Scheduling method and device based on micro-grid coupling traffic system, equipment and medium
By acquiring the data of the microgrid and the electric transport unit, building utility functions and using reinforcement learning algorithms, the energy scheduling problem of the microgrid under incomplete information conditions is solved, and the accuracy and reliability of energy scheduling are achieved.
Patent Information
- Application Number
- CN202411012988.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-26
AI Technical Summary
The existing microgrid energy scheduling methods cannot effectively perform energy scheduling under incomplete information conditions, resulting in the problems of information isolation and maximization of benefits.
By obtaining the microgrid's own data, the interactive data between the microgrids and the interactive data of the electric transport unit, a utility function is constructed, and a reinforcement learning algorithm is used to solve it, the goal is determined to achieve energy transfer and meet the independence of each microgrid. Maximize returns.
Under incomplete information conditions, the energy scheduling of the microgrid coupled transportation system is realized, which improves the accuracy and reliability of the scheduling method and meets the charging requirements of the microgrid.
Smart Images

Figure CN118971078A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of microgrid technology, and in particular to a scheduling method and device, equipment and medium based on a microgrid coupled transportation system. Background Art
[0002] The microgrid coupled transportation system is a system consisting of multiple microgrids and networked electric transportation equipment (such as networked electric vehicles) connected to each microgrid. In this system, each microgrid generates energy and the networked electric transportation equipment consumes energy. The number of networked electric vehicles connected to each microgrid is not fixed, resulting in excess or insufficient energy. Therefore, the surplus energy can be transferred between multiple microgrids to achieve energy scheduling.
[0003] At present, when performing energy scheduling, each microgrid needs to obtain information (such as production capacity, remaining energy, etc.), benefits and energy scheduling strategies (such as which microgrids to transfer energy to and how much energy to transfer) from other microgrids, and then determine its own energy scheduling strategy. However, the goal of the existing microgrid energy scheduling method is to maximize the overall benefits of all microgrids, that is, the existing microgrid energy scheduling method belongs to a cooperative game. But each microgrid actually tends to maximize its own benefits, which is a non-cooperative game. In addition, the existing microgrid energy scheduling method requires that microgrids can obtain each other's benefits and energy scheduling strategies. This is actually a complete information game, which requires that microgrids can fully exchange information. However, the benefits and energy scheduling strategies of microgrids are private information, and microgrids often do not disclose this information, resulting in information isolation between microgrids. This situation belongs to an incomplete information game.
[0004] Therefore, how to dispatch energy for microgrid-coupled transportation systems in non-cooperative games under incomplete information conditions has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] The main purpose of the embodiments of the present application is to propose a scheduling method and device, equipment and medium based on a microgrid-coupled transportation system, aiming to perform energy scheduling in a non-cooperative game of a microgrid-coupled transportation system under incomplete information conditions to meet the charging requirements of the microgrid.
[0006] To achieve the above objectives, a first aspect of an embodiment of the present application proposes a scheduling method based on a microgrid coupled transportation system, the method comprising:
[0007] Acquire the data of the microgrid itself from the microgrid of the microgrid-coupled transportation system to obtain the microgrid's own data; wherein the microgrid-coupled transportation system includes the microgrid and at least one electric transport unit, and each of the electric transport units is electrically connected to one of the microgrids;
[0008] Acquire interaction data between the microgrid and each of the microgrids to obtain first grid interaction data;
[0009] Acquire interaction data between the microgrid and the electric transport unit to obtain second grid interaction data;
[0010] For each of the microgrids, constructing a function according to the microgrid's own data, the first grid interaction data, and the second grid interaction data to obtain a utility function;
[0011] Solving according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm to obtain a target feasible action;
[0012] The microgrid is controlled to execute the target feasible action so that energy is transferred between the microgrid and at least one of the microgrids.
[0013] The scheduling method and device, equipment and medium based on the microgrid coupled transportation system proposed in this application obtain the data of the microgrid itself and the interaction data between each microgrid, and also obtain the interaction data between the microgrid and the electric transportation unit to obtain the second grid interaction data for the situation that the electric transportation unit in the microgrid coupled transportation system charges and discharges the microgrid, so as to take into account the influence of each electric transportation unit in the microgrid coupled transportation system on the charging and discharging operation of the microgrid, increase the influencing factors and constraints of the energy scheduling of the microgrid in this method, and improve the accuracy of this method. Then, for each microgrid, a function is constructed according to the microgrid's own data, the first grid interaction data and the second grid interaction data to obtain a utility function; according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm, a solution is performed to obtain a target feasible action. Each microgrid only focuses on its own utility function, without considering the benefits of other microgrids or the overall benefits of the system. Each microgrid independently determines its own energy scheduling action and maximizes its own benefits, which belongs to a non-cooperative game. Moreover, since the target feasible actions of each microgrid are solved according to its own utility function without obtaining the utility functions of other microgrids, it conforms to the actual situation that the microgrid does not disclose its own privacy data such as utility function, that is, this method belongs to incomplete information game; in order to solve the game under incomplete information conditions to obtain the target feasible actions, this method uses reinforcement learning algorithm to solve and determine the target feasible actions; each microgrid executes its own target feasible actions, thereby performing energy scheduling for each microgrid in the microgrid coupled transportation system. Therefore, this method can perform energy scheduling for the microgrid coupled transportation system in the non-cooperative game under incomplete information conditions, and fully considers the situation of the electric transport unit charging and discharging the microgrid, thereby improving the accuracy and reliability of the scheduling method. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 is a flow chart of a dispatching method based on a microgrid coupled transportation system provided in an embodiment of the present application;
[0015] Figure 2 is a structural schematic diagram of a dispatching device based on a microgrid coupled transportation system provided in an embodiment of the present application;
[0016] Figure 3 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0018] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0020] First, some nouns involved in this application are analyzed:
[0021] Coupled Microgrid-Transportation (CMT) system: a system in which a microgrid and a transportation network perform close energy exchange. The coupled microgrid transportation system includes a microgrid (MG) and a networked electric vehicle (CEV). Energy is exchanged between multiple microgrids, and there is charging and discharging between the microgrid and the networked electric vehicle.
