CPSS system based on cloud edge collaborative control, regulation and control method and application

Abstract

This invention relates to a CPSS system, control method, and application based on cloud-edge collaborative control. The system includes a physical layer, an information layer, and a social layer. The physical layer collects user electricity consumption information and power generation information from power generation equipment, uploads the information to the information layer, executes dispatch instructions, and feeds back the execution results to the information layer. The information layer receives electricity consumption and power generation information, processes and calculates the information using cloud-edge collaborative technology, performs decision simulation based on the calculation results, generates dispatch instructions and guidance instructions, and sends them to the physical layer and user layer respectively. It also optimizes the simulation decisions based on the execution results fed back from the information layer and user layer. The social layer includes operators and users. Operators execute guidance instructions to adjust user electricity consumption behavior and feed back the execution results to the information layer. Through cloud-edge collaborative technology, the computing pressure on the cloud is reduced, and the supply relationship between users and operators can be quickly resolved.

Description

Technical Field

[0001] This invention relates to the field of control systems and CPSS, specifically to a CPSS system, control method, and application based on cloud-edge collaborative control. Background Technology

[0002] Cyber-physical-social systems (CPS) are a class of complex systems comprised of a physical system, a social system (including human beings), and an information system (CyberSystem) connecting the two. Currently, CPS research, primarily focusing on engineering complexity, has become a global research hotspot, achieving significant research results and application benefits in complex systems applications such as transportation, defense, energy, healthcare, and large-scale construction facilities. CPSS, building upon the CPS concept, incorporates human and social factors into the management and control of complex systems. CPSS extends the research scope to social systems, achieving an organic integration of personnel organization and physical systems through intelligent human-computer interaction, potentially enabling comprehensive management and control of various complex systems.

[0003] In recent years, cloud computing technology, characterized by high reliability, easy scalability, and resource sharing, has been applied in an increasing number of fields. The State Grid Corporation of China's Power Dispatching and Control Center has planned and constructed a physically distributed, logically unified dispatching and control cloud platform, aiming to achieve flexible resource allocation, efficient service integration, convenient application development, and intelligent data utilization. However, during the construction of the dispatching and control cloud, the types and volume of data accessed have exploded, placing enormous pressure on the cloud center's data processing capabilities. To address the challenges faced by the cloud center, edge computing has been proposed as a new computing paradigm and is gradually becoming an emerging computing model adapted to the needs of the Internet of Things (IoT) applications. Edge devices in the cloud-edge collaborative computing model possess computing and analysis capabilities. By performing computations at the network edge, overall computing power can be expanded while effectively reducing network bandwidth and the consumption of cloud center computing and storage resources. Therefore, more and more researchers are beginning to study the application of cloud-edge collaborative technology in the power grid field.

[0004] Prior to 2012, the team at the Institute of Automation, Chinese Academy of Sciences, developed the ACP method, the theoretical framework for parallel control and management, and overcame some core technologies, successfully demonstrating its application in urban transportation and petrochemical production. From 2013 to the present, with funding from key projects and major research programs of the National Natural Science Foundation of China, military science and technology projects, provincial and ministerial science and technology projects, and enterprise projects, institutions such as the National University of Defense Technology have continuously participated, focusing on the research and development of the ACP method applicable to modeling, experimentation, and decision-making in complex systems. Emphasis has been placed on data, knowledge, and decision-making, respectively, researching methods for constructing artificial systems based on big data in complex systems such as CPSS, methods for constructing scenario-response knowledge bases based on computational experiments, and control and management methods based on parallel interaction between virtual and real systems. In terms of theoretical research, the concept, basic methods and applications of parallel control have been improved. The differences between the parallel expansion method of virtual-real interaction and the parallel partitioning method of simultaneous computation have been emphasized. Parallel control is proposed to be a specific application of the ACP method in the field of control. It is a data-driven computational control method. Its core is to use artificial systems for modeling and representation, to analyze and evaluate through computational experiments, and finally to achieve control and management of complex systems through parallel execution.

[0005] Currently, CPSS systems face enormous cloud computing pressure in energy management, making it difficult to address the challenges of real-time, ever-changing user needs and low collaborative efficiency in complex manufacturing environments. Summary of the Invention

[0006] This invention provides a CPSS system and control method based on cloud-edge collaborative control. It introduces a cloud-edge-device architecture on the basis of the CPSS system. Through cloud-edge collaborative technology, it alleviates the pressure of centralized computing in the cloud, and can process data and make decisions more quickly. It enables information interaction between users and operators to guide and incentivize users' electricity consumption behavior, and can solve the problems of real-time changes in user needs and low collaborative efficiency in dynamic and complex manufacturing environments.

