Power transmission network frame extension planning optimization method and device considering extreme scene

Abstract

The invention relates to the technical field of electrical engineering, and provides a power transmission network frame extension planning optimization method and device considering an extreme scene. The method comprises the following steps: firstly, acquiring historical data of an extreme disaster scene of a power grid, and performing primary processing to obtain an extreme scene set; then, a power transmission network frame extension optimization objective function is constructed, and the power transmission network frame extension optimization objective function comprises an economic index and a stability index; then, constraint conditions are set based on the power transmission network frame extension optimization objective function; and finally, a TD3 algorithm improved based on a multi-task learning algorithm is adopted to solve and obtain a new energy multi-infeed power transmission network frame extension planning model based on the extreme scene set and the power transmission network frame extension optimization objective function. The overall anti-risk capability of the power grid is enhanced, the structural toughness of the power grid is enhanced, the safe operation level of the power grid under the extreme weather condition is comprehensively improved, and the emergency response capability under the extreme weather condition is enhanced. And the stability, the reliability and the anti-risk capability of the power grid are improved.

Description

Technical Field

[0001] The present application relates to the field of electrical engineering technology, and in particular to a method and device for optimizing transmission network expansion planning taking into account extreme scenarios. Background Art

[0002] The new energy system is an inevitable choice to ensure national energy security. my country's energy distribution and load center show inverse distribution characteristics, and the development of renewable energy is mainly concentrated in natural resource-rich areas such as the west and north. As global climate change has intensified the frequency of extreme weather, the above-mentioned regions are constrained by geographical location, climate conditions, and the continuous increase in the proportion of renewable energy, resulting in a significant reduction in the voltage support strength of their AC transmission lines, and the balance of power and electricity is facing major challenges. The extreme scenarios brought about by climate change have put forward new requirements for the planning and construction of the transmission network.

[0003] At present, the main research methods for the planning of transmission networks in which new energy replaces conventional units are numerical solutions, heuristic learning methods, and reinforcement learning methods. Among them, the numerical solution mainly uses robust optimization technology, multi-scenario technology, and collaborative planning technology for modeling research, and its specific application scenario is determined by the objective function of grid expansion planning. The planning scenario of robust optimization technology emphasizes the safety of the solution, while the transmission network planning based on multi-scenario technology focuses more on the economy of the solution. The collaborative planning technology is suitable for the scenario where a variety of renewable energy sources are concentratedly connected to the power grid. However, when solving the planning and construction scheme of large-scale power grids, the numerical solution has the problem of difficulty in migrating scenarios due to the high computational complexity. Based on this, some scholars have proposed to use heuristic learning algorithms to avoid the defects of numerical solutions, simulate transmission network planning scenarios in a data-driven way, and reduce dependence on physical models. Although the heuristic algorithm has a high solution efficiency, the process of solving the optimal solution is separated from the physical model, and the interpretability of the power grid planning operation is poor. The reinforcement learning algorithm optimizes the decision-making strategy through interaction with the environment, guides the active learning process and mines the optimal solution with a reward mechanism, and shows higher adaptability and robustness in a complex and dynamically changing environment.

[0004] At present, the research on the optimization of transmission network expansion with multiple feed-in of renewable energy is relatively conservative, and the application scenarios are mainly normal operation under universal conditions. However, with the intensification of global climate change, the operation scenarios of power systems have become more extreme. Natural disasters such as cold waves, typhoons, and floods have caused serious damage to the transmission network, while continuous hot and windless weather and extremely cold and lightless weather have a strong impact on renewable energy. The extreme scenarios faced by the expansion planning of the new power system grid can be mainly divided into three categories: low output scenarios of generator sets, surge load scenarios, and disconnection scenarios of transmission networks, which are mainly affected by extreme meteorological disasters. At present, there is little research on the planning of transmission networks with multiple feed-in of renewable energy under extreme scenarios.

[0005] Therefore, in the relevant technology, there is an urgent need for a method that can improve the emergency response capability and stability of the power grid in complex environments. Summary of the invention

[0006] Based on this, it is necessary to provide a transmission network expansion planning optimization method and device that takes extreme scenarios into consideration and can improve the emergency response capability and stability of the power grid in complex environments in response to the above technical problems.

[0007] In a first aspect, the present application provides a method for optimizing transmission network expansion planning considering extreme scenarios. The method comprises: Obtain historical data of extreme disaster scenarios of power grids and perform preliminary processing to obtain extreme scenario sets; Constructing a transmission grid expansion optimization objective function, wherein the transmission grid expansion optimization objective function includes an economic index and a stability index; Setting constraints based on the transmission grid expansion optimization objective function; The TD3 algorithm improved based on the multi-task learning algorithm is used to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain the renewable energy multi-feed transmission grid expansion planning model.

