Parallel control method, device and equipment for digital twinning-oriented power transmission line system

Abstract

The invention discloses a digital twinning-oriented power transmission line system parallel control method, device and equipment. The method comprises the following steps: constructing a power transmission line system virtual model based on a digital twinning technology; acquiring state data of an actual power transmission line system in real time, and inputting the state data into the virtual model of the power transmission line system to optimize the model; based on the power transmission line system virtual model and actual power transmission line system state data collected in real time, a DDPG algorithm is adopted to formulate a power transmission line system intelligent control strategy; considering cooperative work of multiple power transmission lines, and formulating a parallel control strategy. According to the invention, the control efficiency and stability of the power transmission line can be obviously improved, and an important reference is provided for constructing an intelligent digital power transmission network.

Description

Technical Field

[0001] The present invention relates to the field of digital control of power transmission lines, and in particular to a method, device and equipment for parallel control of power transmission line systems oriented to digital twins. Background Art

[0002] With the rapid development of smart grids, traditional transmission line control methods face severe challenges in efficiency, stability and flexibility control. The increasing complexity of power systems has put forward higher requirements for the real-time, accuracy and intelligence of control strategies. Traditional line control methods are usually based on static models and are difficult to adapt to the dynamic changes of power systems. In addition, traditional time series prediction and control optimization methods have certain limitations when processing complex power system data. In order to meet these challenges, more and more research has begun to focus on the application of cutting-edge technologies such as digital twin technology, deep learning and reinforcement learning in transmission line control.

[0003] The existing literature "Research on the Application of Digital Twin Technology in Transmission Lines" introduces that the purpose of introducing digital twin technology is to achieve comprehensive simulation of power equipment and systems. Digital twin technology provides new possibilities for real-time simulation and prediction, can better understand the dynamic behavior of the power system, provide accurate support for the control decision of the smart grid, and can make the actual system evolve synchronously with the digital model, improve the accuracy and real-time performance of the model, and provide more intelligent and reliable control strategies for complex power systems. Although the existing technology enables the power system to better adapt to dynamic changes and improve the accuracy and intelligence of control decisions, the existing technology does not provide a specific solution to solve the problem of digital transmission line control, which makes the control efficiency of the transmission line system low and the stability poor. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects and problems of low control efficiency and poor stability in the prior art, and to provide a parallel control method, device and equipment for a digital twin-oriented power transmission line system with high control efficiency and good stability.

[0005] To achieve the above objectives, the technical solution of the present invention is: a parallel control method of a transmission line system for digital twins, comprising:

[0006] Construct a virtual model of the transmission line system based on digital twin technology;

[0007] Collect the status data of the actual transmission line system in real time and input it into the virtual model of the transmission line system to optimize the model;

[0008] Based on the virtual model of the transmission line system and the actual transmission line system status data collected in real time, the DDPG algorithm is used to formulate the intelligent control strategy of the transmission line system;

[0009] Considering the coordinated operation of multiple transmission lines, a parallel control strategy is formulated.

[0010] The DDPG algorithm includes a main network and a target network, the main network includes a main action network and a main evaluation network, and the target network includes a target action network and a target evaluation network;

[0011] The optimization objective function of the main action network is:

[0012]

[0013] Where N n is the number of time periods to be considered; J t is the objective function with attenuation at time t; E(·) is the expected function; γ is the discount factor, 0<γ<1; r t+n is the return value at time t+n;

[0014] The main evaluation network training optimization goal is to minimize the loss function L, and the loss function L is:

[0015] L=E(q T，t -q t ) 2 ;

[0016] In the formula, q t is the output value of the main evaluation network at time t; q T，t The output value of the evaluation network calculated for the sample to be optimized at time t;

[0017] q T，t =r t +γq′ t+1 ;

[0018] In the formula, r t is the expected return at time t; q′ t+1 The output value of the sample target evaluation network at time t+1;

[0019] The DDPG optimization algorithm is used to obtain the deep neural network parameters of the optimal main action network. and the deep neural network parameters of the main evaluation network Use the following formula to update the target network parameters:

[0020]

[0021] Where η is the divergence factor, 0<η<1; and are the deep neural network parameters of the target action network and the target evaluation network at time t; and are the deep neural network parameters of the target action network and the target evaluation network at time t-1 respectively.

