Integrated energy system multi-energy cooperative operation method based on Internet of Things
By deploying IoT technology and digital twin models in an integrated energy system, and using Nash equilibrium theory to adjust energy management strategies in real time, the problems of uneven allocation of energy resources and untimely failure response are solved, and efficient energy management and collaborative optimization operation are achieved .
Patent Information
- Application Number
- CN202411007869.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing multi-energy collaborative operation method of integrated energy systems is difficult to achieve real-time collaborative energy management, resulting in uneven distribution of energy resources, low system operation efficiency and untimely failure response, especially in different weather conditions, the degree of mutual influence between various energy systems When different and the fault is unpredictable.
Adopt the multi-energy collaborative operation method of integrated energy systems based on the Internet of Things. By installing sensors in energy facilities, collecting data in real time and transmitting it to edge computing devices, developing digital twin models, building energy management slave systems and main systems, and using Nash equilibrium theory Real-time monitoring and dynamic adjustment of energy management strategies.
Real-time data collection, transmission and analysis of various energy systems is realized, accurate operating status monitoring and efficient energy efficiency management are provided, and problems of uneven allocation of energy resources, inefficient system efficiency and untimely failure response are solved, and multi-energy systems are realized. collaborative optimization operation.
Smart Images

Figure CN118966824A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of integrated energy systems, and in particular to a multi-energy coordinated operation method of an integrated energy system based on the Internet of Things. Background Art
[0002] The multi-energy coordinated operation method of the integrated energy system aims to improve the overall efficiency and stability of the energy system. By deploying Internet of Things technology and developing digital twin models of various energy systems, it optimizes the real-time monitoring and dynamic adjustment of energy resources and realizes the coordinated and optimized operation of multiple energy sources.
[0003] The existing multi-energy collaborative operation methods of integrated energy systems are usually difficult to achieve real-time energy collaborative management. In addition, due to the different degrees of mutual influence between energy systems under different weather conditions and the unpredictability of integrated energy failures, it will lead to uneven distribution of energy resources, low system operation efficiency, and untimely fault response. In summary, a multi-energy collaborative operation method for an integrated energy system based on the Internet of Things is provided. Summary of the invention
[0004] The purpose of the present invention is to provide a multi-energy collaborative operation method for an integrated energy system based on the Internet of Things, so as to solve the problems raised in the above background technology that the different degrees of mutual influence between energy systems under different weather conditions and the unpredictability of the occurrence of integrated energy failures will lead to uneven distribution of energy resources, low system operation efficiency and untimely fault response.
[0005] To achieve the above object, the present invention aims to provide a multi-energy coordinated operation method of an integrated energy system based on the Internet of Things, comprising the following steps:
[0006] S1. Install sensors in energy facilities, deploy IoT technology, collect sensor energy data in real time, and transmit the sensor energy data to edge computing devices;
[0007] S2. Develop digital twin models of various energy systems based on sensor energy data, and build physical models, data models, and behavioral models;
[0008] S3. On the digital twin model, build an energy management slave system for each energy system;
[0009] S4. Build the main energy management system, and monitor and dynamically adjust the energy management slave system operation strategy in real time based on the Nash equilibrium theory.
[0010] As a further improvement of the technical solution, in S1, the method for deploying the Internet of Things technology is as follows:
[0011] S1.1. Install sensors on electricity, coal, oil and natural gas energy facilities;
[0012] S1.2. Install IoT gateway devices in energy facilities and configure the connection between IoT devices and gateways;
[0013] S1.3. Install edge computing devices in energy facilities and connect the edge computing devices with sensors and IoT gateways;
[0014] S1.4, using LoRaWAN and NB-IoT communication protocols to transmit sensor energy data to edge computing devices;
[0015] S1.5, filter out noise and outliers from sensor energy data on edge computing devices, and aggregate data from different sensors;
[0016] S1.6. Transmit the processed sensor energy data to the energy management slave system on each digital twin model.