[0008] Optionally, in one embodiment of the present application, the acquiring of historical data of extreme disaster scenarios of power grids and performing preliminary processing to obtain an extreme scenario set includes: Based on the classification and extraction of historical data of extreme disaster scenarios of the power grid, extreme scenario samples are obtained; For extreme scene samples of different categories, a simulation method is used to generate extreme scene sets based on their dynamic characteristics.

[0009] Optionally, in one embodiment of the present application, the acquiring of historical data of extreme disaster scenarios of power grids and performing preliminary processing to obtain an extreme scenario set further comprises: Based on the system power and electricity balance relationship, the historical data of the extreme disaster scenarios of the power grid are secondary screened to extract a supplementary scenario set of power and electricity imbalance.

[0010] Optionally, in one embodiment of the present application, constructing the transmission grid expansion optimization objective function includes: Determine the construction and operation and maintenance costs of the transmission network based on the investment cost of transmission network construction, operation and maintenance costs, and additional costs of new energy grid connection; Determine the voltage support strength margin of the transmission grid based on the short-circuit ratio and critical short-circuit ratio of the new energy grid connection point; The transmission grid expansion optimization objective function is determined based on the transmission grid construction, operation and maintenance costs and the transmission grid voltage support strength margin.

[0011] Optionally, in one embodiment of the present application, the constraint conditions include node power balance constraint, power flow balance constraint, line transmission capacity constraint, voltage support strength margin constraint and N-1 safety constraint.

[0012] Optionally, in one embodiment of the present application, the TD3 algorithm improved based on the multi-task learning algorithm includes: The action network in the TD3 algorithm is used to select the execution action of the transmission line state change; Use multi-task learning algorithms to improve the action network and the corresponding target actions; The key transmission lines are screened through the dual evaluation network, and the reward value generated by executing the action is calculated based on the dual objective network.

[0013] Optionally, in one embodiment of the present application, the algorithm formula for improving the action network and the corresponding target action using the multi-task learning algorithm is:

[0014]

[0015]

[0016]

[0017] in, represents the probability of executing an action on each line, Indicates the current line status set, , and They represent the expert network, the gated network, and the tower network respectively. , and Represent the parameters of the expert network, the gated network, and the tower network, respectively. represents the weight vector generated by the gating network, represents the set of weighted action probabilities, Indicates the execution of an action.

[0018] In a second aspect, the present application also provides a transmission grid expansion planning optimization device considering extreme scenarios. The device comprises: The extreme scenario set acquisition module is used to acquire the historical data of extreme disaster scenarios of the power grid and perform preliminary processing to obtain the extreme scenario set; An objective function building module is used to build an objective function for optimizing the expansion of a power transmission grid, wherein the objective function for optimizing the expansion of a power transmission grid includes an economic index and a stability index; A constraint condition setting module, used for setting constraint conditions based on the transmission grid expansion optimization objective function; The transmission grid expansion planning optimization module is used to adopt the TD3 algorithm improved based on the multi-task learning algorithm to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain a new energy multi-feed transmission grid expansion planning model.

[0019] The above-mentioned transmission network expansion planning optimization method considering extreme scenarios first obtains the historical data of extreme disaster scenarios of the power grid, and performs preliminary processing to obtain the extreme scenario set; then, constructs the transmission network expansion optimization objective function, and the transmission network expansion optimization objective function includes economic indicators and stability indicators; then, sets constraints based on the transmission network expansion optimization objective function; finally, the TD3 algorithm improved based on the multi-task learning algorithm is used to solve the extreme scenario set and the transmission network expansion optimization objective function to obtain the new energy multi-feed transmission network expansion planning model. In other words, through the simulation generation of the extreme scenario set, as an interactive environment of the new energy multi-feed transmission network expansion planning model, it helps to optimize the structural design and operation mode of the power grid, reduce the system's dependence on a single device or line, thereby enhancing the overall risk resistance of the power grid, helping to enhance the structural resilience of the power grid, and comprehensively improve the safe operation level of the power grid under extreme weather conditions and enhance the emergency response capability under extreme weather conditions. At the same time, based on the economy and stability of the grid expansion planning, the constraints are taken into account to build a grid expansion planning model to ensure that the transmission grid can still operate normally after a failure under extreme weather conditions, thereby supporting the safe dispatch and control of the entire power grid, and fundamentally improving the stability, reliability and risk resistance of the power grid. The TD3 algorithm improved based on the multi-task learning algorithm is used to solve the transmission network planning scheme that takes into account both economy and stability. On the basis of the superior performance of the TD3 algorithm, it ensures that the intelligent agent can independently extract other information while sharing the same expert experience, so that the intelligent agent can better adapt to different environmental changes, thereby improving the generalization ability and calculation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 An application environment diagram of a transmission grid expansion planning optimization method considering extreme scenarios in one embodiment; Figure 2 A schematic diagram of a flow chart of a method for optimizing transmission grid expansion planning considering extreme scenarios in one embodiment; Figure 3 A schematic diagram of the structure of the TD3 algorithm in one embodiment; Figure 4 A schematic diagram of improving an action network using a multi-task learning algorithm in one embodiment; Figure 5 A flowchart showing specific steps of a method for optimizing transmission network expansion planning considering extreme scenarios in one embodiment; Figure 6 A structural block diagram of a transmission grid expansion planning optimization device considering extreme scenarios in one embodiment; Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0021] 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.