[0022] Micro-Grid (MG): It is an independent small-scale power system that can manage electricity to achieve power load balancing and perform energy scheduling. A microgrid usually includes different types of loads (i.e., power-consuming equipment), distributed generators, and energy storage equipment. Distributed generators can generate electricity using renewable energy. For transportation networks, microgrids are also associated with connected electric vehicles (CEVs), and microgrids can power connected electric vehicles through wired or wireless charging.
[0023] Connected Electric Vehicles (CEV): refers to electric vehicles that use vehicle networking technology. Connected electric vehicles can exchange data and energy with microgrids. It is usually necessary to manage and dispatch energy for connected electric vehicles and select feasible charging strategies. Connected electric vehicles can charge microgrids through V2G coordination.
[0024] V2G (Vehicle-to-Grid) coordination: refers to the method of using the batteries of electric vehicles to charge the power system. In V2G coordination, the batteries of electric vehicles can be regarded as distributed energy storage devices that provide electrical energy.
[0025] Incomplete information game: In an incomplete information game, the decision maker is not clear about certain information about the other party, such as the other decision maker's payoff function, cost or action strategy.
[0026] Non-cooperative game: refers to a game in which each decision maker makes independent decisions without considering the actions of other decision makers. In a non-cooperative game, each decision maker needs to choose a strategy to maximize his or her own benefits in order to achieve a Nash equilibrium.
[0027] Nash equilibrium: a set of strategies under which any decision maker will not increase his or her own benefits by unilaterally changing his or her strategy.
[0028] Stackelberg game: It is a non-cooperative game theory. Its main idea is that the two decision makers in the game choose their own strategies according to the possible strategies of the other party to ensure that their own benefits under the strategy of the other party are maximized. In the Stackelberg game, it is assumed that there are two decision makers, one is the leader and the other is the follower. The leader first determines the price, and the follower determines his own strategy after knowing the price of the leader.
[0029] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI mainly includes deep learning and reinforcement learning (RL).
[0030] Reinforcement Learning (RL) is a machine learning method used to describe and solve the problem of how an intelligent agent can maximize gains or achieve specific goals by learning strategies during its interaction with the environment. A common model for reinforcement learning is the Markov decision process (MDP).
[0031] Markov Decision Process (MDP): It is used to simulate the random strategies and gains that can be achieved by intelligent agents in an environment where the system state has Markov properties. When a random process has a conditional probability distribution of future states that depends only on the current state given the current state and all past states, the random process has Markov properties. Processes with Markov properties are called Markov processes. In the simulation of MDP, the intelligent agent will take actions according to the strategy based on the system state to obtain rewards. The accumulation of rewards over time is called gains.
[0032] Deep Deterministic Policy Gradient (DDPG): is an algorithm based on deep reinforcement learning that can select feasible actions based on the agent's strategy. The DDPG algorithm can be used to allocate computing resources.
[0033] The scheduling method, device, equipment and medium based on the microgrid coupled transportation system provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the scheduling method based on the microgrid coupled transportation system in the embodiments of the present application is described.
[0034] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0035] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.
[0036] The dispatching method based on the microgrid coupled traffic system provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the dispatching method based on the microgrid coupled traffic system, etc., but is not limited to the above forms.
[0037] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0038] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.
[0039] Figure 1 is an optional flow chart of a scheduling method based on a microgrid coupled transportation system provided in an embodiment of the present application. Figure 1 The method includes but is not limited to steps 101 to 106.
[0040] Step 101, acquiring data of the microgrid itself from a microgrid of a microgrid-coupled transportation system to obtain microgrid-owned data; wherein the microgrid-coupled transportation system includes a microgrid and at least one electric transport unit, and each electric transport unit is electrically connected to a microgrid;
[0041] Step 102, acquiring interaction data between the microgrid and each microgrid to obtain first grid interaction data;
[0042] Step 103, acquiring interaction data between the microgrid and the electric transport unit to obtain second grid interaction data;
[0043] Step 104, for each microgrid, construct a function based on the microgrid's own data, the first grid interaction data, and the second grid interaction data to obtain a utility function;
[0044] Step 105, solving according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm to obtain a target feasible action;
[0045] Step 106 , controlling the microgrid to execute the target feasible action, so that energy is transferred between the microgrid and at least one of the microgrids.
[0046] The beneficial effects of the embodiments of the present application include but are not limited to: obtaining the data of the microgrid itself and the interaction data between each microgrid, and also obtaining the interaction data between the microgrid and the electric transport unit to obtain the second grid interaction data for the situation that the electric transport unit in the microgrid coupled transportation system charges and discharges the microgrid, thereby taking into account the influence of each electric transport unit in the microgrid coupled transportation system on the charging and discharging operation of the microgrid, increasing the influencing factors and constraints of the energy scheduling of the microgrid in this method, and improving the accuracy of this method. Then, for each microgrid, a function is constructed according to the microgrid's own data, the first grid interaction data and the second grid interaction data to obtain a utility function; according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm, a solution is performed to obtain a target feasible action. Each microgrid only focuses on its own utility function, without considering the benefits of other microgrids or the overall benefits of the system. Each microgrid independently determines its own energy scheduling action and maximizes its own benefits, which belongs to a non-cooperative game. Moreover, since the target feasible actions of each microgrid are solved according to its own utility function without obtaining the utility functions of other microgrids, it conforms to the actual situation that the microgrid does not disclose its own privacy data such as utility function, that is, this method belongs to incomplete information game; in order to solve the game under incomplete information conditions to obtain the target feasible actions, this method uses reinforcement learning algorithm to solve and determine the target feasible actions; each microgrid executes its own target feasible actions, thereby performing energy scheduling for each microgrid in the microgrid coupled transportation system. Therefore, this method can perform energy scheduling for the microgrid coupled transportation system in the non-cooperative game under incomplete information conditions, and fully considers the situation of the electric transport unit charging and discharging the microgrid, thereby improving the accuracy and reliability of the scheduling method.
