A new energy management platform based on digital twins

By deploying sensor network and wireless transmission technology in the new energy management system, combining multi-objective model and artificial intelligence algorithms, the problem of insufficient data acquisition and simulation accuracy of the intelligent energy management system is solved, and efficient energy system optimization and remote management are achieved .

CN118552348BActive Publication Date: 2024-11-19JIANGSU MINGYU VISUAL CREATIVE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411019376.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-19
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

The existing intelligent energy management system has problems such as difficulty in obtaining real-time data, low integration, insufficient simulation accuracy and poor flexibility, and it is difficult to effectively utilize new energy resources.

Method used

Adopt a new energy management platform based on digital twins to collect data in real time by deploying sensor networks at key nodes of the energy system, transmitting it to cloud storage and local storage using wireless transmission technology, and data modeling and prediction are carried out based on multi-objective models and artificial intelligence algorithms. Provide user interaction modules for custom configuration and optimization decisions.

Benefits of technology

It improves the reduction degree and computing efficiency of the operating state of the energy system, realizes accurate and intelligent decision-making in complex environments, provides intuitive and easy-to-use user interface and custom functions, and enhances the remote management capabilities of the energy system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118552348B_ABST
    Figure CN118552348B_ABST
Patent Text Reader

Abstract

The name of the present invention is a new energy management platform based on digital twins, which belongs to the field of new energy management systems. The present invention uses digital twins to highly restore the new energy system, optimizes the algorithm of the digital twin model, and improves the restoration of the actual energy system operation state through detailed physical property modeling. It innovatively adopts artificial intelligence algorithms to improve the computing efficiency under massive data, enabling the platform to make accurate intelligent decisions in complex operating environments. At the same time, an intuitive and easy-to-use user interface is designed through the user interaction module, providing user customization functions, so that users can easily achieve remote management of the energy system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of intelligent management, and specifically relates to a new energy management platform and management method based on digital twins. Background Art

[0002] With the rapid development of social economy and the continuous increase in energy demand, new energy has gradually attracted social attention. Solar energy, geothermal energy, wind energy, ocean energy, biomass energy and nuclear fusion energy all have great application potential. However, although they are rich in resources and environmentally friendly, new energy resources generally have problems such as low energy density, wide distribution, large supply fluctuations and high development costs. The stable utilization of new energy power generation has always been the focus of industry research.

[0003] The intelligent energy management system is a comprehensive information management system that integrates data collection, transmission, analysis, processing and display. With the increasing maturity and popularity of Internet of Things technology, energy management systems based on the Internet of Things have gradually attracted attention from academia and industry due to their real-time monitoring, data analysis and intelligent optimization. However, the current intelligent energy management system still has problems such as difficulty in obtaining real-time data, low integration, insufficient simulation accuracy and poor flexibility.

[0004] At present, the development and utilization of new energy still has an urgent need for a new energy intelligent management system with strong comprehensiveness and good adaptability. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in the above-mentioned prior art and provide a new energy management platform based on digital twins.

[0006] The present invention is achieved through the following technical solutions:

[0007] A new energy management platform based on digital twins, including:

[0008] Data collection module, deploying sensor networks at key nodes of the energy system, and the sensor networks collect various energy data in real time;

[0009] A data transmission and storage module, which uses wireless transmission technology to transmit the data collected by the sensor to the storage module, and the storage module includes cloud storage and local storage;

[0010] The digital twin module uses modeling technology to express the physical characteristics of the actual energy system based on the data provided by the data transmission and storage module. The module is implemented based on a multi-objective model, as follows:

[0011] Step (1), initialize the search agent matrix P is formula 1, where Represents a search agent, iThe value is a positive integer and represents a general iteration index,

[0012] Formula 1;

[0013] During the initialization phase, is initialized to Formula 2, where and Represent the lower and upper boundaries of the search agent, respectively.

[0014] Formula 2;

[0015] Step (2), generate random search agents , , , and ;

[0016] Step (3), calculate the search agent matching degree according to formula 3 ,

[0017] Formula 3,

[0018] in, and denote the proportional coefficient and adaptation function respectively;

[0019] Step (4), for , calculate the intensity value according to formula 4-6 ,in, represents the ideal location for the search agent,

[0020] Formula 4,

[0021] Formula 5,

[0022] Formula 6;

[0023] Step (5), Iterate to generate new positions ,

[0024] Formula 7;

[0025] in, and represents the proportionality coefficient, Indicates the best location for the search agent;

[0026] Step (6), execute the judgment step, if ,but , ;if ,but , ;

[0027] Step (7), return ;

[0028] A user interaction module provides visualization of the digital twin model and is configured with a custom module, wherein the custom module allows the user to input or modify target parameters;

[0029] The intelligent decision-making module compares real-time data with historical digital twin models, uses artificial intelligence algorithms to predict the future state of the energy system based on the current state, and automatically adjusts system parameters to optimize the operation strategy of the energy system.

