Active power distribution network grid planning method based on source network load storage collaborative development

Abstract

The invention discloses an active power distribution network grid planning method based on source-grid-load-storage collaborative development, and the method comprises the following steps: in order to solve the technical problem, the invention provides the method. The embodiment of the invention provides an active power distribution network grid planning method based on source network load storage collaborative development. Firstly, source network load storage planning data of an active power distribution network are acquired; then, on the basis of the source network load storage planning data, constructing source network load storage planning models based on a deep neural network algorithm; then constructing a power distribution network source network load storage collaborative planning model based on a deep neural network algorithm on the basis of each source network load storage planning model, and obtaining power distribution network source network load storage collaborative planning data; and finally, determining a source network load storage collaborative planning scheme of the active power distribution network based on an approximate dynamic planning algorithm according to the source network load storage collaborative planning model of the power distribution network. Technical innovation of an energy system is promoted, requirements for advanced technologies such as energy storage and an intelligent power grid management system are increased, and development of related technologies and industrial chains is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network planning, and in particular to a grid planning method for an active distribution network based on the coordinated development of sources, grids, loads and storage. Background Art

[0002] An active distribution network based on the coordinated development of sources, grids, loads and storage refers to the use of advanced technologies and intelligent management methods to organically combine various energy resources, grid facilities and loads to form an efficient, flexible and reliable power system. This system reduces dependence on traditional power systems and improves the resilience and adaptability of power grids. With the increase in global demand for renewable energy, traditional power systems are faced with the challenge of how to effectively integrate these distributed energy resources. The concept of active distribution networks has therefore come into being, aiming to promote large-scale access and efficient utilization of renewable energy through advanced technologies and management methods.

[0003] There are complex interactions and coupling effects between sources, grids, loads and storage. Existing technologies usually find it difficult to consider and optimize these factors simultaneously under large-scale and dynamic changes. Data on sources, grids, loads and storage are usually distributed on different systems and platforms, involving different data formats and transmission protocols. It is a technical challenge to collect and integrate these data in real time and make timely responses and decisions. Different types of sources, power grids of different sizes, diverse loads, and multiple energy storage technologies make the system more complex and heterogeneous. Traditional distribution network planning methods can no longer achieve integrated planning of "sources, grids, loads and storage", and often only focus on one aspect, such as maximizing the utilization of a single energy source or balancing the grid load, while ignoring the coordinated optimization between multiple energy sources, multiple load types and energy storage devices.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an active distribution network grid planning method based on the coordinated development of source, grid, load and storage. First, the source, grid, load and storage planning data of the active distribution network are obtained; then, the source, grid, load and storage planning models are constructed based on the deep neural network algorithm based on the source, grid, load and storage planning data; then, the distribution network source, grid, load and storage collaborative planning model is constructed based on the deep neural network algorithm based on the source, grid, load and storage planning models, and the distribution network source, grid, load and storage collaborative planning data are obtained; finally, the active distribution network source, grid, load and storage collaborative planning scheme is determined based on the approximate dynamic programming algorithm according to the distribution network source, grid, load and storage collaborative planning model. The present invention fully considers the integrated planning of "source, grid, load and storage", promotes the application and development of various new energy technologies, promotes the technological innovation of energy systems, increases the demand for advanced technologies such as energy storage and smart grid management systems, and promotes the development of related technologies and industrial chains.

[0006] The embodiment of the present application provides a method for planning an active distribution network based on the coordinated development of source, grid, load and storage, including the following steps: Obtain active distribution network source, grid, load and storage planning data; Based on the source-grid-load-storage planning data and deep neural network algorithm, various source-grid-load-storage planning models are constructed; Based on the source-grid-load-storage planning models, a distribution network source-grid-load-storage collaborative planning model is constructed based on the deep neural network algorithm, and the distribution network source-grid-load-storage collaborative planning data is obtained; According to the distribution network source-grid-load-storage collaborative planning model, the collaborative planning scheme of the active distribution network source-grid-load-storage is determined based on the approximate dynamic programming algorithm.