[0022] The transmission line system virtual model includes a perception layer, an edge computing layer, an Internet of Things layer, a digital twin layer and an interaction layer;

[0023] The perception layer is used to realize data collection and control of the end-layer power transmission equipment;

[0024] The edge computing layer includes power intelligent terminals and aggregation gateways with edge computing capabilities. The power intelligent terminals are used to implement access management, data collection, protocol analysis, data storage, edge computing, and data forwarding to the cloud for various terminal devices of the transmission line;

[0025] The IoT layer is used to provide the measurement capability of the sensing device and the real-time control capability of the terminal device through the IoT management platform;

[0026] The digital twin layer is used to iteratively update and optimize the virtual model of the transmission line system;

[0027] The interaction layer is used to realize real-time interaction between users and models.

[0028] The edge computing layer is also used to cooperate with the Internet of Things management platform, connect to the equipment at the end of the transmission line, provide real-time data interaction, issue inspection strategies, and control the open services of the Internet of Things in real time.

[0029] The real-time collection of state data of the actual power transmission line system and inputting the data into the virtual model of the power transmission line system to optimize the model includes:

[0030] By deploying sensors and monitoring equipment in the actual transmission line system, the status data of the actual transmission line system can be collected in real time;

[0031] inputting the state data into the transmission line system virtual model to update the internal state of the transmission line system virtual model;

[0032] The response data of the actual transmission line system is fed back to the transmission line system virtual model to adjust the parameters of the transmission line system virtual model.

[0033] The state data of the actual power transmission line system includes current, voltage, power and temperature.

[0034] The internal state of the transmission line system virtual model is updated so that the transmission line system virtual model can reflect the current state of the actual transmission line system, including the actual working conditions and environmental changes of the actual transmission line system.

[0035] A parallel control device for a power transmission line system facing digital twins, the device is applied to the above-mentioned method, the device comprising:

[0036] A transmission line system virtual model building module, which is used to build a transmission line system virtual model based on digital twin technology;

[0037] A transmission line system virtual model optimization module is used to collect the status data of the actual transmission line system in real time and input it into the transmission line system virtual model to optimize the model;

[0038] An intelligent control strategy formulation module is used to formulate an intelligent control strategy for the transmission line system using the DDPG algorithm based on the virtual model of the transmission line system and the actual transmission line system status data collected in real time;

[0039] The parallel control strategy formulation module is used to formulate parallel control strategies by considering the coordinated operation of multiple transmission lines.

[0040] A parallel control device for a power transmission line system for digital twins, comprising a memory and a processor;

[0041] The memory is used to store computer program code and transmit the computer program code to the processor;

[0042] The processor is used to execute the method as described above according to the instructions in the computer program code.

[0043] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention provides a parallel control method for a digital twin transmission line system. First, based on the digital twin technology, a high-fidelity transmission line system virtual model is constructed; second, a sensor network is deployed to collect key parameters of the transmission line in real time, and input into the transmission line system virtual model for real-time simulation of the line status; third, based on the transmission line system virtual model and real-time data, the DDPG algorithm is used to formulate an intelligent control strategy; finally, considering the collaborative work of multiple transmission lines, a parallel control strategy is formulated. The method proposed in the present invention can significantly improve the control efficiency and stability of the transmission line, and provide an important reference for building an intelligent digital transmission network. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of a parallel control method of a power transmission line system for digital twins proposed in the present invention.

[0047] Figure 2 It is a schematic diagram of a virtual model of a power transmission line system proposed in the present invention.

[0048] Figure 3 It is a structural block diagram of a parallel control device for a power transmission line system oriented to digital twins proposed in the present invention.

[0049] Figure 4 It is a structural block diagram of a parallel control device for a power transmission line system oriented to digital twins proposed in the present invention. DETAILED DESCRIPTION

[0050] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0051] See also Figure 1 , a parallel control method for a transmission line system for digital twins, comprising:

[0052] S1. Build a virtual model of the transmission line system based on digital twin technology.

[0053] See also Figure 2 ,Combined with the general architecture of digital transformation, the present invention provides a digital twin architecture for the transmission line system.,Based on the overall architecture of the power Internet of Things cloud, pipe, edge, and end and the characteristics of the transmission line system, the architecture is divided into five parts.,Therefore, the virtual model of the transmission line system includes the perception layer, edge computing layer, Internet of Things layer, digital twin layer, and interaction layer.

[0054] The perception layer is used to realize data collection and control of the end-layer transmission equipment; it mainly includes two types of equipment: transmission equipment and collection equipment. The collection equipment includes measurement and control equipment, video monitoring equipment, and environmental monitoring equipment.