[0030] Preferably, the sensor network includes but is not limited to charging pile sensors, photovoltaic sensors, ground lock sensors, temperature sensors, and pressure sensors to obtain various data of the energy system in real time.

[0031] Preferably, the energy data includes but is not limited to the voltage, current, power of the power system, and the temperature, humidity, and pressure of the environment.

[0032] Preferably, the artificial intelligence algorithm is an optimization algorithm based on a convolutional neural network (CNN) algorithm, specifically comprising:

[0033] Formula 8;

[0034] Formula 9;

[0035] Formula 10;

[0036] Formula 11;

[0037] in, Indicates the current moment, , , , , Represent the iteration parameters of this layer respectively, represents the S function, represents the weight, represents the input deviation, represents the output matrix of the CNN layer, Represents the output of the layer at the previous moment. Time jump connections are introduced into the optimization algorithm to improve the calculation effect. represents the hidden input in the time skip connection, and the output prediction value of the algorithm It is expressed as:

[0038] Formula 12;

[0039] time t The corresponding hidden data, The corresponding input expression is , , …, .

[0040] Preferably, the target parameters in the user interaction module include energy utilization, transmission loss or power.

[0041] At the same time, the present invention also provides a new energy management method based on digital twins, including:

[0042] Collect data, deploy sensor networks at key nodes of the energy system, and the sensor networks collect various energy data in real time;

[0043] Data transmission and storage, using wireless transmission technology to transmit the data collected by the sensor to a storage module, the storage module includes cloud storage and local storage;

[0044] Digital twin modeling, based on the data collected by the sensor network, uses modeling technology to express the physical characteristics of the actual energy system. The modeling technology is implemented based on a multi-objective model, as follows:

[0045] Step (1), initialize the search agent matrix P is formula 1, where Represents a search agent, i The value is a positive integer and represents a general iteration index,

[0046] Formula 1;

[0047] During the initialization phase, is initialized to Formula 2, where and Represent the lower and upper boundaries of the search agent, respectively.

[0048] Formula 2;

[0049] Step (2), generate random search agents , , , and ;

[0050] Step (3), calculate the search agent matching degree according to formula 3 ,

[0051] Formula 3,

[0052] in, and denote the proportional coefficient and adaptation function respectively;

[0053] Step (4), for , calculate the intensity value according to formula 4-6 ,in, represents the ideal location for the search agent,

[0054] Formula 4,

[0055] Formula 5,

[0056] Formula 6;

[0057] Step (5), Iterate to generate new positions ,

[0058] Formula 7;

[0059] in, and represents the proportionality coefficient, Indicates the best location for the search agent;

[0060] Step (6), execute the judgment step, if ,but , ;if ,but , ;

[0061] Step (7), return ;

[0062] Model visualization, visualizing the digital twin model;

[0063] System operation strategy optimization compares real-time data with historical digital twin models, uses artificial intelligence algorithms to predict the future state of the energy system based on the current state, and automatically adjusts system parameters to optimize the operation strategy of the energy system.

[0064] Preferably, the present invention can also input custom parameters through the user interaction module to set operating goals for the energy system or modify operating parameters.

[0065] Preferably, the artificial intelligence algorithm is an optimization algorithm based on a convolutional neural network (CNN) algorithm, specifically comprising:

[0066] Formula 8;

[0067] Formula 9;

[0068] Formula 10;

[0069] Formula 11;

[0070] in, Indicates the current moment, , , , , Represent the iteration parameters of this layer respectively, represents the S function, represents the weight, represents the input deviation, represents the output matrix of the CNN layer, Represents the output of the layer at the previous moment. Time jump connections are introduced into the optimization algorithm to improve the calculation effect. represents the hidden input in the time skip connection, and the output prediction value of the algorithm It is expressed as:

[0071] Formula 12;

[0072] time t The corresponding hidden data, The corresponding input expression is , , …, .