[0047] It should be noted that microgrids are capable of generating electricity from renewable energy (such as solar power generation or wind power generation), but renewable energy generation is intermittent and uncertain; in addition, the charging and discharging behavior of networked electric vehicles on microgrids is also random. These influencing factors may cause random power fluctuations in microgrids, and excessive power fluctuations may cause damage to the microgrid. The scheduling method based on a microgrid-coupled transportation system provided in an embodiment of the present application allows a microgrid with excess energy to exchange energy with a microgrid with insufficient production capacity, thereby stabilizing the power of the microgrid, and determining target feasible actions for each microgrid to achieve energy scheduling of a microgrid-coupled transportation system.
[0048] In step 101 of some embodiments, the microgrid's own data may include the microgrid's power generation, load power consumption, road network, etc. Among them, the road network of the microgrid can be described by a directed graph. For example, the edge set of the directed graph represents multiple road sections in the road network, and the node set of the directed graph represents the intersection position of multiple road sections. The electric transport unit can travel on the road network.
[0049] In step 102 of some embodiments, the first grid interaction data may include the energy transfer amount between each microgrid and the connection relationship between each microgrid, and the connection relationship may be represented by an adjacency matrix. The element A in the i-th row and j-th column of i,j is 1, indicating that the i-th microgrid in the microgrid-coupled transportation system is connected to the j-th microgrid. i,j If it is 0, it means that the above two microgrids are not connected. If the diagonal elements of the adjacency matrix are all 0, it means that the microgrid cannot exchange energy with itself.
[0050] In step 103 of some embodiments, the second grid interaction data may include the real-time number of electric transport units in the microgrid, a wireless charging influence factor indicating whether the electric transport unit participates in wireless charging, a wired charging influence factor indicating whether the electric transport unit participates in wired charging, etc. Each electric transport unit exchanges energy with at most one microgrid at the same time.
[0051] In some embodiments, the road network of the microgrid has a wireless energy track and a wired charging station, and the wireless energy track is defined as an energy supply unit based on wireless power transmission. The wireless energy track can power the electric transport unit by electromagnetic induction. If the wireless charging impact factor is 1, it means that the electric transport unit participates in wireless charging, for example, the electric transport unit is traveling on the wireless energy track of the microgrid; if the wireless charging impact factor is 0, it means that it does not participate in wireless charging. Similarly, a wired charging impact factor of 1 indicates that the electric transport unit participates in wired charging, for example, the electric transport unit is connected to a wired charging station; a wired charging impact factor of 0 indicates that it does not participate in wired charging.
[0052] In step 104 of some embodiments, the function value of the utility function represents the revenue of the corresponding microgrid. In some embodiments, if the function value of the utility function is a negative number, it may represent the operating cost of the microgrid.
[0053] In step 105 of some embodiments, the candidate feasible actions may be substituted into the utility function for calculation to obtain the benefit (utility function value) corresponding to each candidate feasible action. The target feasible action may be the feasible action with the largest utility function value among multiple candidate feasible actions, that is, the feasible action with the largest benefit.
[0054] In some embodiments, the microgrid-coupled transportation system further includes a utility grid electrically connected to the plurality of microgrids.
[0055] Before step 104, the dispatching method based on the microgrid coupled transportation system further includes:
[0056] Acquire the interaction data between the microgrid and the public grid, and obtain the third grid interaction data;
[0057] Step 104 includes:
[0058] For each microgrid, a function is constructed according to the microgrid's own data, the first grid interaction data, the second grid interaction data and the third grid interaction data to obtain a utility function.
[0059] The advantage of this embodiment is that, considering the influence of the public grid on the energy dispatching action of the microgrid in the microgrid-coupled transportation system, the interaction data between the microgrid and the public grid is obtained to obtain the third grid interaction data, and the utility function is constructed according to the third grid interaction data, so that the utility function can reflect the energy exchange process between the microgrid and the public grid, thereby improving the accuracy of the method, and in view of the presence of the public grid in the system, the target feasible action corresponding to the microgrid is selected, thereby realizing the energy dispatching of the microgrid-coupled transportation system.
[0060] It should be noted that in the process of energy transmission between the microgrid and the public grid, the public grid determines the energy transmission cost, which can be specifically set by the public grid. Cost influencing factors (such as the price of electricity transmission) Therefore, this game belongs to the Stackelberg game. The public grid is the leader who determines the price in the game, and the microgrid is the follower. After knowing the price of the leader, the microgrid determines its own strategy (that is, the target feasible action).
[0061] In some embodiments, for each microgrid, a function is constructed based on the microgrid's own data, the first grid interaction data, the second grid interaction data, and the third grid interaction data to obtain a utility function including:
[0062] The microgrid's own data, the first grid interaction data, the second grid interaction data and the third grid interaction data are discretized through a preset Markov decision process model;
[0063] A function is constructed according to the discretized microgrid own data, the first grid interaction data, the second grid interaction data and the third grid interaction data to obtain a utility function;
[0064] Among them, the reinforcement learning algorithm is a deep deterministic policy gradient algorithm;
[0065] The utility function, multiple preset candidate feasible actions and the preset reinforcement learning algorithm are used to solve the problem and obtain the target feasible actions, including:
[0066] Input the utility function and multiple candidate feasible actions into the deep deterministic policy gradient algorithm to calculate the gain value corresponding to each candidate feasible action;
[0067] The candidate feasible action corresponding to the maximum gain value is determined as the target feasible action.
[0068] The advantage of this embodiment is that the first power grid interaction data, the second power grid interaction data and the third power grid interaction data are discretized through the Markov decision process model, and then a utility function is constructed based on the discretized data, and the utility function is calculated using a deep deterministic policy gradient algorithm to determine the maximum gain value; and the candidate feasible action corresponding to the maximum gain value is determined as the target feasible action, thereby maximizing the benefit of the microgrid in the game and realizing the energy scheduling of the system.
[0069] It should be noted that the utility function represents a gain value that varies with time periods. In an embodiment of the present application, the deep deterministic policy gradient algorithm is calculated based on the data corresponding to different time periods (including the first power grid interaction data, the second power grid interaction data, and the third power grid interaction data). Therefore, before solving the target feasible action with the deep deterministic policy gradient algorithm, it is necessary to discretize the data in time through the Markov decision process model.