[0017] As a further improvement of the technical solution, in S2, the energy system digital twin model simulates and reflects the equipment, system, status and operation status in the actual energy, and is used for real-time centralized monitoring of the operation status of each energy source;
[0018] The specific methods for developing digital twin models of various energy systems are as follows:
[0019] S2.1, receiving energy data from sensors on edge computing devices and collecting historical operation data of the energy system;
[0020] S2.2. Identify the physical components in each electricity, coal, oil and natural gas energy system, and establish mathematical models for the physical components based on the laws of physics, including physical models of electricity systems, coal systems, oil systems and natural gas systems.
[0021] S2.3. Extract key features from sensor energy data, build a data-driven model using machine learning techniques, train the data-driven model using historical data, and evaluate the performance of the data-driven model through cross-validation;
[0022] S2.4. Define the operating logic of electricity, coal, oil and natural gas energy systems under normal operating conditions, define the operating logic and emergency response of the system in the event of a fault, and set the control strategy for each energy subsystem.
[0023] As a further improvement of the technical solution, in S2.3, the specific method for establishing the training data driven model is as follows:
[0024] S2.3.1. Fill missing values in sensor energy data by interpolation and averaging methods, and use statistical methods to identify and process outliers in sensor energy data;
[0025] S2.3.2. Use the time series analysis model to build a data-driven model, use historical operation data as the training set, input the feature matrix and labels into the model, and use the gradient descent optimization algorithm to adjust the model parameters;
[0026] S2.3.3. Divide the sensor energy data into K subsets, use K-1 subsets for training in turn, and use the remaining subset for verification, repeat K times, calculate the average evaluation index, and evaluate the performance and stability of the model.
[0027] As a further improvement of the technical solution, in S3, the energy management slave system is a single management system designed for electricity, coal, oil and natural gas energy. The energy management slave system is based on the digital twin model and the Internet of Things technology to monitor the operation status of electricity, coal, oil and natural gas energy in real time, monitor the operation failures and abnormal conditions of electricity, coal, oil and natural gas energy, and visualize the operation status in real time;
[0028] The specific methods for building an energy management system are as follows:
[0029] S3.1. Use a layered architecture to design the overall architecture of the energy management system, including data collection layer, data processing layer, business logic layer and user interface layer;
[0030] S3.2. Develop a data acquisition module and write code to collect sensor energy data from edge computing devices;
[0031] S3.3, develop data storage module and design database structure to store collected sensor energy data using NoSQL database;
[0032] S3.4. Design and develop a real-time monitoring interface to display the real-time status of electricity, coal, oil and natural gas energy operations, and set alarm thresholds for electricity, coal, oil and natural gas energy operations;
[0033] S3.5. Design interface layout and use dashboards, charts, and data tables to visualize data.
[0034] As a further improvement of the technical solution, in S4, the energy management master system is used to monitor the data and alarm information of all energy management slave systems in real time, optimize the strategies of the energy management slave systems, and quickly simulate and adjust the operation strategy operations on the digital twin model to find a balanced energy system operation strategy;
[0035] The specific method of building the main energy management system is as follows:
[0036] S4.1.1. Use a layered architecture to build data collection modules, decision support modules, and user interface modules;
[0037] S4.1.2. Collect operation data and alarm information from each energy management system in real time and store them in the NoSQL database;
[0038] S4.1.3. Integrate the strategy simulation optimization algorithm based on Nash equilibrium theory, use the strategy simulation optimization algorithm to simulate and optimize the energy management slave system with alarms in the digital twin model, and find a balanced operation strategy;
[0039] S4.1.4. Design and develop user interfaces to visualize the simulation results and strategy adjustment recommendations of the main energy management system using charts, dashboards, and tables.