[0073] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention uses digital twins to highly restore the new energy system, optimizes the algorithm of the digital twin model, improves the restoration of the actual energy system operation state through detailed physical property modeling, innovatively adopts artificial intelligence algorithms, improves the computing efficiency under massive data, and enables the platform to make accurate intelligent decisions in a complex operating environment. At the same time, an intuitive and easy-to-use user interface is designed through the user interaction module, providing user customization functions, so that users can easily achieve remote management of the energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic structural diagram of the new energy management platform based on digital twins provided by the present invention.

[0075] Figure 2 Schematic diagram of the new energy management method based on digital twin provided by the present invention. DETAILED DESCRIPTION

[0076] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0077] Figure 1 : is a structural schematic diagram of a new energy management platform based on digital twins provided by the present invention. The new energy management platform based on digital twins includes a data acquisition module, a data transmission and storage module, a digital twin module, an intelligent decision-making module, and a user interaction module. Specifically,

[0078] The data acquisition module deploys a sensor network at key nodes of the energy system, and the sensor network collects various energy data in real time.

[0079] Based on the characteristics of the energy system and the different needs of users for the energy system, select appropriate sensor networks, including but not limited to charging pile sensors, photovoltaic sensors, ground lock sensors, temperature sensors, and pressure sensors to obtain various data of the energy system in real time.

[0080] The data transmission and storage module uses wireless transmission technology to transmit the data collected by the sensor to the storage module, and the storage module includes cloud storage and local storage.

[0081] The wireless transmission technology may adopt conventional wireless transmission protocols, including but not limited to WiFi, Bluetooth, etc. The content data is wirelessly transmitted to cloud storage, so that the management platform can remotely call the data.

[0082] The digital twin module uses modeling technology to express the physical characteristics of the actual energy system based on the data provided by the data transmission and storage module. The module is implemented based on a multi-objective model, as follows:

[0083] Step (1), initialize the search agent matrix P Formula 1, where Represents a search agent, i The value is a positive integer and represents a general iteration index,

[0084] Formula 1;

[0085] During the initialization phase, is initialized to Formula 2, where and Represent the lower and upper boundaries of the search agent, respectively.

[0086] Formula 2;

[0087] Step (2), generate random search agents , , , and ;

[0088] Step (3), calculate the search agent matching degree according to formula 3 ,

[0089] Formula 3,

[0090] in, and denote the proportional coefficient and adaptation function respectively;

[0091] Step (4), for , calculate the intensity value according to formula 4-6 ,in, represents the ideal location for the search agent,

[0092] Formula 4,

[0093] Formula 5,

[0094] Formula 6;

[0095] Step (5), Iterate to generate new positions ,

[0096] Formula 7;

[0097] in, and represents the proportionality coefficient, Indicates the best location for the search agent;

[0098] Step (6), execute the judgment step, if ,but , ;if ,but , ;

[0099] Step (7), return ;

[0100] A user interaction module provides visualization of the digital twin model and is configured with a custom module, wherein the custom module allows the user to input or modify target parameters;

[0101] The intelligent decision-making module compares real-time data with historical digital twin models, uses artificial intelligence algorithms to predict the future state of the energy system based on the current state, and automatically adjusts system parameters to optimize the operation strategy of the energy system.

[0102] For the multi-objective model adopted in the present invention, the energy data includes but is not limited to the voltage, current, power of the power system, and the temperature, humidity, and pressure of the environment.

[0103] The energy system generates massive amounts of data in real time. In order to improve data processing efficiency, the present invention optimizes the algorithm based on the convolutional neural network (CNN) algorithm, which specifically includes:

[0104] Formula 8;

[0105] Formula 9;

[0106] Formula 10;

[0107] Formula 11;

[0108] in, Indicates the current moment, , , , , Represent the iteration parameters of this layer respectively, represents the S function, represents the weight, represents the input deviation, represents the output matrix of the CNN layer, Represents the output of the layer at the previous moment. Time jump connections are introduced into the optimization algorithm to improve the calculation effect. represents the hidden input in the time skip connection, and the output prediction value of the algorithm It is expressed as:

[0109] Formula 12;

[0110] time t The corresponding hidden data, The corresponding input expression is , , …, .

[0111] In addition, the target parameters described in the user interaction module include energy utilization, transmission loss or power.