[0007] The solution of the present invention to solve the above technical problems is as follows: a CPSS system based on cloud-edge collaborative control architecture, wherein the architecture of the CPSS system includes a physical layer, an information layer, and a social layer;

[0008] The physical layer is used to collect electricity consumption information of users in the social layer and power generation information of power generation physical equipment in the physical layer, and upload the electricity consumption information and power generation information to the information layer, execute the scheduling instructions issued by the information layer, and feed back the execution results to the information layer;

[0009] The information layer is used to receive electricity consumption information and power generation information. At the same time, it uses cloud-edge collaborative technology to process and calculate the electricity consumption information and power generation information, and performs decision simulation based on the calculation results to generate scheduling instructions and guidance instructions. The scheduling instructions are sent to the information layer and the guidance instructions are sent to the user layer. The simulation decision is further optimized based on the execution results fed back by the information layer and the user layer.

[0010] The social layer includes operators and users. Users include small users such as ordinary residential communities and large users such as large factories and enterprises. Operators interact with users, execute guidance instructions to adjust users' electricity consumption behavior, and feed back the execution results to the information layer, thereby achieving a balance between supply and demand between users and operators.

[0011] Preferably, the information layer is built on a cloud-edge-device architecture, including a cloud control center, a pipeline communication system, an edge server, and a virtual artificial system;

[0012] The pipeline communication system is used to connect the physical layer with the cloud control center and edge servers, transmitting power consumption and generation information from the physical layer to the cloud control center and edge servers. Given the massive amounts of information uploaded by numerous and widely distributed device terminals and user terminals, its transmission requires the support of information and communication technologies. With the emergence of the ubiquitous Internet of Things (IoT) concept, various links in the power system are interconnected. Pipeline communication, as a ubiquitous connection medium between the cloud management platform and edge servers, transmits key data and information of resource clusters, such as the cluster's adjustable capacity, ramp rate, and real-time status information.

[0013] The edge server is equipped with multiple edge computing nodes, which divide the received electricity consumption information and power generation information into smaller and more manageable units for processing. Based on the multiple edge computing nodes, edge computing is performed on the electricity consumption information and power generation information to establish an equivalent model of the cluster (including information such as adjustable resource types, output range, and ramp rate). The equivalent model is then uploaded to the cloud control center. The server is used to receive scheduling instructions and guidance instructions issued by the cloud control center, control the physical layer and operators to execute them, and feed back the execution results to the cloud control center.

[0014] The cloud control center is used to set up edge computing nodes on the edge server through cloud-edge collaboration technology; it is used to receive user information and power generation information and collect equivalent models, and use technologies such as cloud computing, big data, artificial intelligence, and blockchain to perform data cleaning, classification, modeling, and storage, generate a cloud dynamic aggregation model, and the cloud dynamic aggregation model calculates data information through cloud-edge collaboration technology, uploads the data information to the virtual artificial system, receives simulated decisions generated by the virtual artificial system, decomposes the simulated decisions into scheduling instructions and guidance instructions and sends them to the edge server, and receives feedback on the execution results and transmits the feedback results to the virtual artificial system;

[0015] The virtual artificial intelligence system is used to receive and organize data information uploaded by the cloud control center, extract features from the data information, perform modeling, calculation and simulation based on the extracted features, generate simulated decisions and transmit them to the cloud control center, and further optimize the simulated decisions based on the feedback from the cloud control center.

[0016] The core of the information layer is to use cloud-edge collaboration technology to set up edge computing nodes on edge servers, which actively extends and effectively supplements the cloud computing center. This solves the problems of excessive network bandwidth consumption and poor data timeliness caused by centralized computing, alleviates the computing and storage pressure on the control cloud center, and effectively improves the data quality of the control cloud collaboration nodes.

[0017] The cloud control center has three functions in the cloud-edge collaboration system: global task scheduling, global rule management, and data quality management. Global task scheduling is responsible for the unified management of cloud-edge collaboration tasks; the global rule management module is responsible for the unified management of the data collection scope and data processing rules of each collaboration node; and data quality management is responsible for the unified data management of cloud-edge collaboration nodes.

[0018] Preferably, the edge server is also used to execute the rules formulated by the cloud control center and feed back the execution results to the cloud control center; the cloud control center is also used to formulate rules on the edge server and receive feedback on the execution results.