[0007] In a preferred embodiment, the source, network, load and storage planning data includes source planning data, network planning data, load planning data and storage planning data.

[0008] In a preferred embodiment, the specific method for constructing the source-grid-load-storage planning models based on the source-grid-load-storage planning data and the deep neural network algorithm is as follows: The calculated photovoltaic investment cost and wind power investment cost are calculated to obtain first source planning data, the photovoltaic installation capacity and wind power installation capacity are calculated to obtain second source planning data, and a source planning model is constructed according to the source planning data; The line investment cost and the substation investment cost are combined to calculate the network planning data, and the network planning model is constructed based on the network planning data; Calculate the load equipment maintenance investment cost to obtain load planning data, and build a load planning model based on the load planning data; The energy storage planning data is calculated to obtain storage planning data, and a storage planning model is constructed based on the storage planning data.

[0009] In a preferred embodiment, the distribution network source-grid-load-storage collaborative planning model includes minimizing investment costs and maximizing distributed new energy installation capacity.

[0010] In a preferred embodiment, the specific method for acquiring the distribution network source-grid-load-storage collaborative planning data is as follows: Add up the planning data of source, grid, load and storage to get the source, grid, load and storage investment cost; Adding photovoltaic access energy and wind power access energy to obtain the distributed new energy installation capacity; The source-grid-load-storage investment cost and the installed capacity of distributed renewable energy are combined to calculate the distribution network source-grid-load-storage coordinated planning data.

[0011] In a preferred embodiment, the collaborative planning scheme of determining the source-grid-load-storage of the active distribution network based on the approximate dynamic programming algorithm is specifically as follows: Abstract the state of the distribution network into a state space; Define the actions that can be performed in each state space; Adjust the planned investment costs of sources, grids, loads and storage and the installed capacity of renewable energy that can be connected; With the goal of calculating the data for the coordinated planning of power generation, grid, load and storage, a reward function is constructed; The reward function is iteratively optimized and solved to obtain a collaborative planning scheme for source, grid, load and storage in the active distribution network.

[0012] In a preferred embodiment, the source planning data includes source first planning data and source planning second data.

[0013] In a preferred embodiment, the specific method for obtaining the source second planning data is as follows: The photovoltaic access capacity and the wind power access capacity are calculated according to the number of access nodes, and the photovoltaic access capacity and the wind power access capacity are added together to obtain the source second planning data. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of a method for planning an active distribution network grid based on the coordinated development of source, grid, load and storage provided in an embodiment of the present application; DETAILED DESCRIPTION The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] Embodiment 1, as Figure 1 As shown, it is a flow chart of a method for active distribution network planning based on the coordinated development of source, grid, load and storage provided by an embodiment of the present application, and the method includes the following steps: S10, obtaining active distribution network source-grid-load-storage planning data; Obtaining source-grid-load-storage planning data for active distribution networks involves the following key steps and methods: 1. Source planning data acquisition of active distribution network: The source planning data includes source first planning data and source planning second planning data, wherein the method for obtaining the source first planning data is as follows: Firstly, the photovoltaic installation capacity and wind power installation capacity in the active distribution network are obtained, and the photovoltaic installation capacity and wind power installation capacity are added together to obtain source first planning data; The specific calculation formula for the photovoltaic installation capacity in the active distribution network is as follows:

[0016] In the formula, is the photovoltaic installed capacity, Indicates the photovoltaic node to be installed, where Indicates Nodes to be installed; The specific calculation formula for wind power installation capacity in the active distribution network is as follows:

[0017] In the formula, is the installed capacity of wind power, Indicates the wind power node to be installed, where Indicates Nodes to be installed; The specific calculation formula of the source first planning data is as follows:

[0018] In the formula, is the source first planning data, is the photovoltaic installed capacity, is the installed capacity of wind power; The method for obtaining the source second planning data is as follows: Firstly, the photovoltaic investment cost and wind power investment cost in the active distribution network are obtained, and the photovoltaic investment cost and wind power investment cost are added together to obtain the source second planning data; The specific calculation formula for obtaining the photovoltaic investment cost in the active grid is as follows:

[0019] In the formula, is the photovoltaic investment cost, is the service life of photovoltaic power generation, Indicates the photovoltaic node to be installed, where Indicates Nodes to be installed; The specific calculation formula for obtaining the wind power investment cost in the active planning network is as follows:

[0020] In the formula, is the wind power investment cost, is the service life of photovoltaic power generation, Indicates the photovoltaic node to be installed, where Indicates Nodes to be installed; The specific calculation formula of the source second planning data is as follows:

[0021] In the formula, It is the second planning data. is the photovoltaic investment cost, is the wind power investment cost; 2. Acquisition of network planning data for active planning networks: Firstly, the line investment cost and substation investment cost in the active planning network are obtained, and then the network planning data is calculated according to the preset formula; The specific calculation formula for obtaining the line investment cost in the active planning network is as follows:

[0022] In the formula, is the line investment cost, is the age of the line, is the line length, Indicates the node to be installed on the line, where Indicates Nodes to be installed; The specific calculation formula for obtaining the investment cost of substations in the active planning network is as follows:

[0023] In the formula, is the substation investment cost, is the service life of the substation, Indicates the node to be installed in the substation, where Indicates Nodes to be installed; 3. Obtaining load planning data for active planning networks: The specific calculation formula for obtaining the maintenance investment cost of load equipment in the active planning network is as follows:

[0024] In the formula, It is the equipment maintenance investment cost. is the age of the equipment, Indicates the node where the load is to be installed, Indicates Nodes to be installed; 4. Acquisition of storage planning data of active planning network; The specific calculation formula for energy storage investment costs in active planning networks is as follows:

[0025] In the formula, is the energy storage investment cost, is the service life of energy storage, Represents the node to be installed for energy storage, where Indicates Nodes to be installed; Among them, obtaining the source-grid-load-storage planning data of the active distribution network has the following functions: Optimize energy utilization efficiency: Through detailed data analysis, the design and operation of distributed energy systems can be optimized, energy utilization efficiency can be improved, and energy waste can be reduced; Improve grid stability and reliability: Understanding detailed data on power sources, loads, and energy storage systems can help improve grid stability and reliability, and reduce risks in grid operation through accurate prediction and scheduling; Supporting renewable energy integration: Distributed energy systems use a large amount of renewable energy, such as solar and wind power. Obtaining data can help rationally integrate these energy sources, reduce dependence on traditional power generation methods, and promote low-carbon energy transformation; Promote intelligent management of power systems: Data-driven management and optimization can realize intelligent operation and management of power systems, including real-time dispatch, load balancing and energy storage optimization, and improve system flexibility and responsiveness; Economic benefits and cost control: Data-based system planning and design can effectively control costs, reduce the overall cost of energy supply, and optimize the return on investment, which is an economic benefit to both enterprises and consumers; Support energy policy making: Provide detailed data analysis and simulation to help governments and energy management agencies formulate scientific and reasonable energy policies and regulations, promote sustainable energy development and healthy competition in the energy market; Responding to environmental and climate change challenges: By optimizing energy system design and operation, greenhouse gas emissions and environmental impacts can be reduced, helping to address global climate change challenges; S20, constructing source-grid-load-storage planning models based on the source-grid-load-storage planning data and the deep neural network algorithm, including a source-side model, a grid-side model, a load-side model, and a storage-side model; Among them, building source-grid-load-storage planning models based on source-grid-load-storage planning data and deep neural network algorithms has the following functions: Accurate system planning and optimization: Through source-grid-load-storage planning data, models of the source side, grid side, load side, and storage side can be established to help system designers accurately evaluate and plan each component, thereby optimizing overall system performance; Enhanced system reliability and stability: These models can be used for analysis at the design stage or operation stage to improve the reliability and stability of the power system. Through prediction and optimization, the risk of grid failures and power outages can be reduced. Supporting high-proportion integration of renewable energy: As the proportion of renewable energy increases, the system needs to be flexibly scheduled and optimized. The establishment of various models can help effectively integrate unstable energy sources such as solar energy and wind energy, and reduce dependence on traditional power generation methods; Improved economy and cost-effectiveness: Model-based system planning and design can optimize resource allocation to the greatest extent, reduce energy costs and operating costs, and improve energy utilization efficiency, thereby bringing economic benefits; Intelligent operation and management: These models can support the intelligent operation and management of power systems. Through real-time data analysis and feedback, more accurate load scheduling can be achieved, the operation strategy of energy storage systems can be optimized, and the flexibility and response speed of the system can be improved. Support policy making and decision-making: Governments and energy management agencies can use the results of these models to formulate more scientific and feasible energy policies and development plans, which will help promote the energy industry towards sustainable and green development; Environmental and climate benefits: By optimizing the design and operation of energy systems, greenhouse gas emissions and environmental pollution can be reduced, which helps protect the environment and address climate change challenges; The source side model includes using the photovoltaic installation capacity and wind power installation capacity to calculate the source first planning data, and using the photovoltaic investment cost and wind power investment cost to calculate the source second planning data. The specific calculation formula of the source side model is as follows:

[0027] In the formula, is the source first planning data, is the photovoltaic installed capacity, is the installed capacity of wind power, is the source second planning data, is the photovoltaic investment cost, is the wind power investment cost; The grid-side model includes the use of line investment costs and substation investment costs to calculate the grid planning data. The specific calculation formula is as follows:

[0028] In the formula, is the line investment cost, is the substation investment cost; The load-side model includes the load planning data calculated by using the load equipment maintenance investment cost. The specific calculation formula is as follows:

[0029] In the formula, It is the investment cost for load equipment maintenance; The storage side model includes using the energy storage investment cost to calculate the load planning data. The specific calculation formula is as follows:

[0030] In the formula, is the energy storage investment cost; S30, based on the source-grid-load-storage planning models, a distribution network source-grid-load-storage collaborative planning model is constructed based on a deep neural network algorithm, and distribution network source-grid-load-storage collaborative planning data is obtained; Integrate the sub-models of source, grid, load and storage to establish a complete source, grid, load and storage collaborative planning model. The specific calculation formula of the source, grid, load and storage collaborative planning model is as follows:

[0031] is the investment cost of source, grid, load and storage, is the source planning data, It is network planning data. It is the planning data. It is storage planning data. is the installed capacity of new energy sources, is the photovoltaic access energy, It is the energy access of wind power; The source-grid-load-storage collaborative planning data is calculated based on the source-grid-load-storage collaborative planning model. The specific calculation formula is as follows:

[0032] It is the source-grid-load-storage collaborative planning data. is the investment cost of source, grid, load and storage, is the installed capacity of new energy sources; Through this comprehensive modeling approach, the planning and operation of the source-grid-load-storage system can be effectively optimized, energy utilization efficiency can be improved, operating costs can be reduced, and the development of the power system towards a more sustainable and intelligent direction can be supported.

[0033] Among them, building a distribution network source-grid-load-storage collaborative planning model based on the source-grid-load-storage planning model based on the deep neural network algorithm can bring many benefits: Optimizing energy supply and demand matching: The collaborative planning model can accurately predict power demand and available energy supply by comprehensively considering data and characteristics from the source side, grid side, load side, and storage side. This helps to more effectively adjust the grid operation mode to meet demand in different time periods and load conditions; Improve the stability and reliability of the power system: Collaborative planning can reduce potential risks and instability in the power grid. By rationally allocating and utilizing various resources, such as renewable energy and energy storage systems, it can reduce the risks of system operation and improve the stability of the power system. Reduce energy and operating costs: The collaborative planning model can optimize resource allocation and power dispatch strategies, maximize the use of low-cost energy resources, and thus reduce overall energy and operating costs, which is crucial to improving the economic benefits of energy supply; Supporting large-scale integration of renewable energy: As the proportion of renewable energy increases, the collaborative planning model can effectively integrate unstable energy sources such as solar and wind power, and combine them with energy storage systems for balancing and scheduling to ensure the sustainability and stability of the power grid; Promote intelligent management of energy systems: The collaborative planning model provides theoretical support and practical basis for the intelligent operation and management of power systems. Through real-time data analysis and feedback, more accurate load scheduling and equipment operation control can be achieved, improving the response speed and flexibility of the system; Supporting future energy policy and technology development: The establishment of a collaborative planning model provides guidance for future energy policy and technology development. It can assess the impact of new technologies and policies on the system and help decision makers develop more scientific and feasible development strategies; S40, determining a collaborative planning scheme for the source, grid, load and storage of the active distribution network based on the distribution network source, grid, load and storage collaborative planning model and an approximate dynamic programming algorithm.

