expression are converted by using the optimal control theory to obtain the optimization problem model.

[0016] According to one embodiment of the present application, the energy balance equation is specifically:

[0017] P H (t) = P C (t)+P E (t)+P E (t)P U (t)

[0018] Among them, P H (t) is the rated load of the distribution station area, P C (t) is the charging load of distributed photovoltaic, P E (t) is the capacity of the energy storage system, P U (t) the load consumed by the user;

[0019] The optimal performance indicator parameter expression is specifically:

[0020]

[0021] Among them, J(t) is the performance index, f is the function corresponding to the performance index, P C (k) is the charging load of the distributed photovoltaic at time k, P E (k) is the capacity of the energy storage system at time k.

[0022] According to an embodiment of the present application, the energy balance equation and the optimal performance index parameter expression are converted by using the optimal control theory to obtain the optimization problem model, including:

[0023] Let P C (t) = f(t), P U (t)+1=g(t),P E(t) = u(t), the energy balance equation is converted into a nonlinear equation, which is as follows:

[0024] x(t+1)=f(x(t))+g(x(t))u(x(t))

[0025] Among them, x(t) is the state parameter, u(t) is the control strategy, and t is the time;

[0026] The optimal performance indicator parameter expression is converted into a performance indicator function, and the performance indicator function is as follows:

[0027]

[0028] Among them, U(x(t),u(t))>0 is the performance parameter, and j is the iteration parameter;

[0029] The optimization problem model is defined as minimizing the performance index function through the optimal control strategy. The theoretical expression of the optimal performance index function is:

[0030]

[0031] According to the Bellman principle, the optimal performance index function satisfies the following formula:

[0032]

[0033] According to an embodiment of the present application, the method of iteratively calculating the optimization problem model based on the operating data set and using an adaptive dynamic programming algorithm to obtain a load regulation strategy includes:

[0034] Initialize the parameters of the model network, the judgment network, and the execution network;

[0035] Obtain current status data and control strategy;

[0036] Inputting the state data and control strategy at the current moment into the model network to obtain the state data at the next moment;

[0037] Inputting the state data at the current moment and the output result of the model network into the evaluation network to calculate the value of the performance indicator function;

[0038] Inputting the output results of the model network and the evaluation network into the execution network to obtain the control strategy at the next moment;

[0039] Through a feedback mechanism, the output result of the execution network is applied to the distribution substation microgrid system to obtain the actual response data of the system;

[0040] According to the actual response data of the system and the control strategy at the next moment, the load regulation strategy is obtained through continuous iteration with the goal of minimizing the value of the performance indicator function.

[0041] In the above technical solution, by using the ADP algorithm, the optimization problem model is iteratively calculated to obtain the load control strategy, thereby realizing the application of the ADP algorithm in the field of power distribution and utilization, which can improve the energy utilization efficiency and the stability of the low-voltage distribution network during operation.

[0042] According to one embodiment of the present application, after sending the control instruction to the energy storage system and the distributed photovoltaic power generation system, the method further includes:

[0043] Acquiring status information of the energy storage system and the distributed photovoltaic power generation system;

[0044] If there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system, a first prompt message is sent, and the first prompt message is used to prompt that there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system.

[0045] In a second aspect, the present application provides a load adaptive control device for a distribution station area, the device comprising:

[0046] An acquisition unit, used to acquire power operation data of a microgrid system in a distribution station area within a preset time period, wherein the microgrid system in the distribution station area includes an energy storage system and a distributed photovoltaic power generation system;

[0047] A preprocessing unit, used for preprocessing the power operation data to obtain an operation data set;

[0048] A determination unit, configured to determine a load regulation strategy based on the operating data set by using an adaptive dynamic programming algorithm;

[0049] A sending unit is used to send control instructions to the energy storage system and the distributed photovoltaic power generation system, wherein the control instructions carry the load regulation strategy.

[0050] In the above technical scheme, by obtaining the power operation data of the microgrid system in the distribution station area within a preset time period, the power operation data is preprocessed to obtain an operation data set, and according to the operation data set, an adaptive dynamic programming algorithm is used to determine the load control strategy, and the load control strategy is sent to the energy storage system and the distributed photovoltaic power generation system, thereby realizing adaptive control of the load in the distribution station area, achieving optimal scheduling of resources, improving energy utilization efficiency, balancing fluctuations in renewable energy generation, and quickly responding to load changes or fluctuations in power demand, thereby improving the stability of the low-voltage distribution network during operation.

[0051] In a third aspect, the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for adaptively controlling the load in a distribution station area as described in the first aspect above is implemented.