[0019] Preferably, the cloud control center is also used to collect user information via the Internet, including users' electricity usage intentions and behavioral information.

[0020] Preferably, the edge server includes a task management module, a rule management module, and a data management module;

[0021] The task management module is used to receive scheduling instructions and guidance instructions issued by the cloud control center, control the physical layer and operators to execute them, and report the execution results back to the cloud control center;

[0022] The data management module is used to receive electricity consumption information and power generation information, summarize and integrate them, conduct preliminary evaluation and analysis, establish an equivalent model of the cluster, and then report the integration results, analysis results and equivalent model to the cloud control center.

[0023] The rule management module is used to execute rules pre-set in the cloud control center at the edge and feed back the execution results to the cloud control center.

[0024] Preferably, the virtual artificial system includes a database module, a feature extraction module, and a calculation and simulation module;

[0025] The database module is used to receive various data information from the cloud control center and classify and organize it from multiple dimensions such as time, space, different physical tags and social tags.

[0026] The feature extraction module is used to process and mine data in the database using big data technology, and to extract features from various types of data using machine learning and artificial intelligence technology.

[0027] The computation and simulation module is used to model the extracted data features, conduct computational experiments, obtain simulated decisions and transmit them to the cloud control center, and further optimize the simulated decisions based on feedback from the cloud control center.

[0028] Preferably, the physical layer includes physical devices and terminal devices. The physical devices include power generation physical devices such as photovoltaic power generation, wind power generation, hydropower generation, thermal power generation, and energy storage units, and terminal devices such as smart meters, mobile phones, and computers. All power generation physical devices include power electronic converters, sensors, and controllers.

[0029] The power generation physical equipment is used to collect real-time electricity consumption and power generation information, including operating characteristic parameters, output data, and load demand, through terminal equipment technology. The power generation physical equipment constructs its own control model based on the collected data, and transmits the collected data to the edge server and cloud control center, and executes the scheduling instructions transmitted by the edge server.

[0030] Preferably, the terminal device features technologies including two-way metering, meter reading, anomaly monitoring, and contactless interaction.

[0031] The control method for the CPSS system based on the cloud-edge collaborative control described above includes the following steps:

[0032] The physical layer collects electricity consumption information from users in the social layer and power generation information from the power generation equipment in the physical layer, uploads the electricity consumption information and power generation information to the information layer, executes the scheduling instructions issued by the information layer, and feeds back the execution results to the information layer.

[0033] The information layer receives electricity consumption information and power generation information, and uses cloud-edge collaborative technology to process and calculate the electricity consumption information and power generation information. Based on the calculation results, it performs decision simulation, generates scheduling instructions and guidance instructions, sends the scheduling instructions to the information layer, sends the guidance instructions to the user layer, and further optimizes the simulation decision based on the execution results fed back by the information layer and the user layer.

[0034] The social layer includes operators and users. Operators interact with users, execute guidance instructions to adjust users' electricity consumption behavior, and feed the execution results back to the information layer, thereby achieving a balance between supply and demand between users and operators.

[0035] This invention also provides an application of a cloud-edge collaborative control-based CPSS system in microgrid energy management, aiming to maximize the overall revenue of operators:

[0036] 1)

[0037] Where B is the total profit of the microgrid operator, I is the total revenue of the microgrid operator, and C is the total cost of the microgrid operator;

[0038] Total Revenue:

[0039] 2)

[0040] Introducing renewable energy utilization rate:

[0041] 3)

[0042] in, P users，t This refers to the amount of electricity sold by a microgrid operator to users within one hour; M users，t This refers to the electricity price that a microgrid operator sells to users within one hour; P s,g,t This refers to the amount of electricity sold by a microgrid operator to the grid within one hour. M s,g,t This refers to the price at which a microgrid operator sells electricity to the grid within one hour; P res It is a renewable energy source that is consumed;

[0043] 4)

[0044] in, This refers to the user's initial electrical load; It is the response quantity after the guidance information is provided;

[0045] 5)

[0046] in, This refers to the discount ratio coefficient for the guidance information;

[0047] The price elasticity of electricity demand refers to the responsiveness of relative changes in demand to relative changes in electricity prices. It reflects the sensitivity of users to changes in electricity prices and is widely used in user-response pricing models. The price elasticity coefficient is... express;

[0048] Total cost to the operator:

[0049] 6)

[0050] in, This refers to the amount of electricity that operators purchase from the power grid. This refers to the electricity price that operators pay when purchasing electricity from the grid. This refers to the real-time electricity price charged by the operator to users within one hour. This refers to the scheduling cost coefficient. This refers to the scheduling volume; ΔP t This refers to the number of responses following the guidance information within one hour; η t This refers to the discount rate coefficient for information displayed within one hour;

[0051] Set constraints:

[0052] During time period t, supply and demand are balanced:

[0053] 7)

[0054] User response volume is less than renewable energy generation:

[0055] 8)

[0056] in, P e,i This refers to the total power generation of the edge servers; This refers to the amount of electricity sold by microgrid operators to users; P s,g This refers to the amount of electricity that microgrid operators sell to the grid.