[0070] It should be noted that the first grid interaction data, the second grid interaction data and the third grid interaction data are all based on data within a preset total period. Including time period t1 and time period t2. The microgrid's own data, the first grid interaction data, the second grid interaction data and the third grid interaction data are discretized by the preset Markov decision process model, which means discretizing the time of the data, for example, dividing the total time period The above data in time are discretized in time to obtain the first power grid interaction data, the second power grid interaction data and the third power grid interaction data in time period t1, and the first power grid interaction data, the second power grid interaction data and the third power grid interaction data in time period t2.
[0071] In some embodiments, a function is constructed based on the discretized microgrid own data, the first grid interaction data, the second grid interaction data, and the third grid interaction data to obtain a utility function, including:
[0072] constructing a first sub-formula according to the first power grid interaction data;
[0073] According to the microgrid’s own data, the second sub-formula is constructed;
[0074] According to the microgrid's own data and the interactive data of the second grid, the third sub-formula is constructed;
[0075] constructing a fourth sub-formula according to the third power grid interaction data;
[0076] The first sub-formula, the second sub-formula, the third sub-formula and the fourth sub-formula are integrated to obtain the utility function.
[0077] The advantage of this embodiment is that a function is constructed based on the microgrid's own data, the first grid interaction data, the second grid interaction data and the third grid interaction data, and the obtained utility function can characterize the gain value of the microgrid, thereby more accurately determining the target feasible actions for the microgrid to exchange energy, thereby improving the accuracy and reliability of the method.
[0078] In some embodiments, the second grid interaction data includes the charging state of the electric transport unit, the number of electric transport units, and the charging and discharging power set; the third sub-formula includes a first sub-item, a second sub-item, and a third sub-item;
[0079] According to the microgrid's own data and the second grid interaction data, the third sub-formula is constructed, including:
[0080] Substitute the charging and discharging power set into the preset transport unit charging and discharging loss function to construct the first sub-item;
[0081] Substitute the number of electric transport units and the charging and discharging power set into the preset transport unit power regulation gain function to construct the second sub-item;
[0082] Substitute the charging state and charging and discharging power set of the electric transport unit into the preset insufficient power penalty function to construct the third sub-item.
[0083] In some embodiments, the first grid interaction data is the total amount of energy transferred by the microgrid; the first sub-formula includes a fourth sub-item and a fifth sub-item;
[0084] According to the first power grid interaction data, a first sub-formula is constructed, including:
[0085] Substitute the total amount of microgrid energy transmission into the preset energy transmission gain function to construct the fourth sub-item;
[0086] Substitute the total amount of energy transmitted by the microgrid into the preset energy transmission loss function to construct the fifth sub-item.
[0087] In some embodiments, specifically, the microgrid own data includes the power generation G i,t , Load power consumption L i,t and renewable energy utilization R i,t ; The first grid interaction data is the total amount of energy transmitted by the microgrid, including S ij,t and S ji,t ; The second grid interaction data includes the state of charge SOC of the electric transport unit n,t , the number of electric transport units N and the charging and discharging power set The third grid interaction data is the energy transmission amount of the public grid The definitions of the above data refer to the formula of the utility function (as shown below).
[0088] In some embodiments, the utility function is as follows:
[0089]
[0090] U i,t represents the gain value of the microgrid MGi in time period t; where t represents the total time period The tth time period in the total time period includes T time periods; i represents the microgrid set The i-th microgrid MGi in the microgrid set It includes M microgrids;
[0091] In the above formula, the first term is: When the value of the first term is greater than zero, it represents the energy output benefit, and when the value of the first sub-formula is less than zero, it represents the energy acquisition cost; Represents the energy transfer gain coefficient; ∑ j≠i S ij,t represents the total amount of energy transmitted to microgrid MGi by other microgrids except microgrid MGi during time period t, ∑ j≠i S ji,t It represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t;
[0092] The second term is:∑ j≠i (S ji,t ) 2 , the second term represents the first energy transmission loss of energy transmission between microgrids and each microgrid; where S ji,t represents the energy transmitted from microgrid MGi to microgrid MGj in time period t; ∑ j≠i (S ji,t ) 2 It represents the sum of the squares of the energy transmitted from microgrid MGi to other microgrids in time period t;
[0093] The third item is: The third term characterizes the power generation loss of renewable energy; among them, represents the renewable energy generation loss coefficient of the microgrid MGi, R i,t represents the renewable energy utilization of microgrid MGi in time period t;
[0094] The fourth item is: The fourth item represents the second energy transmission loss of energy transmission between the microgrid and the public grid; wherein, represents the loss coefficient of the energy obtained by the microgrid MGi from the public grid during the period t, represents the energy obtained by the microgrid MGi from the utility grid during time period t;
[0095] The fifth item is: The fifth term characterizes the charging loss of the electric transport unit; where n represents the set of electric transport units The nth electric transport unit CEVn in the electric transport unit collection including N electric transport units; represents the charge and discharge loss coefficient of the electric transport unit CEVn in time period t, P n,t represents the charge and discharge power of the electric transport unit CEVn in time period t, and P n,t Belongs to the charge and discharge power collection Where N represents the number of electric transport units in the microgrid MGi;
[0096] The sixth item is: The sixth term characterizes the power regulation gain of the electric transport unit; where F represents the gain coefficient of the electric transport unit charging the microgrid MGi; Indicates the total time period duration; ξ represents the battery capacity penalty factor, ξ∈(0,1]; time period t and time period t-1 both belong to the total time period represents the active power of the microgrid MGi in time period t-1; represents the active power of the microgrid MGi in time period t;
[0097] is defined as:
[0098]
[0099] in It represents the power imbalance of the microgrid coupled transportation system in time period t; represents the sum of the charging and discharging powers of the electric transport units in the microgrid MGi during the period t;
[0100] It should be noted that the battery capacity penalty factor ξ reflects the reduction of the upper limit of the battery capacity of the electric transport unit. For example, the battery attenuation effect causes the upper limit of the battery capacity of the electric transport unit to be reduced. The battery attenuation effect refers to the phenomenon that the battery material gradually fails and the battery capacity decreases during the use of the battery.