[0040] As a further improvement of the technical solution, the energy management main system finds a balanced energy system operation strategy method as follows:
[0041] S4.2.1. Detect the alarm information of each energy management slave system and record the alarm time, type, parameter value and threshold;
[0042] S4.2.2. Define the participants as the electric energy management slave system P1, the coal energy management slave system P2, the oil energy management slave system P3 and the natural gas energy management slave system P4;
[0043] S4.2.3. Define a set of strategies for each energy management slave system: adjust the parameters of production, conversion, storage and use:
[0044] in, represents the strategy set of the i-th energy management slave system; s in represents the jth strategy of the i-th energy management slave system;
[0045] S4.2.4, introduce the influencing factors of temperature T and humidity H, and define the utility function of the power system, the utility function of the coal system, the utility function of the oil system and the utility function of the natural gas system;
[0046] S4.2.5. Set power balance constraints, production capacity constraints and storage capacity constraints, and construct the objective function;
[0047] S4.2.6. Optimize the objective function using a strategy simulation optimization algorithm based on Nash equilibrium theory;
[0048] S4.2.7. When the Nash equilibrium is reached, the simulation results and optimization suggestions are displayed on the energy management master system. After authorization by the staff, the operation strategies of each energy management slave system are dynamically adjusted.
[0049] As a further improvement of this technical solution, in S4.2.4, the temperature T and humidity H influencing factors are introduced to define the power system utility function U P1 、Coal system utility function U P2 、Oil system utility function U P3 The utility function method of the natural gas system is as follows:
[0050] Power system utility function U P1 :
[0051] U P1 =α ele ·R ele (s P1 )―β ele ·C ele (s P1 ,T,H)―γ ele ·L ele (s P1 );
[0052] Coal system utility function U P2 :
[0053] U P2 =α coal ·R coal (s P2 )―β coal ·C coal (s P2 ,T,H)―γ coal ·L coal (s P2 );
[0054] Oil system utility function U P3 :
[0055] U P3 =α oil ·R oil (s P3 )―β oil ·C oil (s P3 ,T,H)―γ oil ·L oil (s P3 );
[0056] Natural gas system utility function:
[0057] U P4 =α gas ·R gas (s P4 )―β gas ·C gas (s P4 ,T,H)―γgas ·L gas (s P4 );
[0058] Among them, R ele represents the electricity revenue function; C ele represents the electricity cost function; L ele represents the power loss function; α ele , β ele , γ ele is the power weight coefficient; R coal represents the coal revenue function; C coal represents the coal cost function; L coal represents the coal loss function; α ele , β coal , γ coal is the coal weight coefficient; R oil represents the oil revenue function; C oil represents the oil cost function; L oil represents the oil loss function; α oil , β oil , γ oil is the oil weight coefficient; R gas represents the natural gas revenue function; C gas represents the natural gas cost function; L gas represents the natural gas loss function; α gas , β gas , γ gas is the weight coefficient; T is the temperature; H is the humidity.
[0059] As a further improvement of the technical solution, in S4.2.5, the power balance constraint, production capacity constraint and storage capacity constraint are set, and the objective function method is constructed as follows:
[0060] Power balance constraints:
[0061]
[0062] in, is the total power output of all energy systems; P i (s i ) is the power output of the i-th energy system, depending on its strategy s i ;D total (t) is the total electricity demand, which changes with time t;
[0063] Production capacity constraints:
[0064]
[0065] Among them, P i (si ) is the power output of the i-th energy system; P i,max is the maximum production capacity of the i-th energy system;
[0066] Storage capacity constraints:
[0067]
[0068] Among them, S i (s i ) is the storage capacity of the i-th energy system, depending on its strategy s i ; S i,max is the maximum storage capacity of the i-th energy system;
[0069] Objective function;
[0070]
[0071] in, To express finding the combination that maximizes the objective function among all strategy combinations s, s = (s P1 ,s P2 ,s P3 ,s P4 );s ―P1 is the strategy combination of the other three systems except the power system; ―P2 is the strategy combination of the other three systems except the coal system; ―P3 is the strategy combination of the other three systems except the oil system; ―P4 It is the strategy combination of the other three systems except the natural gas system.
[0072] As a further improvement of the technical solution, in S4.2.6, the method for optimizing the objective function using the strategy simulation optimization algorithm based on Nash equilibrium theory is as follows:
[0073] Set the initial strategy:
[0074]
[0075] in, is the initial strategy of the ith energy system; To represent all possible strategies s i Find the utility function U i Maximizing strategies; is the initial strategy of all energy systems except the i-th energy system;
[0076] Set the iterative update strategy:
[0077]
[0078] in, is the strategy of the ith participant in the k+1th iteration; k is the number of iterations;
[0079] Termination condition: When the strategies of all participants no longer change, Nash equilibrium is reached:
[0080]
[0081] in, means that the strategy of the i-th participant in the k+1th iteration is the same as that in the kth iteration; This holds true for all energy systems.