[0112] At the same time, the present invention also provides a new energy management method based on digital twins, including:

[0113] Collect data, deploy sensor networks at key nodes of the energy system, and the sensor networks collect various energy data in real time;

[0114] Data transmission and storage, using wireless transmission technology to transmit the data collected by the sensor to a storage module, the storage module includes cloud storage and local storage;

[0115] Digital twin modeling, based on the data collected by the sensor network, uses modeling technology to express the physical characteristics of the actual energy system. The modeling technology is based on a multi-objective model, as follows:

[0116] Step (1), initialize the search agent matrix P Formula 1, where Represents a search agent, i The value is a positive integer and represents a general iteration index,

[0117] Formula 1;

[0118] During the initialization phase, is initialized to Formula 2, where and Represent the lower and upper boundaries of the search agent, respectively.

[0119] Formula 2;

[0120] Step (2), generate random search agents , , , and ;

[0121] Step (3), calculate the search agent matching degree according to formula 3 ,

[0122] Formula 3,

[0123] in, and denote the proportional coefficient and adaptation function respectively;

[0124] Step (4), for , calculate the intensity value according to formula 4-6 ,in, represents the ideal location for the search agent,

[0125] Formula 4,

[0126] Formula 5,

[0127] Formula 6;

[0128] Step (5), Iterate to generate new positions ,

[0129] Formula 7;

[0130] in, and represents the proportionality coefficient, Indicates the best location for the search agent;

[0131] Step (6), execute the judgment step, if ,but , ;if ,but , ;

[0132] Step (7), return ;

[0133] Model visualization, visualizing the digital twin model;

[0134] System operation strategy optimization compares real-time data with historical digital twin models, uses artificial intelligence algorithms to predict the future state of the energy system based on the current state, and automatically adjusts system parameters to optimize the operation strategy of the energy system.

[0135] The present invention can also input custom parameters through the user interaction module to set operating goals for the energy system or modify operating parameters.

[0136] The artificial intelligence algorithm adopted in the present invention is an optimization algorithm based on the convolutional neural network (CNN) algorithm, which specifically includes:

[0137] Formula 8;

[0138] Formula 9;

[0139] Formula 10;

[0140] Formula 11;

[0141] in, Indicates the current moment, , , , , Represent the iteration parameters of this layer respectively, represents the S function, represents the weight, represents the input deviation, represents the output matrix of the CNN layer, Represents the output of the layer at the previous moment. Time jump connections are introduced into the optimization algorithm to improve the calculation effect. represents the hidden input in the time skip connection, and the output prediction value of the algorithm It is expressed as:

[0142] Formula 12;

[0143] time t The corresponding hidden data, The corresponding input expression is , , …, .

[0144] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention uses digital twins to highly restore the new energy system, optimizes the algorithm of the digital twin model, improves the restoration of the actual energy system operation state through detailed physical property modeling, innovatively adopts artificial intelligence algorithms, improves the computing efficiency under massive data, and enables the platform to make accurate intelligent decisions in a complex operating environment. At the same time, an intuitive and easy-to-use user interface is designed through the user interaction module, providing user customization functions, so that users can easily achieve remote management of the energy system.

[0145] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0146] In the description of the present invention, unless otherwise specified, the terms "upper", "lower", "left", "right", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the present invention.

[0147] Finally, it should be explained that the above technical solution is only one implementation method of the present invention. For those skilled in the art, it is easy to make various types of improvements or modifications based on the application methods and principles disclosed in the present invention, and it is not limited to the method described in the above specific implementation method of the present invention. Therefore, the method described above is only preferred and does not have a restrictive meaning.