[0101] The seventh item is: The seventh term represents the energy surplus penalty when the energy supply of the microgrid MGi exceeds the energy demand in time period t; where σ1 represents the first penalty factor; C i,t represents the charge and discharge amount of the microgrid MGi in time period t; L i,t represents the load power consumption of the microgrid MGi in time period t; S i,t G represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t; i,t represents the power generation of the microgrid MGi in time period t; represents the energy obtained by the microgrid MGi from the public grid during time period t; ∑ j≠i β ji,trepresents the energy obtained by microgrid MGi from other microgrids in time period t; max(·) represents the maximum value, and The value of is greater than or equal to 0;
[0102] The eighth item is:
[0103]
[0104] The eighth term represents the penalty for the microgrid MGi not meeting the charging requirements in time period t; where σ2 represents the second penalty factor; represents the target charging state of the electric transport unit CEVn, that is, the charging requirement of the electric transport unit CEVn; Indicates buffer factor; SOC n,t represents the charging state of the electric transport unit CEVn in time period t; P n,t represents the charge and discharge power of the electric transport unit CEVn in time period t; η(·) represents the energy efficiency of the charge and discharge power of the electric transport unit CEVn; Indicates the duration of the total period; Δt indicates the total period The duration of each period in ch represents the charging efficiency of the electric transport unit CEVn, η ch ∈(0,1]; represents the charging price adjustment factor of the electric transport unit CEVn;
[0105] Buffer Factor Defined as:
[0106]
[0107] Where μ represents the safety margin, μ∈[0,1]; Indicates the upper limit threshold of the electric power of the electric transport unit CEVn;
[0108] The eighth item satisfies the charging requirement constraint, which is shown in the following formula:
[0109]
[0110] in, Indicates that the duration of time period t is less than the duration of the total time period;
[0111] Charge and discharge energy efficiency η(P n,t ) is defined as:
[0112]
[0113] η ch represents the charging efficiency of the electric transport unit CEVn, η dchrepresents the discharge efficiency of the electric transport unit CEVn, η ch ∈(0,1] and η dch ∈(0,1].
[0114] The advantage of this embodiment is that it characterizes the energy transmission gain of the microgrid, the first energy transmission loss for energy transmission between the microgrid and each microgrid, the renewable energy power generation loss of the microgrid, the second energy transmission loss for energy transmission between the microgrid and the public grid, the charging and discharging loss of the electric transport unit, the power regulation gain of the electric transport unit, the energy surplus penalty of the microgrid, and the power shortage penalty of the microgrid through the utility function; determines the target feasible action according to the utility function, thereby more accurately calculating the benefits of energy exchange of the microgrid, thereby improving the accuracy and reliability of the method.
[0115] In an application example, assuming that the total period is 24 hours, including 96 periods, that is, the total period Total time duration The number of time periods is T = 96, and the duration of each time period is Δt = 0.25h = 15min (minutes). Charging price adjustment factor Set to 0.59. The charging price adjustment factor can indicate that the charging price per kilowatt-hour of the electric transport unit is 0.59. Each kilowatt-hour is also called "degree", which means the energy consumed by an electrical appliance with a power of one kilowatt after one hour of use. The gain value U calculated according to the utility function i,t The gain value may represent a bonus of 40 per megawatt-hour, where each megawatt-hour represents the use or production of one million watts of energy in one hour.
[0116] In some embodiments, specifically, the constraint set includes: renewable energy utilization constraint, microgrid energy transmission constraint, public grid energy transmission constraint, power balance constraint, power balance constraint, energy trading constraint, charging and discharging power constraint, charging state constraint, and charging and discharging energy constraint.
[0117] The renewable energy utilization rate constraint is as follows:
[0118]
[0119] represents a microgrid set, which includes M microgrids; i represents the i-th microgrid MGi; represents the total time period, which includes T time periods; t represents the tth time period; R i,t represents the renewable energy utilization of microgrid MGi in time period t, G i,tIt represents the power generation of microgrid MGi in time period t.
[0120] Specifically, the power generation can be the amount of electricity generated by the microgrid through renewable energy generation, and the renewable energy utilization can be the amount of energy obtained by power generation G i,t In the case of , the total amount of energy used (such as the microgrid’s own electricity consumption, or the transmission of electricity to other microgrids) within time period t.
[0121] The energy transmission constraints of the microgrid are shown in the following formula:
[0122]
[0123] i represents the i-th microgrid MGi, j represents the j-th microgrid MGj; represents the upper threshold of energy transfer between microgrid MGi and microgrid MGj; α ij,t represents the energy that microgrid MGj is expected to obtain from microgrid MGi in time period t, and α ij,t The purchased energy vector belonging to the microgrid MGi Buy Energy Vector α j,t It represents the total amount of energy that microgrid MGi is expected to obtain from other microgrids during time period t.
[0124] It should be noted that other microgrids refer to microgrid collections. All microgrids except microgrid MGi. Specifically, the energy transmission upper limit threshold It may be 300KW (kilowatts). In some embodiments, due to energy transmission loss between various microgrids, the energy that the microgrid is expected to obtain is not equal to the energy that the microgrid actually obtains.
[0125] The energy transmission constraints of the public power grid are shown in the following formula:
[0126]
[0127] represents the energy obtained by the microgrid MGi from the utility grid during time period t; It represents the maximum energy that the microgrid MGi can obtain from the utility grid.
[0128] The power balance constraint is as follows:
[0129]
[0130] G i,t represents the power generation of the microgrid MGi in time period t; represents the energy obtained by the microgrid MGi from the public grid during time period t; ∑j≠i β ji,t represents the total energy obtained by microgrid MGi from other microgrids in time period t, β ji,t represents the energy obtained by microgrid MGi from microgrid MGj in time period t; L i,t represents the load power consumption of microgrid MGi in time period t; C i,t represents the charge and discharge amount of the microgrid MGi in time period t; S i,t It represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t;
[0131] β ji,t is defined as:
[0132]
[0133] Among them, α ji,t represents the energy that microgrid MGi is expected to obtain from microgrid MGj in time period t; γ ij,t represents the energy transmission loss between microgrid MGi and microgrid MGj in time period t; γ ij,t Energy transmission loss vector belonging to the microgrid coupled transportation system
[0134] C i,t is defined as:
[0135]
[0136] in, represents the sum of the charging and discharging powers of all electric transport units in the microgrid MGi; P n,i,t represents the charging and discharging power of the electric transport unit CEVn of the microgrid MGi in time period t; represents the electric transport unit set of the microgrid MGi, the electric transport unit set includes N electric transport units; n represents the nth electric transport unit CEVn;
[0137] S i,t is defined as:
[0138]
[0139] Among them, R i,t represents the amount of renewable energy used by the microgrid MGi in time period t; G i,t >R i,t , indicating that the microgrid has excess renewable energy.