[0052] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for adaptively controlling loads in a distribution station area as described in the first aspect above is implemented.

[0053] In a fifth aspect, the present application provides a distribution station area microgrid system, comprising: an energy storage system, a distributed photovoltaic power generation system, and a terminal device as described in the third aspect, wherein the terminal device communicates with the energy storage system and the distributed photovoltaic power generation system via a power line.

[0054] In a sixth aspect, the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method for adaptively controlling loads in a distribution station area as described in the first aspect.

[0055] In a seventh aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for adaptively controlling loads in a distribution station area as described in the first aspect above.

[0056] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0058] Figure 1 It is a flowchart of a method for adaptively controlling loads in a distribution station area provided in some embodiments of the present application;

[0059] Figure 2 This is a flow chart of using an adaptive dynamic programming algorithm to determine a load control strategy provided by some embodiments of the present application.

[0060] Figure 3 is a brief structural diagram of a distribution station area microgrid system provided in some embodiments of the present application;

[0061] Figure 4 It is a schematic diagram of the structure of a load adaptive control device for a distribution station area provided in some embodiments of the present application;

[0062] Figure 5is a schematic diagram of the structure of a terminal device provided in some embodiments of the present application;

[0063] Figure 6 It is a schematic diagram of a distribution station area microgrid system provided in some embodiments of the present application. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0065] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0066] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0067] With the continuous access of distributed photovoltaics, the penetration rate of distributed photovoltaics in the distribution network continues to increase. Although the addition of distributed photovoltaics has brought convenience and some economic benefits to users, it has some adverse effects on the safe operation of low-voltage distribution, such as the replacement flow at the peak of photovoltaic power generation, which will cause voltage to exceed the standard.

[0068] In order to solve the problem of unstable new energy load, batteries can be gradually configured for low-voltage distribution areas. The configuration of energy storage brings many benefits. First, it stores the energy of photovoltaic power generation during the period of high light intensity. Second, it alleviates the uncertainty, intermittency and volatility of photovoltaic power generation. Third, it solves the problem of reverse overload in low-voltage distribution areas. However, for low-voltage distribution areas equipped with photovoltaic and energy storage systems, load regulation has always been a challenge that needs to be faced.

[0069] At present, there are abundant control measures and methods for medium and high voltage, but there is less research and application on control strategies for low voltage power distribution and power consumption. In addition, the characteristics of high proportion of power electronic equipment and high proportion of new energy access to low voltage distribution network bring greater challenges. The current load control in low voltage distribution and power consumption areas has the following pain points:

[0070] (1) Photovoltaic access to low-voltage distribution networks brings instability: With the continuous development of high-proportion photovoltaic access to distribution network technology, the more traditional planning and design of the original distribution network can no longer adapt to the impact of photovoltaic grid connection on the distribution network. After a high proportion of photovoltaic access to the distribution network, the system current will flow in reverse, and the node voltage distribution will change, thereby reducing the power quality and operation reliability of the distribution network; because many factors such as solar radiation intensity, photovoltaic power generation device temperature and on-site environment will have a certain impact on photovoltaic output, it has obvious randomness and volatility, increasing the uncertainty of distribution network system operation.

[0071] (2) Lack of effective control measures after energy storage is connected to the low-voltage distribution grid: The active distribution network connected to the energy storage system can achieve peak shaving and valley filling by reasonably regulating the energy storage charging and discharging power, thereby effectively reducing the impact of node voltage fluctuations caused by distributed photovoltaic grid connection. Although the distributed energy storage system can quickly and accurately respond to system control instructions to optimize the control of the grid-connected energy storage system, thereby achieving optimization effects such as reducing node voltage fluctuations and reducing system network losses. However, with the continuous increase in the grid-connected capacity of photovoltaic and energy storage systems, there is a lack of control strategies that combine photovoltaic and energy storage.

[0072] (3) The application of intelligent algorithms in power systems is relatively rare: With the increasing number of intelligent devices installed in low-voltage power distribution stations, information transmission, processing and edge computing capabilities are also gradually improving. However, the computing power of intelligent devices has not been fully utilized, and the embedded software of intelligent devices has yet to be fully explored. The application of control strategies based on intelligent algorithms in the power distribution field is still relatively lacking.

[0073] In order to solve the above problems, the embodiments of the present application provide a method, device, equipment and system for adaptively controlling loads in a distribution station area. The following is a detailed description of the method, device, equipment and system for adaptively controlling loads in a distribution station area provided by the embodiments of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0074] Figure 1 is a flow chart of a method for adaptively controlling loads in a distribution station area provided in some embodiments of the present application, such as Figure 1 As shown, the method for adaptively controlling load in a distribution station area includes: step 110, step 120, step 130 and step 140.