[0022] The transmission network expansion planning optimization method considering extreme scenarios provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0023] In one embodiment, Figure 2 As shown in the figure, a transmission grid expansion planning optimization method considering extreme scenarios is provided. Figure 1 The server in the example is used to illustrate the following steps: S201: Obtain historical data of extreme disaster scenarios of the power grid, and perform preliminary processing to obtain an extreme scenario set.

[0024] In the embodiment of the present application, first, historical data of extreme disaster scenarios of the power grid are obtained, and the historical data are preliminarily processed to obtain an extreme scenario set. The extreme scenarios faced when planning the expansion of the new power system grid mainly refer to the direct or indirect impact of severe weather on new energy units, traditional generators and transmission grids, resulting in an imbalance in the supply and demand relationship of power grid sources and loads and a continuous gap in the absorption of new energy, and even causing large-scale disconnection of new energy units and disconnection of transmission grids, leading to large-scale power outages. The extreme scenarios of the new power system are strongly coupled with severe meteorological disasters, and the intensity and type of meteorological disasters have obvious spatiotemporal distribution characteristics, and the generation and development process of meteorological disasters are difficult to predict, so extreme scenarios have significant spatiotemporal and random characteristics. Simulations are generated for different extreme scenarios to construct a set of extreme scenarios with typical characteristics.

[0025] Specifically, in one embodiment of the present application, the acquiring of historical data of extreme disaster scenarios of power grids and performing preliminary processing to obtain an extreme scenario set includes: S301: Obtain extreme scenario samples based on classification and extraction of historical data of extreme disaster scenarios of the power grid.

[0026] S303: For extreme scene samples of different categories, a simulation method is used to generate an extreme scene set based on their dynamic characteristics.

[0027] In one embodiment of the present application, for low-output scenarios and load surge scenarios of generator sets, a threshold method is used to identify and extract extreme scenario samples through comprehensive analysis of the new energy output data and load data of a certain area's power grid. According to the system's generator set structure, grid line topology, load dynamic characteristics and other electrical quantities, the lower output limit and upper load limit of conventional units and new energy units are set, and the scenarios in which the generator set output is lower than the threshold and the load level exceeds the load limit in the historical scenario sample set are identified and screened, and typical extreme scenarios are extracted to construct a sparse extreme scenario set. The criteria for low-output scenarios and load surge scenarios of generator sets are as follows:

[0028] in, Representation Node The total output of all generators, Representation Node The total maximum output of all generators; Representation Node The load value, Representation Node Maximum load value; and They respectively represent the low output coefficient and load growth coefficient of the generator set. When the output power of the generator set is less than the low output threshold, the unit is judged to have entered a low output state; when the regional load exceeds the limit load margin, the power grid operation scenario is judged to be an extreme load surge scenario.

[0029] The meteorological model simulation method and Monte Carlo sampling method are used to realize the simulation expansion of the sparse scenario set. The coupling relationship between the sparse scenario set and the regional meteorological conditions is established, and the extreme climate condition scenarios are mapped through the output data and load data of the generator sets in the sample set. The regional extreme weather is simulated based on the climate model, and then the sparse scenario set sequence is reconstructed, the generator output data and load data are recalculated, and more extreme scenarios are simulated. For the generated discrete extreme scenario sample set, the Monte Carlo sampling method is used to sample and simulate to obtain a continuous time series extreme scenario sample set. According to the generator and load data generated by the meteorological simulation model, a probabilistic model of the extreme scenario set is constructed, so as to sample and generate a complete extreme scenario set.

[0030] In addition, in one embodiment of the present application, the acquiring of historical data of extreme disaster scenarios of power grids and performing preliminary processing to obtain an extreme scenario set further includes: Based on the system power and electricity balance relationship, the historical data of the extreme disaster scenarios of the power grid are secondary screened to extract a supplementary scenario set of power and electricity imbalance.