[0140] The power balance constraint is shown in the following formula:
[0141]
[0142] R i,t represents the renewable energy utilization of microgrid MGi in time period t; represents the energy obtained by the microgrid MGi from the public grid during time period t; ∑ j≠i β ji,t represents the energy obtained by microgrid MGi from other microgrids in time period t; C i,t represents the charge and discharge amount of the microgrid MGi in time period t; L i,t represents the load power consumption of the microgrid MGi in time period t; S i,t It represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t.
[0143] The energy trading constraints are as follows:
[0144]
[0145] ∑ j≠i a ij,t S represents the total amount of energy purchased from microgrid MGi by other microgrids in time period t; i,t It represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t.
[0146] The charging and discharging power constraints are shown in the following formula:
[0147]
[0148] P n,t represents the charging and discharging power of the electric transport unit CEVn in time period t; represents the discharge power threshold of the electric transport unit CEVn, and represents the charging power threshold of the electric transport unit CEVn, and represents the electric transport unit set of the microgrid MGi, and the electric transport unit set includes N electric transport units; n represents the electric transport unit set The nth electric transport unit CEVn in n,t Indicates whether the electric transport unit CEVn participates in wireless charging and discharging scheduling; if k n,t = 0, indicating that the electric transport unit CEVn does not participate in the wireless charging and discharging scheduling in time period t. In this case, P n,t =0; if k n,t =1, indicating that the electric transport unit CEVn participates in the wireless charging and discharging scheduling in time period t;
[0149] When the electric transport unit CEVn is charged, the electric transport unit CEVn is connected to the wired charging unit CEVAk or the wireless charging unit PTs; the wired charging unit CEVAk belongs to the wired charging unit set of the microgrid MGi. The wireless charging unit PTs belongs to the wireless charging unit collection of the microgrid MGi The electric transport unit CEVn has a charging state, the corresponding formula is:
[0150]
[0151] SOC n,t+Δt Indicates the charging state of the electric transport unit CEVn in the time period (t+Δt); SOC n,t represents the charging status of the electric transport unit CEVn in time period t; Δt represents the total time period The duration of each period in represents the battery capacity of the electric transport unit CEVn, and η(·) represents the energy efficiency of the charging and discharging power of the electric transport unit CEVn. η(·) is defined as:
[0152]
[0153] η ch represents the charging efficiency of the electric transport unit CEVn, η dch represents the discharge efficiency of the electric transport unit CEVn, η ch ∈(0,1] and η dch ∈(0,1];
[0154] SOC n,t+Δt is defined as:
[0155]
[0156] λ n represents the unit energy consumption coefficient of the electric transport unit CEVn, and λ n ≥0; represents the travel distance of the electric transport unit CEVn from position s to position v in the microgrid MGi during time period t; the microgrid MGi includes a road network The edge set ε i Represents multiple road segments in a road network, a node set Represents the intersection of multiple road sections; road section (s, v) ∈ ε i , and
[0157] The corresponding formula is in represents the average driving speed of the electric transport unit CEVn from position s to position v in time period t; Δt represents the total time period The length of each period in is also the length of period t.
[0158] Specifically, the unit energy consumption coefficient λ n It can be 1.112 kWh per kilometer.
[0159] The charging state constraint is shown in the following formula:
[0160]
[0161] Indicates the final charging state of the electric transport unit CEVn, that is, the electric transport unit CEVn after the total period The subsequent charging status; Indicates the initial charging state of the electric transport unit CEVn, represents the target charging state of the electric transport unit CEVn, that is, the charging requirement of the electric transport unit CEVn; n represents the set of electric transport units The nth electric transport unit CEVn in .
[0162] The charge and discharge energy constraint condition is shown in the following formula:
[0163]
[0164] SOC n Indicates the lower limit of the electric transport unit CEVn. Indicates the upper limit of the electric transport unit CEVn; SOC n,t represents the charging state of the electric transport unit CEVn in time period t.
[0165] In an application example, the specific value of the above charging state follows a uniform distribution U[a,b] in the interval [a,b]. For example, the initial charging state of the electric transport unit is U[0%,10%], target charging state U[40%,50%], the lower limit of power SOC n U[10%,20%], the upper limit of power is U[90%,99%].
[0166] In some embodiments, before inputting the utility function and the plurality of candidate feasible actions into the deep deterministic policy gradient algorithm, the method further comprises:
[0167] Obtain historical data sets and historical action sets from a preset microgrid status database;
[0168] Based on historical data sets and historical action sets, the deep deterministic policy gradient algorithm is gradient trained and updated.
[0169] The advantage of this embodiment is that the deterministic policy gradient algorithm is trained based on historical data, thereby improving the accuracy and reliability of the method and realizing energy scheduling of a microgrid coupled transportation system.
[0170] In some embodiments, specifically, data such as the power generation of the microgrid, the load power consumption, the total amount of energy transmitted by the microgrid, the charging status of the electric transport unit, the number of electric transport units, and the time period can be obtained from a preset information state. The information state is defined as:
[0171]
[0172] Represents the information status of the microgrid MGi; G i,t represents the power generation of the microgrid MGi in time period t; L u,t represents the load power consumption of the microgrid MGi in time period t; α uj,t S represents the energy transmitted from microgrid MGi to microgrid MGj during time period t, that is, the energy purchased by microgrid MGj from microgrid MGi during time period t; i,t It represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t; represents the charging and discharging regulation signal of the microgrid MGi in time period t, such as the charging and discharging price; represents the set of electric transport units in the microgrid MGi in time period t The charging state of the microgrid MGi; N represents the number of electric transport units; t represents the total time The tth period in .