[0075] Step 110: Acquire power operation data of a microgrid system in a distribution substation area within a preset time period, wherein the microgrid system in the distribution substation area includes an energy storage system and a distributed photovoltaic power generation system;

[0076] The distribution station microgrid system is a comprehensive system that integrates multiple technical elements such as modern power technology, distributed energy, energy storage technology, and smart grid. It is mainly deployed at the station level of the distribution network.

[0077] The microgrid system in the distribution area includes: distributed photovoltaic power generation system (it should be noted that wind power generation can also be used as a supplementary energy source), energy storage system, load management system, power conversion equipment, smart grid and communication system, protection and control system, etc. Among them, the energy storage system is used to store excess renewable energy to provide backup power when energy is insufficient. The energy storage system helps to improve the reliability and flexibility of the microgrid, balance load fluctuations, and ensure stable operation of the system. The load management system can monitor and adjust the load demand in the area in real time, optimize the scheduling according to the power supply situation, and ensure the power supply balance and reliability of the system. Power conversion equipment includes inverters, transformers, and DC / AC conversion equipment, which are responsible for the conversion and scheduling of different types of energy, so that the microgrid can flexibly access different types of distributed energy and support bidirectional current flow. Microgrids require the support of smart grid technologies, including smart sensors, monitoring systems, and communication facilities. These technologies can realize real-time monitoring and adjustment of the power grid status and exchange information through communication networks (such as optical fiber, wireless networks, etc.). The management system of the microgrid can make decisions based on real-time data, automatically adjust energy flow, and optimize energy use. To ensure the safe and stable operation of the microgrid system, it is usually equipped with a protection system with fault detection, automatic isolation, and automatic recovery functions. When a fault occurs or the external grid connection is disconnected, the microgrid can operate independently to ensure the power supply to users in the substation area.

[0078] The embodiment of the present application first obtains the power operation data of the microgrid system in the distribution station area within a preset time period, and optionally obtains the power operation data through real-time monitoring, data collection, etc. The power operation data includes: the power generation of the distributed photovoltaic power generation system, the charging amount and discharge amount of the energy storage system, the load demand, the load forecast data, the voltage, the power, the frequency, the equipment operation status, etc.

[0079] Step 120: pre-process the power operation data to obtain an operation data set;

[0080] Optionally, preprocessing of the distribution station area microgrid obtained within a preset time period includes: data cleaning, missing value processing, outlier detection, data smoothing and denoising, data normalization, time series processing, feature engineering, etc.

[0081] An operation data set is obtained by preprocessing the power operation data of the microgrid system in the distribution station area within a preset time period.

[0082] Step 130: Determine a load control strategy using an adaptive dynamic programming algorithm according to the operating data set;

[0083] With the development of computer algorithms and artificial intelligence, the adaptive dynamic programming algorithm (ADP) based on reinforcement learning and optimal control theory is very helpful for solving control systems with high nonlinearity and short adjustment time. With the gradual maturity of the adaptive dynamic programming algorithm and the development of neural network approximation algorithms, this control method has been applied to many complex control systems. In recent years, the adaptive dynamic programming algorithm has been widely used in power dispatching, energy system optimization and other fields. In addition, the large-area coverage of local communication equipment and side terminals on power lines provides a strong hardware support system for new algorithms.

[0084] The ADP algorithm uses the principle of reinforcement learning and approximates the performance index function and control strategy in the dynamic programming equation through the function approximation structure, which can effectively solve the decision-making problem of nonlinear dynamic systems. The ADP algorithm includes: a model network, a judgment network and an execution network, wherein the model network is used to estimate the state at the next moment according to the state and control action of the system at the previous moment, the judgment network is used to approximate the performance evaluation function, evaluate the state prediction error of the model network, and reduce the error, the execution network is used to combine the output results of the first two networks to obtain the control strategy at the next moment, and the execution network maps the relationship between state variables and control quantities. The embodiment of the present application uses an adaptive dynamic programming algorithm to determine the load control strategy based on the operating data set, and achieves the optimal and stable load control of the distribution station microgrid system through algorithm tuning.

[0085] Step 140: Send a control instruction to the energy storage system and the distributed photovoltaic power generation system, wherein the control instruction carries the load regulation strategy.