[0082] Compared with the prior art, the present invention has the following beneficial effects:
[0083] 1. In this multi-energy collaborative operation method of an integrated energy system based on the Internet of Things, by deploying Internet of Things technology and developing digital twin models of various energy systems, real-time data collection, transmission and analysis of various energy systems can be achieved, providing accurate operation status monitoring and efficient energy efficiency management.
[0084] 2. In this multi-energy collaborative operation method of an integrated energy system based on the Internet of Things, an energy management slave system and an energy management master system are built, and according to the Nash equilibrium theory, the energy management slave system operation strategy is monitored in real time and dynamically adjusted, which can realize the collaborative optimization operation of multiple energy systems and solve the problems of uneven distribution of energy resources, low system efficiency and untimely fault response. BRIEF DESCRIPTION OF THE DRAWINGS
[0085] Figure 1 The figure is a flow chart of the overall method of the present invention. DETAILED DESCRIPTION
[0086] 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.
[0087] Example:
[0088] See also Figure 1 As shown, this embodiment provides a multi-energy coordinated operation method of an integrated energy system based on the Internet of Things, comprising the following steps:
[0089] S1. Install sensors in energy facilities, deploy IoT technology, collect sensor energy data in real time, and transmit the sensor energy data to edge computing devices;
[0090] The methods for deploying IoT technologies are as follows:
[0091] S1.1. Install sensors on electricity, coal, oil and natural gas energy facilities;
[0092] S1.2. Install IoT gateway devices in energy facilities and configure the connection between IoT devices and gateways;
[0093] S1.3. Install edge computing devices in energy facilities and connect the edge computing devices with sensors and IoT gateways;
[0094] S1.4, using LoRaWAN and NB-IoT communication protocols to transmit sensor energy data to edge computing devices;
[0095] S1.5, filter out noise and outliers from sensor energy data on edge computing devices, and aggregate data from different sensors;
[0096] S1.6. Transmit the processed sensor energy data to the energy management slave system on each digital twin model.
[0097] S2. Develop digital twin models of various energy systems based on sensor energy data, and build physical models, data models, and behavioral models;
[0098] The digital twin model of the energy system simulates the equipment, system, status and operation status of the actual energy, and is used to centrally monitor the operation status of each energy source in real time;
[0099] The specific methods for developing digital twin models of various energy systems are as follows:
[0100] S2.1, receiving energy data from sensors on edge computing devices and collecting historical operation data of the energy system;
[0101] S2.2. Identify the physical components in each electricity, coal, oil and natural gas energy system, and establish mathematical models for the physical components based on the laws of physics, including physical models of electricity systems, coal systems, oil systems and natural gas systems.
[0102] S2.3. Extract key features from sensor energy data, build a data-driven model using machine learning techniques, train the data-driven model using historical data, and evaluate the performance of the data-driven model through cross-validation;
[0103] S2.4. Define the operating logic of electricity, coal, oil and natural gas energy systems under normal operating conditions, define the operating logic and emergency response of the system in the event of a fault, and set the control strategy for each energy subsystem.
[0104] The specific method of establishing a training data-driven model is as follows:
[0105] S2.3.1. Fill missing values in sensor energy data by interpolation and averaging methods, and use statistical methods to identify and process outliers in sensor energy data;
[0106] S2.3.2. Use the time series analysis model to build a data-driven model, use historical operation data as the training set, input the feature matrix and labels into the model, and use the gradient descent optimization algorithm to adjust the model parameters;
[0107] S2.3.3. Divide the sensor energy data into K subsets, use K-1 subsets for training in turn, and use the remaining subset for verification, repeat K times, calculate the average evaluation index, and evaluate the performance and stability of the model.