[0173] In some embodiments, assuming that in the total period In the t-1 period and the period before it The corresponding microgrid own data, first grid interaction data, second grid interaction data, third grid interaction data, and target feasible actions are all known historical data. Then, the deterministic policy gradient algorithm can be trained based on the historical data, and the trained deterministic policy gradient algorithm can be used to solve the target feasible actions in the future period (for example, period t). The target feasible action is defined as:
[0174]
[0175] Hi,t represents the target feasible action of the microgrid MGi, and the target feasible action satisfies the constraint condition set; S ij,t represents the energy transmitted from microgrid MGj to microgrid MGi in time period t; i represents the microgrid set The i-th microgrid MGi in the MGi; j represents the microgrid set The jth microgrid MGj in R i,t represents the renewable energy utilization of microgrid MGi in time period t, represents the energy obtained by the microgrid MGi from the public grid during time period t, represents the charging and discharging power set of the electric transport unit in the microgrid MGi Where P n,t Represents the set of electric transport units in the microgrid MGi The charging and discharging power of the electric transport unit CEVn.
[0176] See also Figure 2 The embodiment of the present application further provides a dispatching device based on a microgrid coupled transportation system, which can implement the above-mentioned dispatching method based on a microgrid coupled transportation system, and the device includes:
[0177] The self-owned data acquisition module 201 is used to acquire the data of the microgrid itself from the microgrid of the microgrid coupled transportation system to obtain the self-owned data of the microgrid; wherein the microgrid coupled transportation system includes a microgrid and at least one electric transport unit, and each electric transport unit is electrically connected to a microgrid;
[0178] A first interaction data acquisition module 202 is used to acquire interaction data between the microgrid and each microgrid to obtain first grid interaction data;
[0179] The second interaction data acquisition module 203 is used to acquire the interaction data between the microgrid and the electric transport unit to obtain the second grid interaction data;
[0180] A function construction module 204 is used to construct a function for each microgrid according to the microgrid's own data, the first grid interaction data and the second grid interaction data to obtain a utility function;
[0181] The action solving module 205 is used to solve the problem according to the utility function, multiple preset candidate feasible actions and a preset reinforcement learning algorithm to obtain a target feasible action;
[0182] The action execution module 206 is used to control the microgrid to execute the target feasible action, so that energy is transferred between the microgrid and at least one of the microgrids.
[0183] The specific implementation of the dispatching device based on the microgrid coupled transportation system is basically the same as the specific implementation of the dispatching method based on the microgrid coupled transportation system mentioned above, and will not be repeated here.
[0184] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned scheduling method based on the microgrid coupled transportation system when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.
[0185] See also Figure 3 , Figure 3 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0186] The processor 301 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;
[0187] The memory 302 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 302 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 302, and the processor 301 calls and executes the scheduling method based on the microgrid coupled transportation system of the embodiment of this application;
[0188] Input / output interface 303, used to implement information input and output;
[0189] The communication interface 304 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);
[0190] A bus 305 that transmits information between the various components of the device (e.g., the processor 301, the memory 302, the input / output interface 303, and the communication interface 304);
[0191] The processor 301 , the memory 302 , the input / output interface 303 and the communication interface 304 are connected to each other in communication within the device via the bus 305 .
[0192] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned scheduling method based on the microgrid-coupled transportation system is implemented.
[0193] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0194] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0195] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0196] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0197] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0198] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application 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 interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0199] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0200] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0201] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0202] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0203] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0204] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A dispatching method based on a microgrid coupled transportation system, characterized in that: The method comprises: Acquire the data of the microgrid itself from the microgrid of the microgrid-coupled transportation system to obtain the microgrid's own data; wherein the microgrid-coupled transportation system includes the microgrid and at least one electric transport unit, and each of the electric transport units is electrically connected to one of the microgrids; Acquire interaction data between the microgrid and each of the microgrids to obtain first grid interaction data; Acquire interaction data between the microgrid and the electric transport unit to obtain second grid interaction data; For each of the microgrids, constructing a function according to the microgrid's own data, the first grid interaction data, and the second grid interaction data to obtain a utility function; Solving according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm to obtain a target feasible action; The microgrid is controlled to execute the target feasible action so that energy is transferred between the microgrid and at least one of the microgrids.
2. The scheduling method according to claim 1, characterized in that: The microgrid coupled transportation system further includes a public grid, which is electrically connected to the plurality of microgrids; before constructing a function for each microgrid according to the microgrid's own data, the first grid interaction data, and the second grid interaction data to obtain a utility function, the method further includes: Acquire interaction data between the microgrid and the public power grid to obtain third power grid interaction data; For each of the microgrids, constructing a function according to the microgrid's own data, the first grid interaction data, and the second grid interaction data to obtain a utility function includes: For each of the microgrids, a function is constructed according to the microgrid's own data, the first grid interaction data, the second grid interaction data, and the third grid interaction data to obtain a utility function.
3. The scheduling method according to claim 2, characterized in that: For each of the microgrids, constructing a function according to the microgrid's own data, the first grid interaction data, the second grid interaction data, and the third grid interaction data to obtain a utility function includes: Discretizing the microgrid's own data, the first grid interaction data, the second grid interaction data, and the third grid interaction data through a preset Markov decision process model; Constructing a function according to the microgrid's own data, the first grid interaction data, the second grid interaction data, and the third grid interaction data after discretization to obtain the utility function; The reinforcement learning algorithm is a deep deterministic policy gradient algorithm; the solving according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm to obtain the target feasible action includes: Input the utility function and the plurality of candidate feasible actions into the deep deterministic policy gradient algorithm, and calculate a gain value corresponding to each candidate feasible action; The candidate feasible action corresponding to the maximum gain value is determined as the target feasible action.
4. The scheduling method according to claim 3, characterized in that: The constructing a function according to the microgrid's own data after discretization, the first grid interaction data, the second grid interaction data and the third grid interaction data to obtain the utility function includes: constructing a first sub-formula according to the first power grid interaction data; Constructing a second sub-formula according to the microgrid's own data; Constructing a third sub-formula according to the microgrid's own data and the second grid interaction data; constructing a fourth sub-formula according to the third power grid interaction data; The first sub-formula, the second sub-formula, the third sub-formula and the fourth sub-formula are integrated to obtain the utility function.