[0034] Dynamic programming is usually used to solve optimization problems with multi-stage decision-making and state transitions. However, in practical applications, the complexity and large-scale nature of distribution networks make it difficult to directly apply classical dynamic programming methods. Therefore, it is more realistic and feasible to use approximate dynamic programming algorithms to deal with them. According to the source-grid-load-storage collaborative planning model of the distribution network, an approximate dynamic programming algorithm is used to determine the collaborative planning scheme of the active distribution network, which can be divided into the following key steps and considerations: 1. Model building State space definition: The state of the distribution network is abstracted into state space; Action space definition: define the actions that can be performed in each state space; Reward function: Set the reward function. The goal is to maximize the planning data. The design of the reward function needs to comprehensively consider the trade-offs between different objectives. 2. Application of approximate dynamic programming algorithm Approximate dynamic programming algorithms use approximate value functions to learn and optimize strategies to solve optimization problems in large-scale state spaces and continuous action spaces. In the distribution network scenario, common algorithms include: Value iteration: gradually optimize the strategy by iteratively updating the value function; Strategy iteration: directly find the optimal strategy by iteratively optimizing the selection of strategies; Q-Learning: A reinforcement learning algorithm based on action-value function, which learns the optimal strategy by optimizing the exploration and exploitation strategies; 3. Model solution steps Initialization: set the initial state and parameters; Status update: Update the system status based on the current status and action selection; Reward calculation: Calculate the reward under the current state according to the reward function; Value function update: Use an approximate dynamic programming algorithm to update the value function to reflect the long-term cumulative reward of the state; Strategy update: select a new optimal strategy based on the updated value function; 4. Model optimization and result evaluation Parameter adjustment: According to the actual performance of the model, adjust the algorithm parameters and model structure to improve performance and convergence speed.

[0035] Result evaluation: Verify the effectiveness and reliability of the model through simulation, experimental data or historical data, and confirm whether the optimization results meet the design requirements.

[0036] 5. Implementation and Deployment Once the optimal collaborative planning scheme is determined, it can be implemented into the actual distribution network management system, which involves the process of real-time data collection, control and execution of optimization strategies. The distribution network source-grid-load-storage collaborative planning model is based on an approximate dynamic programming algorithm. It achieves the optimal scheduling of energy resources and minimization of costs by optimizing a complex system with multiple variables and multiple objectives. This method not only improves the energy utilization efficiency of the distribution network, but also helps to improve the stability and sustainability of the power grid and adapt to the needs of the complex energy environment in the future.

[0037] Approximate Dynamic Programming (ADP) has several benefits that make it very useful in solving complex problems: Handling large-scale state spaces: Traditional dynamic programming methods face computational and storage difficulties when the state space is very large or continuous. ADP can handle these situations efficiently through approximate function approximation, allowing computation in larger state spaces; Processing continuous action space: Similar to large-scale state space, if the action space is continuous, traditional discrete methods are difficult to apply directly. ADP can better process continuous action space through function approximation; Generalization: ADP uses function approximation methods, such as deep neural network algorithms or basis functions, which can learn and generalize to unseen states, which enables the algorithm to better generalize to new situations based on the experience accumulated during training; Flexibility: ADP is very flexible because it can choose different approximate function approximation methods. It can choose the most appropriate approximate model according to the specific problem. This flexibility enables ADP to adapt to problems of different complexity and characteristics; Computational efficiency: Compared with directly storing and calculating all possible state values ​​or policy values, ADP can usually find approximately optimal solutions in a more efficient way, which is particularly important in real-time decision-making problems that require fast response; Adaptability: ADP is not limited to solving standard reinforcement learning problems, but can also be extended to include multi-objective optimization, constrained optimization and other complex decision-making problems, making its application range wider.