Claims

1. A new energy management platform based on digital twins, comprising: Data collection module, deploying sensor networks at key nodes of the energy system, and the sensor networks collect various energy data in real time; A data transmission and storage module, which uses wireless transmission technology to transmit the data collected by the sensor to the storage module, and the storage module includes cloud storage and local storage; The digital twin module uses modeling technology to express the physical characteristics of the actual energy system based on the data provided by the data transmission and storage module. The module is implemented based on a multi-objective model, as follows: Step (1), initialize the search agent matrix P Formula 1, where Represents a search agent, i The value is a positive integer and represents a general iteration index, Formula 1; During the initialization phase, is initialized to Formula 2, where and Represent the lower and upper boundaries of the search agent, respectively. Formula 2; Step (2), generate random search agents , , , and ; Step (3), calculate the search agent matching degree according to formula 3 , Formula 3, in, and denote the proportional coefficient and adaptation function respectively; Step (4), for , calculate the intensity value according to formula 4-6 ,in, represents the ideal location for the search agent, Formula 4, Formula 5, Formula 6: Step (5), Iterate to generate new positions , Formula 7: in, and represents the proportionality coefficient, Indicates the best location for the search agent; Step (6), execute the judgment step, if ,but , ;if ,but , ; Step (7), return ; A user interaction module provides visualization of the digital twin model and is configured with a custom module, wherein the custom module allows the user to input or modify target parameters; The intelligent decision-making module compares real-time data with historical digital twin models, uses artificial intelligence algorithms to predict the future state of the energy system based on the current state, and automatically adjusts system parameters to optimize the operation strategy of the energy system; The artificial intelligence algorithm is an optimization algorithm based on the convolutional neural network (CNN) algorithm, specifically including: Formula 8: Formula 9: Formula 10: Formula 11: in, Indicates the current moment, , , , , Represent the iteration parameters of this layer respectively, represents the S function, represents the weight, represents the input deviation, represents the output matrix of the CNN layer, Represents the output of the layer at the previous moment. Time skip connection is introduced in this optimization algorithm to improve the calculation effect. represents the hidden input in the time skip connection, and the output prediction value of the algorithm It is expressed as: Formula 12: Indicates time t The corresponding hidden data, The corresponding input expression is , , …, .

2. The new energy management platform based on digital twin according to claim 1 is characterized in that: The sensor network includes but is not limited to charging pile sensors, photovoltaic sensors, ground lock sensors, temperature sensors, and pressure sensors to obtain various data of the energy system in real time.

3. The new energy management platform based on digital twin according to claim 2 is characterized in that: The energy data includes but is not limited to the voltage, current, power of the power system, and the temperature, humidity, and pressure of the environment.

4. The new energy management platform based on digital twin according to claim 1 is characterized in that: The target parameters described in the user interaction module include energy utilization, transmission loss or power.

5. A new energy management method based on digital twins, comprising: Collect data, deploy sensor networks at key nodes of the energy system, and the sensor networks collect various energy data in real time; Data transmission and storage, using wireless transmission technology to transmit the data collected by the sensor to a storage module, the storage module includes cloud storage and local storage; Digital twin modeling, based on the data collected by the sensor network, uses modeling technology to express the physical characteristics of the actual energy system. The modeling technology is based on a multi-objective model, as follows: Step (1), initialize the search agent matrix P Formula 1, where Represents a search agent, i The value is a positive integer and represents a general iteration index, Formula 1; During the initialization phase, is initialized to Formula 2, where and Represent the lower and upper boundaries of the search agent, respectively. Formula 2; Step (2), generate random search agents , , , and ; Step (3), calculate the search agent matching degree according to formula 3 , Formula 3, in, and denote the proportional coefficient and adaptation function respectively; Step (4), for , calculate the intensity value according to formula 4-6 ,in, represents the ideal location for the search agent, Formula 4, Formula 5, Formula 6: Step (5), Iterate to generate new positions , Formula 7: in, and represents the proportionality coefficient, Indicates the best location for the search agent; Step (6), execute the judgment step, if ,but , ;if ,but , ; Step (7), return ; Model visualization, visualizing the digital twin model; System operation strategy optimization, comparing real-time data with historical digital twin models, using artificial intelligence algorithms to predict the future state of the energy system based on the current state, and automatically adjusting system parameters to optimize the operation strategy of the energy system; The artificial intelligence algorithm is an optimization algorithm based on the convolutional neural network (CNN) algorithm, specifically including: Formula 8: Formula 9: Formula 10: Formula 11: in, Indicates the current moment, , , , , Represent the iteration parameters of this layer respectively, represents the S function, represents the weight, represents the input deviation, represents the output matrix of the CNN layer, Represents the output of the layer at the previous moment. Time skip connection is introduced in this optimization algorithm to improve the calculation effect. represents the hidden input in the time skip connection, and the output prediction value of the algorithm It is expressed as: Formula 12: Indicates time t The corresponding hidden data, The corresponding input expression is , , …, .

6. The new energy management method based on digital twin according to claim 5 is characterized in that: Enter custom parameters through the user interaction module to set operating goals for the energy system or modify operating parameters.

7. The new energy management method based on digital twin according to claim 5 is characterized in that: The sensor network includes but is not limited to charging pile sensors, photovoltaic sensors, ground lock sensors, temperature sensors, and pressure sensors to obtain various data of the energy system in real time.

8. The new energy management method based on digital twin according to claim 5 is characterized in that: The energy data includes but is not limited to the voltage, current, power of the power system, and the temperature, humidity, and pressure of the environment.