[0031] In one embodiment of the present application, the probability of occurrence of a severe extreme scenario of a power transmission grid disconnection is extremely small, and it is difficult to find a scenario with typical characteristics. Therefore, for the simulation of the disconnection scenario, the different directions of the typhoon attack are considered, the transient process is ignored, and only the power transmission grid optimization scheme that the system can still be put into operation when some nodes are disconnected from the grid is considered. After the grid disconnection occurs, it can be expressed as:

[0032] in, Represents the disconnection probability factor, which is a random array between 0 and 1, used to indicate the possibility of random disconnection of the transmission grid under typhoon attack. and They represent the set of transmission lines before and after the disconnection occurs.

[0033] S203: Constructing a transmission grid expansion optimization objective function, wherein the transmission grid expansion optimization objective function includes an economic index and a stability index.

[0034] In the embodiment of the present application, in order to solve the transmission expansion planning problem of large-scale grid connection of new energy in extreme scenarios, it is necessary to consider the construction and operation costs of the transmission grid, and to improve the voltage support strength of the transmission grid to cope with the large-capacity access of new energy while taking into account the economy. Therefore, the construction, operation and maintenance costs of the transmission grid are used as economic indicators, and the short-circuit ratio of the grid new energy grid connection point is used as a stability indicator, and the transmission grid expansion optimization objective function is constructed by taking into account both economy and stability.

[0035] In one embodiment of the present application, constructing a transmission grid expansion optimization objective function includes: S401: Determine the transmission network construction and operation and maintenance costs based on the transmission network construction investment cost, operation and maintenance costs and the additional costs of new energy grid connection.

[0036] S403: Determine the voltage support strength margin of the transmission grid based on the short-circuit ratio and critical short-circuit ratio of the new energy grid connection point.

[0037] S405: Determine a transmission network expansion optimization objective function based on the transmission network construction, operation and maintenance costs and the transmission network voltage support strength margin.

[0038] In one embodiment of the present application, the transmission network construction and operation costs and the grid voltage support strength are taken as optimization targets. , Operation and maintenance costs Additional costs for connecting to the grid with new energy sources The comprehensive total cost is used as an indicator to measure the economy of grid construction. The short-circuit ratio margin of the energy grid connection point is used as an indicator to measure the stability of grid construction. The optimization objective function of the transmission grid expansion planning model with multiple feeds of renewable energy under extreme scenarios is constructed.

[0039] The investment cost of transmission network construction mainly considers the line construction cost between grid nodes and the line construction cost of connecting new energy units to the grid. The expression is as follows:

[0040] in, represents the investment cost of transmission network construction, and They represent the construction status of the lines connected to the new energy units between the grid nodes, and and Respectively represent the [0,1] construction state variables; Indicates line The investment price of construction.

[0041] The operation and maintenance cost of the transmission network includes the power generation cost of synchronous machines and new energy units, the line power loss cost, and the inspection and maintenance cost of the transmission network. The expression is as follows:

[0042] in, represents the operation and maintenance cost of the transmission network, and Represent the total power of synchronous machine and new energy unit respectively, and and They correspond to their operating cost coefficients respectively, and They represent the line loss cost coefficient and line maintenance cost coefficient respectively. Represents the set of construction lines. Since the construction of one line corresponds to two grid nodes, and They represent the phase angles of the two nodes connected by the line, Indicates the resistance value of this line. Indicates the total length of all lines constructed.

[0043] Since the power generation of new energy units is volatile and intermittent, additional costs will be added during the grid connection process, mainly including power fluctuation penalty costs and wind and solar abandonment penalty costs, which are expressed as follows:

[0044] in, represents the additional cost of connecting new energy to the grid, It indicates the actual power fluctuation caused by the power generation of new energy units on the line, and It indicates the power flow of the line under normal working conditions. When the power fluctuation is small, the "wind and solar abandonment" of the new energy units is not serious, so the penalty cost is not taken into account; and They represent the power fluctuation penalty cost coefficient and the wind and solar power abandonment penalty cost coefficient respectively. When the power fluctuation is more obvious, the new energy grid connection penalty cost is imposed on the power grid planning according to the power fluctuation amount.

[0045] The construction, operation and maintenance cost of the transmission grid, i.e. the comprehensive total cost, can be expressed as:

[0046] When planning the transmission network, the static voltage stability of the grid is approximately analyzed by static analysis, and the multi-feed model of renewable energy is subjected to Thevenin equivalence. Based on the superposition theorem, the equivalent decoupling analysis of the AC grid and renewable energy is realized. The voltage characteristics of the transmission grid do not change before and after the equivalence. The stability of the grid expansion plan is measured by the short-circuit ratio index of the renewable energy grid connection point. The calculation formula is as follows:

[0047] in, represents the short circuit ratio, Indicates the nominal voltage of the new energy grid connection point. It represents the equivalent potential of the grid connection point. Indicates the offset voltage of the grid connection point, Indicates the node voltage of the new energy grid connection point.