[0055] The edge computing layer includes power smart terminals and aggregation gateways with edge computing capabilities. The power smart terminals are used to realize access management, data collection, protocol analysis, data storage, edge computing, and data forwarding to the cloud for various end devices of the transmission line; they are also used to connect to the transmission line end devices in conjunction with the Internet of Things management platform, provide real-time data interaction, inspection strategy issuance, and real-time control of Internet of Things open services.

[0056] The IoT layer is used to provide measurement capabilities of sensing devices and real-time control capabilities of end devices through the IoT management platform; the IoT management platform is an important component that connects the end and the cloud, and provides edge computing devices and power transmission equipment with secure and reliable registration access, data aggregation, data flow, control distribution, application management and other core services, playing a connecting role in cloud-edge communications.

[0057] The digital twin layer is used to iteratively update and optimize the virtual model of the transmission line system. The virtual model of the transmission line system constructed by the digital twin uses a hybrid modeling technology of "model-driven + data-driven", adopts a model-based system engineering modeling methodology, takes "data" as the main line, and combines AI technology to iteratively update and optimize the system model to achieve real virtual mapping.

[0058] The interaction layer is used to realize real-time interaction between users and models. The virtual model of the power transmission line system based on digital twins can realize real-time interaction between customers and models, and can also use voice, action and other technologies to establish connections between customers and smart devices. At the same time, it can also provide application interfaces for third-party customers to realize the sharing and use of data and functions.

[0059] S2. Real-time collection of status data of the actual transmission line system and input into the virtual model of the transmission line system to optimize the model, including:

[0060] By deploying sensors and monitoring equipment in the actual transmission line system, the status data of the actual transmission line system is collected in real time; the status data includes information related to the operating status of the transmission line equipment, such as current, voltage, power and temperature;

[0061] inputting the state data into the transmission line system virtual model to update the internal state of the transmission line system virtual model so that the transmission line system virtual model can reflect the current state of the actual transmission line system, including the actual working conditions and environmental changes of the actual transmission line system;

[0062] The response data of the actual transmission line system is fed back to the virtual model of the transmission line system to adjust the parameters of the virtual model of the transmission line system to improve the fit of the model to the actual system and ensure that the virtual model of the transmission line system is continuously optimized to adapt to changes in the actual system.

[0063] S3. Based on the virtual model of the transmission line system and the actual transmission line system status data collected in real time, the DDPG algorithm is used to formulate the intelligent control strategy of the transmission line system.

[0064] The DDPG algorithm includes a main network and a target network, wherein the main network includes a main action network and a main evaluation network, and the target network includes a target action network and a target evaluation network;

[0065] The optimization objective function of the main action network is:

[0066]

[0067] Where N n is the number of time periods to be considered; J tis the objective function with attenuation at time t; E(·) is the expected function; γ is the discount factor, 0<γ<1; r t+n is the return value at time t+n;

[0068] The main evaluation network training optimization goal is to minimize the loss function L, and the loss function L is:

[0069] L=E(q T，t -q t ) 2 ;

[0070] In the formula, q t is the output value of the main evaluation network at time t; q T，t The output value of the evaluation network calculated for the sample to be optimized at time t;

[0071] q T，t =r t +γq′ t+1 ;

[0072] In the formula, r t is the expected return at time t; q′ t+1 The output value of the sample target evaluation network at time t+1;

[0073] The DDPG optimization algorithm is used to obtain the deep neural network parameters of the optimal main action network. and the deep neural network parameters of the main evaluation network Use the following formula to update the target network parameters:

[0074]

[0075] Where η is the divergence factor, 0<η<1; and are the deep neural network parameters of the target action network and the target evaluation network at time t; and are the deep neural network parameters of the target action network and the target evaluation network at time t-1 respectively.

[0076] DDPG is a deep reinforcement learning algorithm for continuous action spaces. In the process of making decisions based on DDPG, by continuously conducting experiments in the environment, using techniques such as experience replay and target network to improve the stability and efficiency of training, the decision-making strategy of the agent is gradually optimized. The steps are as follows:

[0077] (1) Environmental modeling:

[0078] It includes state space (the state of the transmission line, such as current, voltage, etc.), action space (device control actions, such as line configuration changes), and reward function (a measure of system performance). This serves as the input of the DDPG algorithm.