[0108] S3. On the digital twin model, build an energy management slave system for each energy system;
[0109] The energy management slave system is a single management system designed for electricity, coal, oil and natural gas energy. Based on the digital twin model and Internet of Things technology, the energy management slave system monitors the operating status of electricity, coal, oil and natural gas energy in real time, monitors the operating failures and abnormal conditions of electricity, coal, oil and natural gas energy, and displays the operating status in real time;
[0110] The specific methods for building an energy management system are as follows:
[0111] S3.1. Use a layered architecture to design the overall architecture of the energy management system, including data collection layer, data processing layer, business logic layer and user interface layer;
[0112] S3.2. Develop a data acquisition module and write code to collect sensor energy data from edge computing devices;
[0113] S3.3, develop data storage module and design database structure to store collected sensor energy data using NoSQL database;
[0114] S3.4. Design and develop a real-time monitoring interface to display the real-time status of electricity, coal, oil and natural gas energy operations, and set alarm thresholds for electricity, coal, oil and natural gas energy operations;
[0115] S3.5. Design interface layout and use dashboards, charts, and data tables to visualize data.
[0116] S4. Build the main energy management system, monitor in real time and dynamically adjust the operation strategy of the energy management slave system according to the Nash equilibrium theory;
[0117] The energy management master system is used to monitor the data and alarm information of all energy management slave systems in real time, optimize the strategies of energy management slave systems, and quickly simulate and adjust the operation strategies on the digital twin model to find a balanced energy system operation strategy.
[0118] The specific method of building the main energy management system is as follows:
[0119] S4.1.1. Use a layered architecture to build data collection modules, decision support modules, and user interface modules;
[0120] S4.1.2. Collect operation data and alarm information from each energy management system in real time and store them in the NoSQL database;
[0121] S4.1.3. Integrate the strategy simulation optimization algorithm based on Nash equilibrium theory, use the strategy simulation optimization algorithm to simulate and optimize the energy management slave system with alarms in the digital twin model, and find a balanced operation strategy;
[0122] S4.1.4. Design and develop user interfaces to visualize the simulation results and strategy adjustment recommendations of the main energy management system using charts, dashboards, and tables.
[0123] The energy management main system finds a balanced energy system operation strategy method as follows:
[0124] S4.2.1. Detect the alarm information of each energy management slave system and record the alarm time, type, parameter value and threshold;
[0125] S4.2.2. Define the participants as the electric energy management slave system P1, the coal energy management slave system P2, the oil energy management slave system P3 and the natural gas energy management slave system P4;
[0126] S4.2.3. Define a set of strategies for each energy management slave system: adjust the parameters of production, conversion, storage and use:
[0127] in, represents the strategy set of the i-th energy management slave system; s in represents the jth strategy of the i-th energy management slave system;
[0128] S4.2.4, introduce the influencing factors of temperature T and humidity H, and define the utility function of the power system, the utility function of the coal system, the utility function of the oil system and the utility function of the natural gas system;
[0129] S4.2.5. Set power balance constraints, production capacity constraints and storage capacity constraints, and construct the objective function;
[0130] S4.2.6. Optimize the objective function using a strategy simulation optimization algorithm based on Nash equilibrium theory;
[0131] S4.2.7. When the Nash equilibrium is reached, the simulation results and optimization suggestions are displayed on the energy management master system. After authorization by the staff, the operation strategies of each energy management slave system are dynamically adjusted.