[0048] The critical short-circuit ratio is the short-circuit ratio corresponding to the system being in a critical stable state, which can be used to evaluate the strength of the transmission grid. The calculation formula for the critical short-circuit ratio of the new energy grid connection point is as follows:

[0049] in, represents the critical short-circuit ratio, For synchronous machines to connect to new energy grids Provided short circuit capacity, Corresponding network point The maximum transmission power of the line when it is in critical stability, Equivalent grid-connected capacity of new energy The reactive power corresponding to the imaginary part.

[0050] The difference between the short-circuit ratio of the grid connection point and the critical short-circuit ratio is used as the voltage support strength margin of the transmission grid. The greater the voltage support strength, the stronger the voltage support strength of the system. The stability margin calculation formula is as follows:

[0051] Therefore, the optimization objective function of the transmission grid expansion planning model with multiple new energy feed-ins under extreme scenarios can be expressed as:

[0052] in, Represents the objective function. Since the goal is to maximize the stability margin, it is represented as a negative value here.

[0053] S205: Setting constraints based on the transmission grid expansion optimization objective function.

[0054] In the embodiment of the present application, constraints are set based on the optimization objective function, that is, a constraint set is set for the transmission grid expansion planning model with multiple inputs of new energy under extreme scenarios.

[0055] Specifically, in one embodiment of the present application, the constraint conditions include node power balance constraint, power flow balance constraint, line transmission capacity constraint, voltage support strength margin constraint and N-1 safety constraint.

[0056] In one embodiment of the present application, the expression of the node power balance constraint is as follows:

[0057] in, Representation Node The total output of all synchronous machines, Representation Node The total output of all new energy units, Representation Node The difference between the power flowing into and out of the line is Representation Node of the total load.

[0058] The expression of the power flow balance constraint is as follows:

[0059] in, Indicates line The susceptance value, and They respectively represent the phase angles of the two nodes connected by the line.

[0060] The expression of line transmission capacity constraint is as follows:

[0061] in, Indicates the maximum transmission power of the line.

[0062] The expression of voltage support strength margin constraint is as follows:

[0063] The expression of the N-1 safety constraint is as follows:

[0064] in, Indicates the node under N-1 condition The total output of all synchronous machines, Indicates the node under N-1 condition The total output of all new energy units, Indicates the node under N-1 condition The difference between the power flowing into and out of the line is Indicates the node under N-1 condition When the agent performs a new action, it will evaluate the previous action and return the reward value, and substitute the power grid into the N-1 scenario to test the grid voltage stability to guide the next action.

[0065] S207: Using the TD3 algorithm improved based on the multi-task learning algorithm to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain a new energy multi-feed transmission grid expansion planning model.

[0066] In the embodiment of the present application, the TD3 algorithm is a reinforcement learning algorithm based on an action-evaluation framework, which can be used to solve the continuous action space problem of power transmission network planning in extreme scenarios. The TD3 algorithm is used to implement the state transition of the transmission line. Based on the current line state, the action network selects the execution action, and the evaluation network evaluates the execution action. The line state is transformed and the reward value is obtained by executing the action until the intelligent agent finds a planning scheme that takes into account the economy and reliability of the transmission network. The action value function Q is independently estimated by two evaluation networks, and the smaller value of the estimated value is taken to calculate the target Q value, which effectively reduces the over-estimation problem caused by the maximization operation. At the same time, since the target network updates parameters more slowly than the evaluation network, the process of calculating the target Q value is smoother, which solves the bootstrap problem to a certain extent. Figure 3 As shown, this is a schematic diagram of the structure of the TD3 algorithm.

[0067] Since the TD3 algorithm uses the line state space as the algorithm input when solving the transmission network planning problem, it is difficult to take into account the characteristics of each line through a single Actor network calculation when calculating the action probability of each line, and it is affected by different experiences. Therefore, the multi-task learning algorithm (MMOE) is used to improve the TD3 agent, and the expert network is used to realize parameter sharing between tasks, thereby improving the agent's ability to extract the same knowledge; the multi-gating mechanism and specific task tower can realize the independent solution of the action probability of each line, and extract information other than the same knowledge from multiple perspectives, thereby ensuring that the agent can share expert experience when solving tasks while performing differentiated independent calculations, effectively improving the model's solution efficiency, and achieving better strategy learning in different environments. Figure 4 As shown in Figure 1, it is a schematic diagram of the improvement of the action network by the multi-task learning algorithm, where represents the probability of choosing a certain action, Indicates the execution of an action, and Tower indicates a network of multiple towers.