[0079] (2)DDPG network structure:

[0080] Design Actor and Critic networks to learn strategies and value functions, respectively. These two networks are deep neural networks that use the structure of multi-layer perceptron (MLP) or convolutional neural network (CNN). The Actor network outputs an action, while the Critic network evaluates the value of this action.

[0081] (3) Experience replay buffer:

[0082] Implement an experience replay buffer to store experience tuples (state, action, reward, next state) during the interaction between the agent and the environment, improving sample efficiency and algorithm stability.

[0083] (4) DDPG algorithm parameters:

[0084] Set the hyperparameters of the DDPG algorithm, including learning rate, discount factor, soft update parameters (used to update the weights of the target network), exploration noise, etc.

[0085] (5) Training of Actor Network:

[0086] The actions output by the Actor network are compared with the actions in the actual environment, the Actor loss is calculated, and the gradient descent method is used to update the weights of the Actor network to improve the Agent's strategy.

[0087] (6) Training of Critic Network:

[0088] Calculate the loss between the value output by the Critic network and the actual reward, and use the gradient descent method to update the weight of the Critic network. The update of the Critic network helps to more accurately evaluate the Actor's strategy.

[0089] (7) Update of target network:

[0090] Using the soft update method, the weights of the target network are updated regularly to gradually approach the weights of the actual network to stabilize the training process.

[0091] (8) Exploration and Utilization:

[0092] By adding exploration noise or other methods, we can ensure that the agent continues to explore new action spaces during the learning process, rather than just using the currently known optimal policy.

[0093] (9) Training process:

[0094] Perform multiple iterations of training, and continuously update the weights of the Actor and Critic networks through the interaction between the Agent and the environment until the Agent can obtain a satisfactory strategy.

[0095] S4. Consider the coordinated operation of multiple transmission lines and formulate a parallel control strategy.

[0096] The present invention uses digital twin technology to simulate the status of transmission lines in real time and provide highly accurate line operation status; collects line parameters in real time through a sensor network to ensure that the virtual model of the transmission line system is synchronized with the actual line; combines the virtual model of the transmission line system and real-time data, and uses machine learning and optimization algorithms to make intelligent decisions; considers the collaborative work of multiple lines and formulates parallel control strategies to improve the overall efficiency of the power system; realizes remote monitoring functions so that operators can respond to changes in line status in a timely manner; continuously optimizes the line operation status, and adapts to the dynamic power system environment through a learning mechanism.

[0097] See also Figure 3 The present invention also provides a parallel control device for a power transmission line system oriented to digital twins, which is applied to the above-mentioned parallel control method for a power transmission line system oriented to digital twins, and the device comprises:

[0098] A transmission line system virtual model building module, which is used to build a transmission line system virtual model based on digital twin technology;

[0099] A transmission line system virtual model optimization module is used to collect the status data of the actual transmission line system in real time and input it into the transmission line system virtual model to optimize the model;

[0100] An intelligent control strategy formulation module is used to formulate an intelligent control strategy for the transmission line system using the DDPG algorithm based on the virtual model of the transmission line system and the actual transmission line system status data collected in real time;

[0101] The parallel control strategy formulation module is used to formulate parallel control strategies by considering the coordinated operation of multiple transmission lines.

[0102] See also Figure 4 ,The present invention also provides a parallel control device for a power transmission line system for digital twins, comprising a memory and a processor;

[0103] The memory is used to store computer program code and transmit the computer program code to the processor;

[0104] The processor is used to execute the above-mentioned parallel control method of a transmission line system for digital twins according to the instructions in the computer program code.

[0105] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned parallel control method for a digital twin-oriented power transmission line system.

[0106] Generally speaking, the computer instructions for implementing the method of the present invention may be carried in any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media may include any computer-readable media, except for the signal itself that is temporarily propagating.

[0107] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EKROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0108] Computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer or to an external computer (for example, using an Internet service provider to connect via the Internet) through any type of network, including a local area network (LAN) or a wide area network (WAN).

[0109] The above-mentioned devices and non-temporary computer-readable storage media can be found in the specific description of a parallel control method for a digital twin transmission line system and its beneficial effects, which will not be repeated here.

[0110] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A parallel control method for a power transmission line system for digital twins, characterized in that: include: Construct a virtual model of the transmission line system based on digital twin technology; Collect the status data of the actual transmission line system in real time and input it into the virtual model of the transmission line system to optimize the model; Based on the virtual model of the transmission line system and the actual transmission line system status data collected in real time, the DDPG algorithm is used to formulate the intelligent control strategy of the transmission line system; Considering the coordinated operation of multiple transmission lines, a parallel control strategy is formulated.