[0132] Introducing the influencing factors of temperature T and humidity H, defining the utility function U of the power system P1 、Coal system utility function U P2 、Oil system utility function U P3 The utility function method of the natural gas system is as follows:
[0133] Power system utility function U P1 :
[0134] U P1 =α ele ·R ele (s P1 )―β ele ·C ele (s P1 ,T,H)―γ ele ·L ele (s P1 );
[0135] Coal system utility function U P2 :
[0136] U P2 =α coal ·R coal (s P2 )―β coal ·C coal (s P2 ,T,H)―γ coal ·L coal (s P2 );
[0137] Oil system utility function U P3 :
[0138] U P3 =α oil ·R oil (s P3 )―β oil ·C oil (s P3 ,T,H)―γ oil ·L oil (s P3 );
[0139] Natural gas system utility function:
[0140] U P4 =α gas ·R gas (s P4 )―β gas ·C gas (S P4 ,T,H)―γ gas ·L gas (s P4 );
[0141] Among them, R ele represents the electricity revenue function; C ele represents the electricity cost function; L ele represents the power loss function; α ele , β ele , γ ele is the power weight coefficient; R coal represents the coal revenue function; C coal represents the coal cost function; L coal represents the coal loss function; α ele , β coal , γ coal is the coal weight coefficient; R oil represents the oil revenue function; C oil represents the oil cost function; L oil represents the oil loss function; α oil , β oil , γ oil is the oil weight coefficient; R gas represents the natural gas revenue function; C gas represents the natural gas cost function; L gas represents the natural gas loss function; α gas , β gas , γ gas is the weight coefficient; T is the temperature; H is the humidity.
[0142] The power balance constraint, production capacity constraint and storage capacity constraint are set, and the objective function is constructed as follows:
[0143] Power balance constraints:
[0144]
[0145] in, is the total power output of all energy systems; P i (s i ) is the power output of the i-th energy system, depending on its strategy s i ;D total (t) is the total electricity demand, which changes with time t;
[0146] Production capacity constraints:
[0147]
[0148] Among them, P i (s i ) is the power output of the i-th energy system; P i,max is the maximum production capacity of the i-th energy system;
[0149] Storage capacity constraints:
[0150]
[0151] Among them, S i (s i ) is the storage capacity of the i-th energy system, depending on its strategy s i ; S i,max is the maximum storage capacity of the i-th energy system;
[0152] Objective function;
[0153]
[0154] in, To express finding the combination that maximizes the objective function among all strategy combinations s, s = (s P1 ,s P2 ,s P3 ,s P4 );s ―P1 is the strategy combination of the other three systems except the power system; ―P2 is the strategy combination of the other three systems except the coal system; ―P3 is the strategy combination of the other three systems except the oil system; ―P4 It is the strategy combination of the other three systems except the natural gas system.
[0155] The method of optimizing the objective function using the strategy simulation optimization algorithm based on Nash equilibrium theory is as follows:
[0156] Set the initial strategy:
[0157]
[0158] in, is the initial strategy of the ith energy system; To represent all possible strategies s i Find the utility function U i Maximizing strategies; is the initial strategy of all energy systems except the i-th energy system;
[0159] Set the iterative update strategy:
[0160]
[0161] in, is the strategy of the ith participant in the k+1th iteration; k is the number of iterations;
[0162] Termination condition: When the strategies of all participants no longer change, Nash equilibrium is reached:
[0163]
[0164] in, means that the strategy of the i-th participant in the k+1th iteration is the same as that in the kth iteration; This holds true for all energy systems.
[0165] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A multi-energy coordinated operation method of an integrated energy system based on the Internet of Things, characterized in that: The following steps are involved: S1. Install sensors in energy facilities, deploy IoT technology, collect sensor energy data in real time, and transmit the sensor energy data to edge computing devices; S2. Develop digital twin models of various energy systems based on sensor energy data, and build physical models, data models, and behavioral models; S3. On the digital twin model, build an energy management slave system for each energy system; S4. Build the main energy management system, and monitor and dynamically adjust the energy management slave system operation strategy in real time based on the Nash equilibrium theory.
2. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 1 is characterized in that: In S1, the method for deploying the Internet of Things technology is as follows: S1.
1. Install sensors on electricity, coal, oil and natural gas energy facilities; S1.
2. Install IoT gateway devices in energy facilities and configure the connection between IoT devices and gateways; S1.
3. Install edge computing devices in energy facilities and connect the edge computing devices with sensors and IoT gateways; S1.4, using LoRaWAN and NB-IoT communication protocols to transmit sensor energy data to edge computing devices; S1.5, filter out noise and outliers from sensor energy data on edge computing devices, and aggregate data from different sensors; S1.