[0068] Specifically, in one embodiment of the present application, the TD3 algorithm improved based on the multi-task learning algorithm includes: S501: Using the action network in the TD3 algorithm to select an execution action for a transmission line state change.

[0069] S503: Using a multi-task learning algorithm to improve the action network and the corresponding target action.

[0070] S505: Screening critical transmission lines through the dual evaluation network, and calculating the reward value generated by executing the action based on the dual objective network.

[0071] In one embodiment of the present application, the action network in the TD3 algorithm is used to select the execution action of the transmission line state change, the dual evaluation network is used to screen the key transmission lines, and the reward value generated by the execution action is calculated based on the dual target network. and the action network, which selects and executes actions , get the next state and rewards , the algorithm state space is as follows:

[0072] First, based on the state and the target action network to generate execution actions Then, based on the idea of ​​dual networks, the target Q value is estimated through the relatively small values ​​in the two target evaluation networks. Finally, the gradient descent algorithm is used to minimize the error between the evaluation value and the target value, thereby updating the parameters in the dual evaluation network. The calculation formula is as follows:

[0073] in, represents the target action network, represents the target action network parameters, represents the target review network parameters, represents the comment network parameters, represents a dual-objective review network, represents the profit factor, represents the target Q value, represents the loss function of the review network, represents the number of samples, Represents the actions produced by the action network.

[0074] The TD3 algorithm introduces a delayed policy update mechanism, that is, the action network is updated only after a certain number of review network updates, thereby providing more stable feedback for the action network. The action network is updated based on the gradient ascent method, and its loss function and gradient are:

[0075] Based on the idea of ​​multi-gated hybrid expert network, the Actor network and the corresponding target Actor are improved, realizing the improvement from a single Actor network calculating the action probability of multiple lines to a multi-task tower network calculating the action probability of each line separately.

[0076] In one embodiment of the present application, the algorithm formula for improving the action network and the corresponding target action using the multi-task learning algorithm is:

[0077]

[0078]

[0079]

[0080] in, represents the probability of executing an action on each line, Indicates the current line status set, , and They represent the expert network, the gated network, and the tower network respectively. , and Represent the parameters of the expert network, the gated network, and the tower network, respectively. represents the weight vector generated by the gating network, represents the set of weighted action probabilities, Indicates the execution of an action.

[0081] In the above-mentioned transmission network expansion planning optimization method considering extreme scenarios, first, the historical data of extreme disaster scenarios of the power grid are obtained, and preliminary processing is performed to obtain an extreme scenario set; then, a transmission network expansion optimization objective function is constructed, and the transmission network expansion optimization objective function includes economic indicators and stability indicators; then, constraints are set based on the transmission network expansion optimization objective function; finally, the TD3 algorithm improved based on the multi-task learning algorithm is used to solve the extreme scenario set and the transmission network expansion optimization objective function to obtain a new energy multi-feed transmission network expansion planning model. In other words, through the simulation generation of extreme scenario sets, as an interactive environment for the new energy multi-feed transmission network expansion planning model, it helps to optimize the structural design and operation mode of the power grid, reduce the system's dependence on a single device or line, thereby enhancing the overall risk resistance of the power grid, helping to enhance the structural resilience of the power grid, and comprehensively improve the safe operation level of the power grid under extreme weather conditions and enhance the emergency response capability under extreme weather conditions. At the same time, based on the economy and stability of the grid expansion planning, the constraints are taken into account to build a grid expansion planning model to ensure that the transmission grid can still operate normally after a failure under extreme weather conditions, thereby supporting the safe dispatch and control of the entire power grid, and fundamentally improving the stability, reliability and risk resistance of the power grid. The TD3 algorithm improved based on the multi-task learning algorithm is used to solve the transmission network planning scheme that takes into account both economy and stability. On the basis of the superior performance of the TD3 algorithm, it ensures that the intelligent agent can independently extract other information while sharing the same expert experience, so that the intelligent agent can better adapt to different environmental changes, thereby improving the generalization ability and calculation accuracy.

[0082] The following is a specific example to illustrate the specific implementation steps of the transmission network expansion planning optimization method considering extreme scenarios of this application. Figure 5 As shown, first, S601, obtain the historical data of extreme disaster scenarios of the power grid, and perform preliminary processing to obtain the extreme scenario set. Specifically, S603-S607, based on the classification and extraction of the historical data of extreme disaster scenarios of the power grid, obtain extreme scenario samples; for extreme scenario samples of different categories, use simulation methods based on their dynamic characteristics to generate extreme scenario sets; based on the system power and electricity balance relationship, perform secondary screening on the historical data of extreme disaster scenarios of the power grid to extract a supplementary scenario set of power and electricity imbalance.