[0086] The above steps 110 to 130 are implemented in a real environment. The algorithm is packaged into an embedded APP, built into the edge smart terminal, and the control instructions of the algorithm are sent to the battery management system of the energy storage system and the photovoltaic inverter in the distributed photovoltaic power generation system through the local communication device.

[0087] The Substation Smart Convergence Terminal (SCU) is a side smart device that has been widely used in low-voltage platforms. The above algorithms are packaged as micro-applications and embedded in containers within the SCU.

[0088] Uplink communication can upload data to the cloud system through wireless communication, and downlink communication can connect the battery management system of the energy storage system and the photovoltaic inverter in the distributed photovoltaic power generation system through a wired connection and send control instructions.

[0089] The SCU first collects power operation data from the electricity meter, energy storage device, and distributed photovoltaic inverter. Then, the APP in the SCU calculates the collected power operation data and obtains the load regulation strategy through the embedded algorithm. Once the load regulation strategy is generated, there will be a trigger in the application to send control commands to the energy storage system and distributed photovoltaic power generation system to ensure optimal energy utilization.

[0090] It should be noted that sending control commands to the energy storage system and the distributed photovoltaic power generation system can be understood as sending control commands to the energy storage battery management system and the photovoltaic inverter.

[0091] In some embodiments, after sending the control instruction to the energy storage system and the distributed photovoltaic power generation system, the method further includes:

[0092] Acquiring status information of the energy storage system and the distributed photovoltaic power generation system;

[0093] If there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system, a first prompt message is sent, and the first prompt message is used to prompt that there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system.

[0094] It is understandable that after sending control instructions to the energy storage system and the distributed photovoltaic power generation system, the cloud system collects some status information of the SCU so that the operation and maintenance personnel can monitor the status of the energy storage system and / or the distributed photovoltaic power generation system in real time.

[0095] The method for adaptively controlling the load in a distribution station area provided in the embodiment of the present application obtains the power operation data of the microgrid system in the distribution station area within a preset time period, pre-processes the power operation data, obtains an operation data set, and determines the load control strategy based on the operation data set using an adaptive dynamic programming algorithm. The load control strategy is sent to the energy storage system and the distributed photovoltaic power generation system, thereby realizing adaptive control of the load in the distribution station area, achieving optimal scheduling of resources, improving energy utilization efficiency, balancing fluctuations in renewable energy power generation, and quickly responding to load changes or fluctuations in power demand, thereby improving the stability of the low-voltage distribution network during operation.

[0096] Optional, Figure 2 1 is a flow chart of using an adaptive dynamic programming algorithm to determine a load control strategy according to some embodiments of the present application. Figure 2As shown, according to the operating data set, using an adaptive dynamic programming algorithm, determining the load regulation strategy further includes: step 210 and step 220.

[0097] Step 210, determining the optimization problem model of the distribution station area microgrid system;

[0098] The embodiment of the present application adopts an adaptive dynamic programming algorithm to solve the load control problem of the microgrid system in the distribution station area, constructs a mathematical model of the system, and then converts the mathematical model into an optimization problem model.

[0099] In some embodiments, determining the optimization problem model of the distribution substation microgrid system includes:

[0100] Determine the energy balance equation and optimal performance index parameter expression of the distribution station area microgrid system;

[0101] The energy balance equation and the optimal performance index parameter expression are converted by using the optimal control theory to obtain the optimization problem model.

[0102] Specifically, consider the rated load of the low voltage area as P H (t), the charging load of the distributed photovoltaic system is P C (t), the capacity of the energy storage system in the substation is P E (t). Figure 3 It is a brief structural diagram of a distribution station area microgrid system provided in some embodiments of the present application.

[0103] The energy consumed by the user side is related to the energy released by the energy storage, expressed as P E (t)P U (t).

[0104] For the entire substation area, an energy balance equation of the microgrid system of the distribution substation area is determined.

[0105] In some embodiments, the energy balance equation is specifically:

[0106] P H (t) = P C (t)+P E (t)+P E (t)P U (t)

[0107] Among them, P H (t) is the rated load of the distribution station area, P C (t) is the charging load of distributed photovoltaic, P E (t) is the capacity of the energy storage system, P U (t) is the load consumed by the user.

[0108] Among them, P E (t) Satisfaction Indicates the maximum and minimum energy of the energy storage system. For an actual system, the charge and discharge curves of the energy storage system are very complex and irregular. In the embodiment of the present application, the energy storage system simulates its charge and discharge energy by means of neural network approximation.

[0109] For the entire distribution substation area microgrid system, an optimal performance parameter is set with the minimum energy consumption as the indicator.