6. Transmit the processed sensor energy data to the energy management slave system on each digital twin model.
3. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 1 is characterized in that: In S2, the energy system digital twin model simulates and reflects the equipment, system, status and operation status in the actual energy, and is used to centrally monitor the operation status of each energy source in real time; The specific methods for developing digital twin models of various energy systems are as follows: S2.1, receiving energy data from sensors on edge computing devices and collecting historical operation data of the energy system; S2.
2. Identify the physical components in each electricity, coal, oil and natural gas energy system, and establish mathematical models for the physical components based on the laws of physics, including physical models of the electricity system, coal system, oil system and natural gas system; S2.
3. Extract key features from sensor energy data, build a data-driven model using machine learning techniques, train the data-driven model using historical data, and evaluate the performance of the data-driven model through cross-validation; S2.
4. Define the operating logic of electricity, coal, oil and natural gas energy systems under normal operating conditions, define the operating logic and emergency response of the system in the event of a fault, and set the control strategy for each energy subsystem.
4. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 3 is characterized by: In S2.3, the specific method for establishing a training data driven model is as follows: S2.3.
1. Fill missing values in sensor energy data by interpolation and averaging methods, and use statistical methods to identify and process outliers in sensor energy data; S2.3.
2. Use the time series analysis model to build a data-driven model, use historical operation data as the training set, input the feature matrix and labels into the model, and use the gradient descent optimization algorithm to adjust the model parameters; S2.3.
3. Divide the sensor energy data into K subsets, use K-1 subsets for training in turn, and use the remaining subset for verification, repeat K times, calculate the average evaluation index, and evaluate the performance and stability of the model.
5. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 1 is characterized in that: In S3, the energy management slave system is a single management system designed for electricity, coal, oil and natural gas energy. The energy management slave system is based on the digital twin model and the Internet of Things technology to monitor the operation status of electricity, coal, oil and natural gas energy in real time, monitor the operation failures and abnormal conditions of electricity, coal, oil and natural gas energy, and visualize the operation status in real time; The specific methods for building an energy management system are as follows: S3.
1. Use a layered architecture to design the overall architecture of the energy management system, including data collection layer, data processing layer, business logic layer and user interface layer; S3.
2. Develop a data acquisition module and write code to collect sensor energy data from edge computing devices; S3.3, develop data storage module and design database structure to store collected sensor energy data using NoSQL database; S3.
4. Design and develop a real-time monitoring interface to display the real-time status of electricity, coal, oil and natural gas energy operations, and set alarm thresholds for electricity, coal, oil and natural gas energy operations; S3.
5. Design interface layout and use dashboards, charts, and data tables to visualize data.
6. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 1 is characterized by: In S4, the energy management master system is used to monitor the data and alarm information of all energy management slave systems in real time, optimize the strategies of the energy management slave systems, and quickly simulate and adjust the operation strategies on the digital twin model to find a balanced energy system operation strategy; The specific method of building the main energy management system is as follows: S4.1.
1. Use a layered architecture to build data collection modules, decision support modules, and user interface modules; S4.1.
2. Collect operation data and alarm information from each energy management system in real time and store them in the NoSQL database; S4.1.
3. Integrate the strategy simulation optimization algorithm based on Nash equilibrium theory, use the strategy simulation optimization algorithm to simulate and optimize the energy management slave system with alarms in the digital twin model, and find a balanced operation strategy; S4.1.
4. Design and develop user interfaces to visualize the simulation results and strategy adjustment recommendations of the main energy management system using charts, dashboards, and tables.
7. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 6 is characterized by: The energy management main system finds a balanced energy system operation strategy method as follows: S4.2.
1. Detect the alarm information of each energy management slave system and record the alarm time, type, parameter value and threshold; S4.2.
2. Define the participants as the electric energy management slave system P1, the coal energy management slave system P2, the oil energy management slave system P3 and the natural gas energy management slave system P4; S4.2.
3. Define a set of strategies for each energy management slave system: adjust the parameters of production, conversion, storage and use: in, represents the strategy set of the i-th energy management slave system; s in represents the jth strategy of the i-th energy management slave system; S4.2.4, introduce the influencing factors of temperature T and humidity H, and define the utility function of the power system, the utility function of the coal system, the utility function of the oil system and the utility function of the natural gas system; S4.2.