[0083] After that, S609, construct the transmission network expansion optimization objective function, which includes economic indicators and stability indicators. Specifically, S611-S615, determine the transmission network construction operation and maintenance costs based on the transmission network construction investment cost, operation and maintenance costs, and the additional cost of new energy grid connection; determine the transmission network voltage support strength margin based on the short-circuit ratio and critical short-circuit ratio of the new energy grid connection point; determine the transmission network expansion optimization objective function based on the transmission network construction operation and maintenance costs and the transmission network voltage support strength margin.

[0084] Then, S617, setting constraints based on the transmission grid expansion optimization objective function. S619, the constraints include node power balance constraints, power flow balance constraints, line transmission capacity constraints, voltage support strength margin constraints and N-1 safety constraints.

[0085] Finally, S621, the TD3 algorithm improved based on the multi-task learning algorithm is used to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain the new energy multi-feed transmission grid expansion planning model. Specifically, S623-S627, the action network in the TD3 algorithm is used to select the execution action of the transmission line state change; the multi-task learning algorithm is used to improve the action network and the corresponding target action; the key transmission lines are screened through the dual evaluation network, and the reward value generated by the execution action is calculated based on the dual target network. S629, the algorithm formula for improving the action network and the corresponding target action using the multi-task learning algorithm is:

[0086]

[0087]

[0088]

[0089] in, represents the probability of executing an action on each line, Indicates the current line status set, , and They represent the expert network, the gated network, and the tower network respectively. , and Represent the parameters of the expert network, the gated network, and the tower network, respectively. represents the weight vector generated by the gating network, represents the set of weighted action probabilities, Indicates the execution of an action.

[0090] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0091] Based on the same inventive concept, the embodiment of the present application also provides a device for optimizing the expansion planning of a power transmission network taking into account extreme scenarios for implementing the above-mentioned method for optimizing the expansion planning of a power transmission network taking into account extreme scenarios. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the device for optimizing the expansion planning of a power transmission network taking into account extreme scenarios provided below can be referred to the limitations of the method for optimizing the expansion planning of a power transmission network taking into account extreme scenarios above, and will not be repeated here.

[0092] In one embodiment, Figure 6 As shown, a transmission network expansion planning optimization device 600 considering extreme scenarios is provided, comprising: an extreme scenario set acquisition module 601, an objective function construction module 603, a constraint condition setting module 605 and a transmission network expansion planning optimization module 607, wherein: The extreme scenario set acquisition module 601 is used to acquire the historical data of extreme disaster scenarios of the power grid and perform preliminary processing to obtain the extreme scenario set.

[0093] The objective function construction module 603 is used to construct the transmission grid expansion optimization objective function, and the transmission grid expansion optimization objective function includes an economic index and a stability index.

[0094] The constraint condition setting module 605 is used to set constraint conditions based on the transmission grid expansion optimization objective function.

[0095] The transmission grid expansion planning optimization module 607 is used to adopt the TD3 algorithm improved based on the multi-task learning algorithm to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain a new energy multi-feed transmission grid expansion planning model.

[0096] In one embodiment of the present application, the extreme scenario set acquisition module is further used to: Based on the classification and extraction of historical data of extreme disaster scenarios of the power grid, extreme scenario samples are obtained; For extreme scene samples of different categories, a simulation method is used to generate extreme scene sets based on their dynamic characteristics.

[0097] In one embodiment of the present application, the extreme scenario set acquisition module is further used to: Based on the system power and electricity balance relationship, the historical data of the extreme disaster scenarios of the power grid are secondary screened to extract a supplementary scenario set of power and electricity imbalance.

[0098] In one embodiment of the present application, the objective function construction module is also used to: Determine the construction and operation and maintenance costs of the transmission network based on the investment cost of transmission network construction, operation and maintenance costs, and additional costs of new energy grid connection; Determine the voltage support strength margin of the transmission grid based on the short-circuit ratio and critical short-circuit ratio of the new energy grid connection point; The transmission grid expansion optimization objective function is determined based on the transmission grid construction, operation and maintenance costs and the transmission grid voltage support strength margin.

[0099] In one embodiment of the present application, the constraint conditions include node power balance constraint, power flow balance constraint, line transmission capacity constraint, voltage support strength margin constraint and N-1 safety constraint.

[0100] In one embodiment of the present application, the TD3 algorithm improved based on the multi-task learning algorithm includes: The action network in the TD3 algorithm is used to select the execution action of the transmission line state change; Use multi-task learning algorithms to improve the action network and the corresponding target actions; The key transmission lines are screened through the dual evaluation network, and the reward value generated by executing the action is calculated based on the dual objective network.