[0110] Let J(t) represent this index, and the optimal performance index parameter expression is specifically:

[0111]

[0112] Among them, J(t) is the performance index, f is the function corresponding to the performance index, P C (k) is the charging load of the distributed photovoltaic power generation system at time k, P E (k) is the capacity of the energy storage system at time k.

[0113] The actual power consumption can be calculated between the user's meter and the total meter in the low distribution area.

[0114] In some embodiments, based on the physical characteristics of the microgrid system in the distribution station area, the energy balance equation and the optimal performance indicator parameter expression are converted using the method of optimal control theory to obtain the optimal solution.

[0115] The optimal control theory is used to transform the energy balance equation and the optimal performance index parameter expression to obtain the optimization problem model, including:

[0116] Let P C (t) = f(t), P U (t)+1=g(t),P E (t) = u(t), so it can be transformed into a nonlinear system solution problem, and the energy balance equation is converted into a nonlinear equation. The nonlinear equation is as follows:

[0117] x(t+1)=f(x(t))+g(x(t))u(x(t))

[0118] Among them, x(t) is the state parameter, u(t) is the control strategy, and t is the time;

[0119] The optimal performance indicator parameter expression is converted into a performance indicator function, and the performance indicator function is as follows:

[0120]

[0121] Among them, U(x(t),u(t))>0 is the performance parameter, and j is the iteration parameter;

[0122] The optimization problem model is defined as minimizing the performance index function through the optimal control strategy. The theoretical expression of the optimal performance index function is:

[0123]

[0124] According to the Bellman optimality principle, the optimal performance index function satisfies the following formula:

[0125]

[0126] Step 220: According to the operating data set, an adaptive dynamic programming algorithm is used to iteratively calculate the optimization problem model to obtain a load control strategy.

[0127] Due to the nonlinear characteristics of the unknown function, a neural network is introduced to approximate the unknown function to obtain a solution.

[0128] Take any semidefinite function (the initial function is set to 0), the iterative control law and the iterative performance index function are continuously updated as the iterative index continues to increase, and the performance index function eventually converges to the solution of the HJB equation.

[0129] In some embodiments, the optimization problem model is iteratively calculated using the ADP algorithm to obtain a load regulation strategy, including:

[0130] Initialize the parameters of the model network, the judgment network, and the execution network;

[0131] Obtain current status data and control strategy;

[0132] Inputting the state data and control strategy at the current moment into the model network to obtain the state data at the next moment;

[0133] Inputting the state data at the current moment and the output result of the model network into the evaluation network to calculate the value of the performance indicator function;

[0134] Inputting the output results of the model network and the evaluation network into the execution network to obtain the control strategy at the next moment;

[0135] Through a feedback mechanism, the output result of the execution network is applied to the distribution substation microgrid system to obtain the actual response data of the system;

[0136] According to the actual response data of the system and the control strategy at the next moment, the load regulation strategy is obtained through continuous iteration with the goal of minimizing the value of the performance indicator function.

[0137] It can be understood that the implementation steps of the ADP algorithm include: 1) initializing the parameters of the model network, the judgment network and the execution network, 2) preparing the input and output data, the input data includes the state data such as the load power and the capacity of the energy storage device, and the output data includes the control strategy. 3) Model network calculation, the model network receives the state data and control strategy at the current moment, and estimates the state data at the next moment; 4) Judgment network calculation, the judgment network receives the state data at the current moment and the output of the model network, and calculates the value of the performance index function; 5) Execution network calculation, combining the output results of the first two networks to obtain the control strategy at the next moment; 6) Through the feedback mechanism, the output of the execution network is applied to the system, and the actual response of the system is observed; 7) According to the actual response data of the system and the control strategy at the next moment, with the minimum value of the performance index function as the goal, the load regulation strategy is obtained through continuous iteration.

[0138] The specific solution process of ADP is as follows:

[0139] Let the iteration parameter j = 0, and we can get the initial performance index function J0(x(t)) = 0. Therefore, we can get the initial control strategy:

[0140]

[0141] The next performance indicator function is:

[0142] J1(x(t))=U(x(t),u0(x(t)))+J0(x(t+1))

[0143] For iteration parameters j = 1, 2, 3, ..., the ADP algorithm can be iteratively calculated using the following two equations:

[0144]

[0145] J j+1 (x(t))=U(x(t),u j (x(t)))+J j (x(t+1))

[0146] As j→∞, the optimal performance index function and the optimal control strategy can be obtained. The optimal control strategy is the load regulation strategy.