[0057] The beneficial effects of this invention are: by adding a cloud-edge-device architecture to the CPSS system and using cloud-edge collaborative control technology, the pressure of centralized computing and storage in the cloud control center is reduced, data can be processed more quickly, and the data quality of the cloud collaborative nodes is also effectively improved, enhancing timeliness, enabling rapid decision-making, releasing guidance and scheduling information, providing reasonable incentives for users, and rationally planning power generation physical equipment.

[0058] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0059] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0060] Figure 1 This is a schematic diagram of the framework of a CPSS system based on cloud-edge collaborative control provided in Embodiment 1 of the present invention;

[0061] Figure 2 This is a schematic diagram illustrating the application of a cloud-edge collaborative control-based CPSS system in energy management, as provided in Embodiment 3 of the present invention.

[0062] Figure 3 The flowchart of the cloud-edge collaborative algorithm in the energy management process of a CPSS system based on cloud-edge collaborative control, provided in Embodiment 3 of the present invention, is shown. Detailed Implementation

[0063] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0064] Example 1

[0065] A cloud-edge collaborative control (CPSS) system, wherein the architecture of the CPSS system includes a physical layer, an information layer, and a social layer;

[0066] The physical layer is used to collect electricity consumption information of users in the social layer and power generation information of power generation equipment in the physical layer. It then uploads the electricity consumption and power generation information to the information layer, executes the dispatch instructions issued by the information layer, and feeds back the execution results to the information layer. Among them, the electricity consumption information of users includes users' energy consumption intentions and behavioral information.

[0067] The information layer is used to receive electricity consumption and generation information, and at the same time, it uses cloud-edge collaborative technology to process and calculate the electricity consumption and generation information, and performs decision simulation based on the calculation results to generate scheduling instructions and guidance instructions. The scheduling instructions are sent to the information layer and the guidance instructions are sent to the user layer. The simulation decision is further optimized based on the execution results fed back by the information layer and the user layer.

[0068] The social layer includes operators and users. Users include small users such as ordinary residential communities and large users such as large factories and enterprises. Operators interact with users, execute guidance instructions to adjust users' electricity consumption behavior, and feed back the execution results to the information layer, thereby achieving a balance between supply and demand between users and operators.

[0069] Preferably, the information layer is built on a cloud-edge-device architecture, including a cloud control center, a pipeline communication system, edge servers, and a virtual artificial system;

[0070] Pipeline communication systems connect the physical layer with cloud control centers and edge servers, transmitting power consumption and generation information from the physical layer to these systems. Given the vast amounts of information uploaded by numerous and widely distributed device and user terminals, this transmission requires the support of information and communication technologies. With the emergence of the ubiquitous Internet of Things (IoT) concept, and the interconnection of various components of the power system, pipeline communication serves as a ubiquitous connection medium between the cloud management platform and edge servers, transmitting critical data and information from resource clusters, such as adjustable capacity, ramp rates, and real-time status information.

[0071] The edge server is equipped with multiple edge computing nodes. It divides the received electricity consumption information and power generation information into smaller and more manageable units for processing. It performs edge computing and establishes an equivalent model of the cluster (including information such as adjustable resource types, output range, and ramp rate). The equivalent model is then uploaded to the cloud control center. The server is used to receive scheduling instructions and guidance instructions issued by the cloud control center, control the physical layer and operators to execute them, and feed back the execution results to the cloud control center.

[0072] The cloud control center is used to set up edge computing nodes on edge servers through cloud-edge collaboration technology; it is used to receive user information and power generation information and collect equivalent models, and use technologies such as cloud computing, big data, artificial intelligence, and blockchain to perform data cleaning, classification, modeling, and storage, generating a cloud dynamic aggregation model. The cloud dynamic aggregation model calculates data information through cloud-edge collaboration technology, uploads the data information to the virtual artificial system, receives simulated decisions generated by the virtual artificial system, decomposes the simulated decisions into scheduling instructions and guidance instructions and sends them to the edge server, and receives feedback on the execution results and transmits the feedback results to the virtual artificial system.