2. A parallel control method for a power transmission line system for digital twins according to claim 1, characterized in that: The DDPG algorithm includes a main network and a target network, the main network includes a main action network and a main evaluation network, and the target network includes a target action network and a target evaluation network; The optimization objective function of the main action network is: Where N n is the number of time periods to be considered; J t is the objective function with attenuation at time t; E(·) is the expected function; γ is the discount factor, 0<γ<1; r t+n is the return value at time t+n; The main evaluation network training optimization goal is to minimize the loss function L, and the loss function L is: L=E(q T，t -q t ) 2 ; In the formula, q t is the output value of the main evaluation network at time t; q T，t The output value of the evaluation network calculated for the sample to be optimized at time t; q T，t =r t +γq′ t+1 ; In the formula, r t is the expected return at time t; q′ t+1 The output value of the sample target evaluation network at time t+1; The DDPG optimization algorithm is used to obtain the deep neural network parameters of the optimal main action network. and the deep neural network parameters of the main evaluation network Use the following formula to update the target network parameters: Where η is the divergence factor, 0<η<1; and are the deep neural network parameters of the target action network and the target evaluation network at time t; and are the deep neural network parameters of the target action network and the target evaluation network at time t-1 respectively.

3. A parallel control method for a power transmission line system for digital twins according to claim 1, characterized in that: The transmission line system virtual model includes a perception layer, an edge computing layer, an Internet of Things layer, a digital twin layer and an interaction layer; The perception layer is used to realize data collection and control of the end-layer power transmission equipment; The edge computing layer includes power intelligent terminals and aggregation gateways with edge computing capabilities. The power intelligent terminals are used to implement access management, data collection, protocol analysis, data storage, edge computing, and data forwarding to the cloud for various terminal devices of the transmission line; The IoT layer is used to provide the measurement capability of the sensing device and the real-time control capability of the terminal device through the IoT management platform; The digital twin layer is used to iteratively update and optimize the virtual model of the transmission line system; The interaction layer is used to realize real-time interaction between users and models.

4. A parallel control method for a power transmission line system for digital twins according to claim 3, characterized in that: The edge computing layer is also used to cooperate with the Internet of Things management platform, connect to the equipment at the end of the transmission line, provide real-time data interaction, issue inspection strategies, and control the open services of the Internet of Things in real time.

5. The method for parallel control of a power transmission line system for digital twinning according to claim 1, characterized in that: The real-time collection of state data of the actual power transmission line system and inputting the data into the virtual model of the power transmission line system to optimize the model includes: By deploying sensors and monitoring equipment in the actual transmission line system, the status data of the actual transmission line system can be collected in real time; inputting the state data into the transmission line system virtual model to update the internal state of the transmission line system virtual model; The response data of the actual transmission line system is fed back to the transmission line system virtual model to adjust the parameters of the transmission line system virtual model.

6. A parallel control method for a power transmission line system for digital twins according to claim 5, characterized in that: The state data of the actual power transmission line system includes current, voltage, power and temperature.

7. A parallel control method for a power transmission line system for digital twins according to claim 5, characterized in that: The internal state of the transmission line system virtual model is updated so that the transmission line system virtual model can reflect the current state of the actual transmission line system, including the actual working conditions and environmental changes of the actual transmission line system.

8. A parallel control device for a power transmission line system for digital twins, characterized in that: The device is applied to the method described in any one of claims 1 to 7, and the device comprises: A transmission line system virtual model building module, which is used to build a transmission line system virtual model based on digital twin technology; A transmission line system virtual model optimization module is used to collect the status data of the actual transmission line system in real time and input it into the transmission line system virtual model to optimize the model; An intelligent control strategy formulation module is used to formulate an intelligent control strategy for the transmission line system using the DDPG algorithm based on the virtual model of the transmission line system and the actual transmission line system status data collected in real time; The parallel control strategy formulation module is used to formulate parallel control strategies by considering the coordinated operation of multiple transmission lines.

9. A parallel control device for a power transmission line system for digital twins, characterized in that: including memory and processor; The memory is used to store computer program code and transmit the computer program code to the processor; The processor is configured to execute the method according to any one of claims 1 to 7 according to instructions in the computer program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images