[0147] The method for adaptively controlling loads in a distribution station area provided in the embodiment of the present application utilizes the ADP algorithm to iteratively calculate the optimization problem model to obtain a load control strategy, thereby realizing the application of the ADP algorithm in the field of power distribution and utilization, and can improve energy utilization efficiency and the stability of the low-voltage distribution network during operation.

[0148] Figure 4 is a schematic diagram of the structure of a load adaptive control device for a distribution station area provided in some embodiments of the present application, such as Figure 4 As shown, the load adaptive control device 400 for a distribution station area includes: an acquisition unit 410, a preprocessing unit 420, a determination unit 430 and a sending unit 440, wherein:

[0149] An acquisition unit 410 is used to acquire power operation data of a microgrid system in a distribution station area within a preset time period, wherein the microgrid system in the distribution station area includes an energy storage system and a distributed photovoltaic power generation system;

[0150] A preprocessing unit 420, configured to preprocess the power operation data to obtain an operation data set;

[0151] A determination unit 430 is used to determine a load control strategy based on the operating data set using an adaptive dynamic programming algorithm;

[0152] The sending unit 440 is used to send control instructions to the energy storage system and the distributed photovoltaic power generation system, and the control instructions carry the load regulation strategy.

[0153] In the above technical scheme, the power operation data of the microgrid system in the distribution station area within a preset time period is obtained, and the power operation data is preprocessed to obtain an operation data set. According to the operation data set, an adaptive dynamic programming algorithm is used to determine the load control strategy, and the load control strategy is sent to the energy storage system and the distributed photovoltaic power generation system. The adaptive control of the load in the distribution station area is realized, the energy utilization efficiency is improved, and the fluctuations in renewable energy power generation can be balanced, and the load changes or fluctuations in power demand can be quickly responded to, thereby improving the stability of the low-voltage distribution network during operation.

[0154] In some embodiments, the determining unit 430 is configured to:

[0155] Determine the optimization problem model of the distribution station area microgrid system;

[0156] According to the operating data set, an adaptive dynamic programming algorithm is used to iteratively calculate the optimization problem model to obtain a load regulation strategy.

[0157] In some embodiments, determining the optimization problem model of the distribution substation microgrid system includes:

[0158] Determine the energy balance equation and optimal performance index parameter expression of the distribution station area microgrid system;

[0159] The energy balance equation and the optimal performance index parameter expression are converted by using the optimal control theory to obtain the optimization problem model.

[0160] In some embodiments, the energy balance equation is specifically:

[0161] P H (t) = P C (t)+P E (t)+P E (t)P U (t)

[0162] Among them, P H (t) is the rated load of the distribution station area, P C (t) is the charging load of distributed photovoltaic, P E (t) is the capacity of the energy storage system, P U (t) the load consumed by the user;

[0163] The optimal performance indicator parameter expression is specifically:

[0164]

[0165] Among them, J(t) is the performance index, f is the function corresponding to the performance index, P C (k) is the charging load of the distributed photovoltaic at time k, P E (k) is the capacity of the energy storage system at time k.

[0166] In some embodiments, the use of optimal control theory to convert the energy balance equation and the optimal performance indicator parameter expression to obtain an optimization problem model includes:

[0167] Let P C (t) = f(t), P U (t)+1=g(t),P E (t) = u(t), the energy balance equation is converted into a nonlinear equation, which is as follows:

[0168] x(t+1)=f(x(t))+g(x(t))u(x(t))

[0169] Among them, x(t) is the state parameter, u(t) is the control strategy;

[0170] The optimal performance indicator parameter expression is converted into a performance indicator function, and the performance indicator function is as follows:

[0171]

[0172] Among them, U(x(t),u(t))>0 is the performance parameter, and j is the iteration parameter;

[0173] The optimization problem model is defined as minimizing the performance index function through the optimal control strategy. The theoretical expression of the optimal performance index function is:

[0174]

[0175] According to the Bellman principle, the optimal performance index function satisfies the following formula:

[0176]

[0177] In some embodiments, the method of iteratively calculating the optimization problem model based on the operating data set and using an adaptive dynamic programming algorithm to obtain a load regulation strategy includes:

[0178] Initialize the parameters of the model network, the judgment network, and the execution network;

[0179] Obtain current status data and control strategy;

[0180] Inputting the state data and control strategy at the current moment into the model network to obtain the state data at the next moment;

[0181] Inputting the state data at the current moment and the output result of the model network into the evaluation network to calculate the value of the performance indicator function;

[0182] Inputting the output results of the model network and the evaluation network into the execution network to obtain the control strategy at the next moment;

[0183] Through a feedback mechanism, the output result of the execution network is applied to the distribution substation microgrid system to obtain the actual response data of the system;

[0184] According to the actual response data of the system and the control strategy at the next moment, the load regulation strategy is obtained through continuous iteration with the goal of minimizing the value of the performance indicator function.