[0101] In one embodiment of the present application, the algorithm formula for improving the action network and the corresponding target action using the multi-task learning algorithm is:

[0102]

[0103]

[0104]

[0105] in, represents the probability of executing an action on each line, Indicates the current line status set, , and They represent the expert network, the gated network, and the tower network respectively. , and Represent the parameters of the expert network, the gated network, and the tower network, respectively. represents the weight vector generated by the gating network, represents the set of weighted action probabilities, Indicates the execution of an action.

[0106] Each module in the above-mentioned transmission grid expansion planning optimization device considering extreme scenarios can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0107] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a transmission grid expansion planning optimization method considering extreme scenarios is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0108] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0109] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0110] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A transmission network expansion planning optimization method considering extreme scenarios, characterized in that: The method comprises: Obtain historical data of extreme disaster scenarios of power grids and perform preliminary processing to obtain extreme scenario sets; Constructing a transmission grid expansion optimization objective function, wherein the transmission grid expansion optimization objective function includes an economic index and a stability index; Setting constraints based on the transmission grid expansion optimization objective function; The TD3 algorithm improved based on the multi-task learning algorithm is used to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain the renewable energy multi-feed transmission grid expansion planning model.

2. The method for optimizing transmission network expansion planning considering extreme scenarios according to claim 1 is characterized in that: The acquisition of historical data of extreme disaster scenarios of power grids and preliminary processing to obtain an extreme scenario set includes: Based on the classification and extraction of historical data of extreme disaster scenarios of the power grid, extreme scenario samples are obtained; For extreme scene samples of different categories, a simulation method is used to generate extreme scene sets based on their dynamic characteristics.

3. The method for optimizing transmission network expansion planning considering extreme scenarios according to claim 2 is characterized in that: The step of obtaining historical data of extreme disaster scenarios of power grids and performing preliminary processing to obtain an extreme scenario set also includes: Based on the system power and electricity balance relationship, the historical data of the extreme disaster scenarios of the power grid are secondary screened to extract a supplementary scenario set of power and electricity imbalance.

4. The method for optimizing transmission network expansion planning considering extreme scenarios according to claim 1 is characterized in that: The objective function of constructing the transmission grid expansion optimization includes: Determine the construction and operation and maintenance costs of the transmission network based on the investment cost of transmission network construction, operation and maintenance costs, and additional costs of new energy grid connection; Determine the voltage support strength margin of the transmission grid based on the short-circuit ratio and critical short-circuit ratio of the new energy grid connection point; The transmission grid expansion optimization objective function is determined based on the transmission grid construction, operation and maintenance costs and the transmission grid voltage support strength margin.

5. The method for optimizing transmission network expansion planning considering extreme scenarios according to claim 1 is characterized in that: The constraints include node power balance constraints, power flow balance constraints, line transmission capacity constraints, voltage support strength margin constraints and N-1 safety constraints.

6. The method for optimizing transmission network expansion planning considering extreme scenarios according to claim 1 is characterized in that: The TD3 algorithm improved based on the multi-task learning algorithm includes: The action network in the TD3 algorithm is used to select the execution action of the transmission line state change; Use multi-task learning algorithms to improve the action network and the corresponding target actions; The key transmission lines are screened through the dual evaluation network, and the reward value generated by executing the action is calculated based on the dual objective network.

7. The method for optimizing transmission network expansion planning considering extreme scenarios according to claim 6 is characterized in that: The algorithm formula for improving the action network and the corresponding target action using the multi-task learning algorithm is: in, represents the probability of executing an action on each line, Indicates the current line status set, , and They represent the expert network, the gated network, and the tower network respectively. , and Represent the parameters of the expert network, the gated network, and the tower network, respectively. represents the weight vector generated by the gating network, represents the set of weighted action probabilities, Indicates the execution of an action.

8. A transmission network expansion planning optimization device considering extreme scenarios, characterized in that: The device comprises: The extreme scenario set acquisition module is used to obtain the historical data of extreme disaster scenarios of the power grid and perform preliminary processing to obtain the extreme scenario set; An objective function building module is used to build an objective function for optimizing the expansion of a power transmission grid, wherein the objective function for optimizing the expansion of a power transmission grid includes an economic index and a stability index; A constraint condition setting module, used for setting constraint conditions based on the transmission grid expansion optimization objective function; The transmission grid expansion planning optimization module is used to adopt the TD3 algorithm improved based on the multi-task learning algorithm to solve the extreme scenario set and the transmission grid expansion optimization objective function to obtain a new energy multi-feed transmission grid expansion planning model.

Images