[0038] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0039] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for planning an active distribution network based on the coordinated development of source, grid, load and storage, characterized in that: The following steps are involved: Obtain active distribution network source, grid, load and storage planning data; Based on the source-grid-load-storage planning data and deep neural network algorithm, various source-grid-load-storage planning models are constructed; Based on the source-grid-load-storage planning models, a distribution network source-grid-load-storage collaborative planning model is constructed based on the deep neural network algorithm, and the distribution network source-grid-load-storage collaborative planning data is obtained; According to the distribution network source-grid-load-storage collaborative planning model, the collaborative planning scheme of the active distribution network source-grid-load-storage is determined based on the approximate dynamic programming algorithm.

2. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The source, network, load and storage planning data includes source planning data, network planning data, load planning data and storage planning data.

3. The active distribution network planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The specific acquisition method of constructing the source-grid-load-storage planning model based on the source-grid-load-storage planning data and the deep neural network algorithm is as follows: The photovoltaic investment cost and the wind power investment cost are calculated to obtain the second source planning data, and the source planning model is constructed in combination with the first source planning data; The line investment cost and the substation investment cost are combined to calculate the network planning data, and the network planning model is constructed based on the network planning data; Calculate the load equipment maintenance investment cost to obtain load planning data, and build a load planning model based on the load planning data; The energy storage planning data is calculated to obtain storage planning data, and a storage planning model is constructed based on the storage planning data.

4. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The distribution network source-grid-load-storage collaborative planning model includes minimizing investment costs and maximizing distributed renewable energy installation capacity.

5. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The specific method for acquiring the distribution network source-grid-load-storage collaborative planning data is as follows: Add up the planning data of source, grid, load and storage to get the source, grid, load and storage investment cost; Adding photovoltaic access energy and wind power access energy to obtain the distributed new energy installation capacity; The source-grid-load-storage investment cost and the installed capacity of distributed renewable energy are combined to calculate the distribution network source-grid-load-storage coordinated planning data.

6. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The specific calculation formula of the distribution network source-grid-load-storage collaborative planning model is as follows: is the investment cost of source, grid, load and storage. is the source planning data, It is network planning data. It is the planning data. It is storage planning data. It is the installed capacity of distributed renewable energy, including source-first planning data, is the photovoltaic access capacity, is the wind power access capacity.

7. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The specific calculation formula for the distribution network source-grid-load-storage collaborative planning data is as follows: The source-grid-load-storage collaborative planning data is calculated based on the source-grid-load-storage collaborative planning model. The specific calculation formula is as follows: It is the source-grid-load-storage collaborative planning data. is the investment cost of source, grid, load and storage, It is the installed capacity of new energy.

8. The active distribution network planning method based on the coordinated development of source, grid, load and storage as claimed in claim 1, characterized in that: The collaborative planning scheme for determining the source, grid, load and storage of the active distribution network based on the approximate dynamic programming algorithm is specifically as follows: Abstract the state of the distribution network into a state space; Define the actions that can be performed in each state space; Adjust the planned investment costs of sources, grids, loads and storage and the installed capacity of renewable energy that can be connected; With the goal of calculating the data for the coordinated planning of power generation, grid, load and storage, a reward function is constructed; The reward function is iteratively optimized and solved to obtain a collaborative planning scheme for source, grid, load and storage in the active distribution network.

9. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 2, characterized in that: The source planning data includes source first planning data and source planning second data.

10. The active distribution network grid planning method based on the coordinated development of source, grid, load and storage as claimed in claim 9, characterized in that: The specific method for obtaining the source first planning data is as follows: The photovoltaic access capacity and the wind power access capacity are calculated according to the number of access nodes, and the photovoltaic access capacity and the wind power access capacity are added together to obtain the source first planning data.

Images