[0185] In some embodiments, the acquisition unit 410 is further used to: acquire status information of the energy storage system and the distributed photovoltaic power generation system;

[0186] The sending unit 440 is also used to: if there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system, send a first prompt message, and the first prompt message is used to prompt that there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system.

[0187] The distribution station area load adaptive control device 400 in the embodiment of the present application can be an electronic device, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook, a personal digital assistant (personal digital assistant, PDA), a vehicle-mounted device, a wearable device, a wireless terminal or computing device in industrial control, etc., and the non-mobile electronic device can be a server, a network attached storage (Network Attached Storage, NAS) or a personal computer (personal computer, PC), etc., which is not specifically limited in the present application.

[0188] The distribution station area load adaptive control device 400 in the embodiment of the present application may be a device having an operating system. The operating system may be a Microsoft (Windows) operating system, an Android (Android) operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0189] The distribution station area load adaptive control device 400 provided in the embodiment of the present application can achieve Figures 1 to 3 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0190] In some embodiments, Figure 5 As shown, an embodiment of the present application also provides a terminal device 500, including a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the program is executed by the processor 501, each process of the above-mentioned distribution station area load adaptive control method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0191] It should be noted that the terminal devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0192] The embodiment of the present application also provides a distribution substation microgrid system, including: an energy storage system, a distributed photovoltaic power generation system, and a terminal device as described above, wherein the terminal device communicates with the energy storage system and the distributed photovoltaic power generation system via a power line. It should be noted that the distribution substation microgrid system also includes other systems, which can be referred to in related technologies and will not be described in detail here.

[0193] Figure 6 Schematic diagram of a distribution substation microgrid system provided in some embodiments of the present application. Figure 6 As shown in the figure, the distribution substation microgrid system includes:

[0194] Cloud system: It has the ability to analyze communication signals, decrypt data, and display data. It receives remote communication information from the intelligent fusion terminal in the substation area and provides intuitive information display and decision-making basis for distribution network managers.

[0195] The intelligent fusion terminal in the substation area (i.e. the above-mentioned terminal device) is a low-voltage distribution substation area-side intelligent device. Its main control chip adopts a Cortex-A7 architecture single-core 4-core processor with a main frequency of 1.2GHz. It uses container technology to realize the simultaneous operation of multiple containers, supports data communication between containers, and realizes data interactive sharing. The ADP algorithm involved in this application is packaged as an application APP, deployed in a container, and runs in an intelligent device.

[0196] ADP algorithm: Construct a mathematical model of a low-voltage distribution station area configured with low-voltage distributed photovoltaics and energy storage, apply the ADP algorithm to optimize the load configuration of energy storage and photovoltaics, form the optimal control instructions, and send the instructions to the photovoltaic inverter and energy storage battery management system.

[0197] Power line communication: It realizes local communication between the intelligent fusion terminal in the substation area and the photovoltaic inverter and energy storage. The instructions of the smart devices on the side are sent to the photovoltaic inverter and energy storage battery management system through the power line carrier.

[0198] Through remote upgrade, the ADP algorithm is installed into the edge intelligent terminal equipment, and the data information that needs to be expanded is accessed by improving the cloud system. The corresponding uplink communication protocol is expanded on the photovoltaic inverter and energy storage battery equipment side, and then the edge intelligent terminal can collect photovoltaic and energy storage power information through the power line carrier. The built-in ADP algorithm uses power information as the input source and performs online calculations. The calculated optimization control instructions are sent to the photovoltaic inverter and energy storage system through the power line carrier.

[0199] The distribution substation microgrid system realizes adaptive control of the distribution substation load, can achieve optimal scheduling of resources, improve energy efficiency, balance fluctuations in renewable energy generation, and quickly respond to changes in load or fluctuations in power demand, thereby improving the stability of the low-voltage distribution network during operation.

[0200] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned distribution station area load adaptive control method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0201] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0202] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned distribution station area load adaptive control method when executed by a processor.

[0203] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0204] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned distribution station area load adaptive control method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0205] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0206] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0207] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods 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 such an understanding, the technical solution of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0208] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0209] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0210] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for adaptively controlling load in a distribution station area, characterized in that: include: Acquire power operation data of a microgrid system in a distribution substation area within a preset time period, wherein the microgrid system in the distribution substation area includes an energy storage system and a distributed photovoltaic power generation system; Preprocessing the power operation data to obtain an operation data set; Determine a load control strategy using an adaptive dynamic programming algorithm according to the operating data set; A control instruction is sent to the energy storage system and the distributed photovoltaic power generation system, wherein the control instruction carries the load regulation strategy.