5. Set power balance constraints, production capacity constraints and storage capacity constraints, and construct the objective function; S4.2.
6. Optimize the objective function using a strategy simulation optimization algorithm based on Nash equilibrium theory; S4.2.
7. When the Nash equilibrium is reached, the simulation results and optimization suggestions are displayed on the energy management master system. After authorization by the staff, the operation strategies of each energy management slave system are dynamically adjusted.
8. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 7 is characterized in that: In S4.2.4, the temperature T and humidity H influencing factors are introduced to define the power system utility function U P1 、Coal system utility function U P2 、Oil system utility function U P3 and the utility function U of the natural gas system P4 The method is as follows: Power system utility function U P1 : U P1 =a ele ·R ele (s P1 )―b ele ·C ele (s P1 ,T,H)―c ele ·L ele (s P1 ); Coal system utility function U P2 : U P2 =a coal ·R coal (s P2 )―b coal ·C coal (s P2 ,T,H)―c coal ·L coal (s P2 ); Oil system utility function U P3 : U P3 =a oil ·R oil (S P3 )―b oil ·C oil (s P3 ,T,H)―c oil ·L oil (s P3 ); Natural gas system utility function: U P4 =a gas ·R gas (sP4)―b gas ·C gas (s P4 ,T,H)―c gas ·L gas (S P4 ); Among them, R ele represents the electricity revenue function; C ele represents the electricity cost function; L ele represents the power loss function; α ele , β ele , γ ele is the power weight coefficient; R coal represents the coal revenue function; C coal represents the coal cost function; L coal represents the coal loss function; α coal , β coal , γ coal is the coal weight coefficient; R oil represents the oil revenue function; C oil represents the oil cost function; L oil represents the oil loss function; α oil , β oil , γ oil is the oil weight coefficient; R gas represents the natural gas revenue function; C gas represents the natural gas cost function; L gas represents the natural gas loss function; α gas , β gas , γ gas is the weight coefficient; T is the temperature; H is the humidity.
9. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 7 is characterized in that: In S4.2.5, the power balance constraint, production capacity constraint and storage capacity constraint are set, and the objective function method is constructed as follows: Power balance constraints: in, is the total power output of all energy systems; P i (s i ) is the power output of the i-th energy system, depending on its strategy s i ;D total (t) is the total electricity demand, which changes with time t; Production capacity constraints: Among them, P i (s i ) is the power output of the i-th energy system; P i,max is the maximum production capacity of the i-th energy system; Storage capacity constraints: Among them, S i (s i ) is the storage capacity of the i-th energy system, depending on its strategy s i ; S i,max is the maximum storage capacity of the i-th energy system; Objective function; in, To express finding the combination that maximizes the objective function among all strategy combinations s, s = (s P1 ,s P2 ,s P3 ,s P4 );s ―P1 is the strategy combination of the other three systems except the power system; ―P2 is the strategy combination of the other three systems except the coal system; ―P3 is the strategy combination of the other three systems except the oil system; ―P4 It is the strategy combination of the other three systems except the natural gas system.
10. The multi-energy coordinated operation method of the integrated energy system based on the Internet of Things according to claim 7 is characterized in that: In S4.2.6, the method for optimizing the objective function using the strategy simulation optimization algorithm based on Nash equilibrium theory is as follows: Set the initial strategy: in, is the initial strategy of the ith energy system; To represent all possible strategies s i Find the utility function U i Maximizing strategies; is the initial strategy of all energy systems except the i-th energy system; Set the iterative update strategy: in, is the strategy of the ith participant in the k+1th iteration; k is the number of iterations; Termination condition: When the strategies of all participants no longer change, Nash equilibrium is reached: in, means that the strategy of the i-th participant in the k+1th iteration is the same as that in the kth iteration; This holds true for all energy systems.
Citation Information
Cited By
Smart park energy management method and system based on digital twinning
CN121481130A