5. The scheduling method according to claim 4, characterized in that: The second grid interaction data includes the charging state of the electric transport unit, the number of electric transport units and the charging and discharging power set; the third sub-formula includes a first sub-item, a second sub-item and a third sub-item; The constructing of a third sub-formula according to the microgrid's own data and the second grid interaction data includes: Substituting the charging and discharging power set into a preset transport unit charging and discharging loss function to construct the first sub-item; Substituting the number of electric transport units and the charge and discharge power set into a preset transport unit power regulation gain function to construct the second sub-item; Substitute the charging state of the electric transport unit and the charging and discharging power set into a preset insufficient power penalty function to construct the third sub-item.
6. The scheduling method according to claim 4, characterized in that: The first grid interaction data is the total amount of energy transmitted by the microgrid; The first sub-formula includes a fourth sub-term and a fifth sub-term; The constructing a first sub-formula according to the first power grid interaction data includes: Substituting the total amount of energy transmitted by the microgrid into a preset energy transmission gain function to construct the fourth sub-item; Substitute the total amount of energy transmitted by the microgrid into a preset energy transmission loss function to construct the fifth sub-item.
7. The scheduling method according to any one of claims 1 to 6, characterized in that: The utility function is shown in the following formula: U i , t represents the gain value of the microgrid MGi in the time period t; wherein t represents the tth time period in the total time period T = {1, 2, ..., t, ..., T}, and the total time period includes T time periods; i represents the microgrid set The i-th microgrid MGi in the microgrid set It includes M microgrids; In the formula of the utility function, the first term is: in, Represents the energy transfer gain coefficient; ∑ j≠i S ij,t represents the total amount of energy transmitted to microgrid MGi by other microgrids except microgrid MGi during time period t, ∑ j≠i S ji,t It represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t; The second term is:∑ j≠i (S ji,t ) 2 ; Among them, S ji,t represents the energy transmitted from microgrid MGi to microgrid MGj in time period t; ∑ j≠i (S ji,t ) 2 It represents the sum of the square of energy transmitted from microgrid MGi to other microgrids in time period t: The third item is: in, represents the renewable energy generation loss coefficient of the microgrid MGi, R i , t represents the renewable energy utilization of microgrid MGi in time period t; The fourth item is: in, represents the loss coefficient of the energy obtained by the microgrid MGi from the public grid during the period t, represents the energy obtained by the microgrid MGi from the utility grid during time period t; The fifth item is: Where n represents the set of electric transport units The nth electric transport unit CEVn in the electric transport unit set including N electric transport units; represents the charge and discharge loss coefficient of the electric transport unit CEVn in time period t, P n,t represents the charge and discharge power of the electric transport unit CEVn in time period t, and P n,t Belongs to the charge and discharge power collection Where N represents the number of electric transport units in the microgrid MGi; The sixth item is: Wherein, F represents the gain coefficient of the electric transport unit charging the microgrid MGi; Indicates the total time period duration; ξ represents the battery capacity penalty factor, ξ∈(0,1]; time period t and time period t-1 both belong to the total time period represents the active power of the microgrid MGi in time period t-1; represents the active power of the microgrid MGi in time period t; is defined as: in It represents the power imbalance of the microgrid coupled transportation system in time period t; represents the sum of the charging and discharging powers of the electric transport units in the microgrid MGi during the period t; The seventh item is: Among them, σ1 represents the first penalty factor; C i , t represents the charge and discharge amount of the microgrid MGi in time period t; L i , t represents the load power consumption of the microgrid MGi in time period t; S i , t represents the total amount of energy transmitted from microgrid MGi to other microgrids in time period t; G i,t Represents the power generation of the microgrid MGi in time period t; ∑ j≠i β ji,t represents the energy obtained by microgrid MGi from other microgrids in time period t; max(·) represents the maximum value; The eighth item is: Among them, σ2 represents the second penalty factor; represents the target charging state of the electric transport unit CEVn, that is, the charging requirement of the electric transport unit CEVn; Indicates buffer factor; SOC n,t represents the charging state of the electric transport unit CEVn in time period t; P n,t represents the charge and discharge power of the electric transport unit CEVn in time period t; η(·) represents the energy efficiency of the charge and discharge power of the electric transport unit CEVn; Indicates the duration of the total period; Δt indicates the total period The duration of each period in ch represents the charging efficiency of the electric transport unit CEVn, η ch ∈(0,1]; represents the charging power of the electric transport unit CEVn; Buffer Factor Defined as: Where μ represents the safety margin, μ∈[0,1]; Indicates the upper limit threshold of the electric power of the electric transport unit CEVn; The eighth item satisfies the charging requirement constraint condition, and the formula corresponding to the charging requirement constraint condition is: in, Indicates that the duration of time period t is less than the duration of the total time period; η(P n,t ) is defined as: η ch represents the charging efficiency of the electric transport unit CEVn, η dch represents the discharge efficiency of the electric transport unit CEVn, η ch ∈(0,1] and η dch ∈(0,1].
8. A dispatching device based on a microgrid coupled transportation system, characterized in that: The device comprises: A self-owned data acquisition module, used to acquire the data of the microgrid itself from the microgrid of the microgrid-coupled transportation system to obtain the microgrid's own data; wherein the microgrid-coupled transportation system includes the microgrid and at least one electric transport unit, and each of the electric transport units is electrically connected to one of the microgrids; A first interaction data acquisition module, used to acquire interaction data between the microgrid and each of the microgrids, to obtain first grid interaction data; A second interaction data acquisition module, used to acquire interaction data between the microgrid and the electric transport unit to obtain second grid interaction data; A function construction module, used for constructing a function for each of the microgrids according to the microgrid's own data, the first grid interaction data and the second grid interaction data to obtain a utility function; An action solving module, used to solve according to the utility function, a plurality of preset candidate feasible actions and a preset reinforcement learning algorithm to obtain a target feasible action; The action execution module is used to control the microgrid to execute the target feasible action so that energy is transferred between the microgrid and at least one of the microgrids.
9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the scheduling method based on the microgrid coupled transportation system as described in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the scheduling method based on a microgrid coupled transportation system according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Micro-grid group power energy transaction method
CN111626569A
Multi-microgrid load optimization scheduling method and system
CN112564102A
Energy interaction optimization method and system based on micro-grids
CN113690925A