2. The method for adaptively controlling load in a distribution station area according to claim 1 is characterized in that: Determining the load control strategy by using an adaptive dynamic programming algorithm according to the operating data set includes: Determine the optimization problem model of the distribution station area microgrid system; According to the operating data set, an adaptive dynamic programming algorithm is used to iteratively calculate the optimization problem model to obtain a load regulation strategy.

3. The method for adaptively controlling load in a distribution station area according to claim 2 is characterized in that: The step of determining the optimization problem model of the distribution station area microgrid system comprises: Determine the energy balance equation and optimal performance index parameter expression of the distribution station area microgrid system; The energy balance equation and the optimal performance index parameter expression are converted by using the optimal control theory to obtain the optimization problem model.

4. The method for adaptively controlling load in a distribution station area according to claim 3 is characterized in that: The energy balance equation is specifically: P H (t)=P C (t)+P E (t)+P E (t)P U (t) Among them, P H (t) is the rated load of the distribution station area, P C (t) is the charging load of distributed photovoltaic, P E (t) is the capacity of the energy storage system, P U (t) the load consumed by the user; The optimal performance indicator parameter expression is specifically: Among them, J(t) is the performance index, f is the function corresponding to the performance index, P C (k) is the charging load of the distributed photovoltaic at time k, P E (k) is the capacity of the energy storage system at time k.

5. The method for adaptively controlling load in a distribution station area according to claim 3 is characterized in that: The optimal control theory is used to transform the energy balance equation and the optimal performance index parameter expression to obtain the optimization problem model, including: Let P C (t) = f(t), P U (t)+1=g(t),P E (t) = u(t), the energy balance equation is converted into a nonlinear equation, which is as follows: x(t+1)=f(x(t))+g(x(t))u(x(t)) Among them, x(t) is the state parameter, u(t) is the control strategy, and t is the time; The optimal performance indicator parameter expression is converted into a performance indicator function, and the performance indicator function is as follows: Among them, U(x(t),u(t))>0 is the performance parameter, and j is the iteration parameter; The optimization problem model is defined as minimizing the performance index function through the optimal control strategy. The theoretical expression of the optimal performance index function is: According to the Bellman principle, the optimal performance index function satisfies the following formula:

6. The method for adaptively controlling load in a distribution station area according to claim 2, characterized in that: The method of iteratively calculating the optimization problem model according to the operating data set and using an adaptive dynamic programming algorithm to obtain a load regulation strategy includes: Initialize the parameters of the model network, the judgment network, and the execution network; Obtain current status data and control strategy; Inputting the state data and control strategy at the current moment into the model network to obtain the state data at the next moment; Inputting the state data at the current moment and the output result of the model network into the evaluation network to calculate the value of the performance indicator function; Inputting the output results of the model network and the evaluation network into the execution network to obtain the control strategy at the next moment; Through a feedback mechanism, the output result of the execution network is applied to the distribution substation microgrid system to obtain the actual response data of the system; According to the actual response data of the system and the control strategy at the next moment, the load regulation strategy is obtained through continuous iteration with the goal of minimizing the value of the performance indicator function.

7. The method for adaptively controlling load in a distribution station area according to claim 1, characterized in that: After sending the control instruction to the energy storage system and the distributed photovoltaic power generation system, the method further includes: Acquiring status information of the energy storage system and the distributed photovoltaic power generation system; If there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system, a first prompt message is sent, where the first prompt message is used to prompt that there is an abnormality in the status information of the energy storage system and / or the distributed photovoltaic power generation system.

8. A load adaptive control device for a distribution station area, characterized in that: include: An acquisition unit, used to acquire power operation data of a microgrid system in a distribution station area within a preset time period, wherein the microgrid system in the distribution station area includes an energy storage system and a distributed photovoltaic power generation system; A preprocessing unit, used for preprocessing the power operation data to obtain an operation data set; A determination unit, configured to determine a load regulation strategy based on the operating data set by using an adaptive dynamic programming algorithm; A sending unit is used to send control instructions to the energy storage system and the distributed photovoltaic power generation system, wherein the control instructions carry the load regulation strategy.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for adaptively controlling the load in a distribution station area according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for adaptively controlling load in a distribution station area as described in any one of claims 1 to 7 is implemented.

Images