[0073] The virtual artificial intelligence system is used to receive and process data information uploaded by the cloud control center, extract features from the data information, perform modeling, calculation and simulation based on the extracted features, generate simulated decisions and transmit them to the cloud control center, and further optimize the simulated decisions based on the feedback from the cloud control center.

[0074] The core of the information layer is to use cloud-edge collaboration technology to set up edge computing nodes on edge servers, which actively extends and effectively supplements the cloud computing center. This solves the problems of excessive network bandwidth consumption and poor data timeliness caused by centralized computing, alleviates the computing and storage pressure on the control cloud center, and effectively improves the data quality of the control cloud collaboration nodes.

[0075] The cloud control center has three functions in the cloud-edge collaboration system: global task scheduling, global rule management, and data quality management. Global task scheduling is responsible for the unified management of cloud-edge collaboration tasks; the global rule management module is responsible for the unified management of the data collection scope and data processing rules of each collaboration node; and data quality management is responsible for the unified data management of cloud-edge collaboration nodes.

[0076] Edge servers are also used to execute rules set by the cloud control center and feed back the results of rule execution to the cloud control center; the cloud control center is also used to set rules on edge servers and receive feedback on the results of rule execution.

[0077] The cloud-based control center is also used to collect user information via the internet.

[0078] The edge server includes a task management module, a rule management module, and a data management module;

[0079] The task management module is used to receive scheduling instructions and guidance instructions issued by the cloud control center, control the physical layer and operators to execute them, and report the execution results back to the cloud control center;

[0080] The data management module is used to receive electricity consumption information and power generation information, summarize and integrate them, conduct preliminary evaluation and analysis, establish an equivalent model of the cluster, and then report the integration results, analysis results and equivalent model to the cloud control center.

[0081] The rules management module is used to execute rules pre-defined in the cloud control center at the edge and feed the execution results back to the cloud control center.

[0082] The virtual artificial intelligence system includes a database module, a feature extraction module, and a computation and simulation module;

[0083] The database module is used to receive various data information from the cloud control center and classify and organize it from multiple dimensions such as time, space, different physical tags, and social tags.

[0084] The feature extraction module is used to process and mine data in the database using big data technology, and to extract features from various types of data using machine learning and artificial intelligence technology.

[0085] The computation and simulation module is used to model the extracted data features, conduct computational experiments, obtain simulated decisions and transmit them to the cloud control center, and further optimize the simulated decisions based on the feedback from the cloud control center.

[0086] The physical layer includes physical devices and terminal devices. Physical devices include power generation physical devices such as photovoltaic power generation, wind power generation, hydropower generation, thermal power generation, and energy storage units, as well as terminal devices such as smart meters, mobile phones, and computers. All power generation physical devices include power electronic converters, sensors, and controllers.

[0087] Power generation physical equipment is used to collect real-time electricity consumption and power generation information, including operating characteristic parameters, output data, and load demand, through terminal equipment technology. The power generation physical equipment constructs its own control model based on the collected data, and transmits the collected data to the edge server and cloud control center, and executes the scheduling instructions transmitted by the edge server.

[0088] The technologies of the terminal equipment include two-way metering, meter reading, anomaly monitoring, and contactless interaction.

[0089] The control method for the CPSS system based on cloud-edge collaborative control, as described above, includes the following steps:

[0090] The physical layer collects electricity consumption information from users in the social layer and power generation information from the physical generation equipment in the physical layer, and uploads the electricity consumption information and power generation information to the information layer. It also executes the scheduling instructions issued by the information layer and feeds back the execution results to the information layer.

[0091] The information layer receives electricity consumption and generation information, and uses cloud-edge collaborative technology to process and calculate the electricity consumption and generation information. Based on the calculation results, it performs decision simulation, generates scheduling instructions and guidance instructions, sends the scheduling instructions to the information layer, sends the guidance instructions to the user layer, and further optimizes the simulation decision based on the execution results fed back by the information layer and the user layer.

[0092] The social layer includes operators and users. Operators interact with users, execute guidance instructions to adjust users' electricity consumption behavior, and feed the results back to the information layer, thereby achieving a balance between supply and demand between users and operators.

[0093] Example 2

[0094] A CPSS control method based on cloud-edge collaborative control is disclosed. The method is applied to the CPSS system based on cloud-edge collaborative control in Example 1. The architecture of the CPSS system includes a physical layer, an information layer, and a social layer. The method includes the following steps:

[0095] The physical layer collects electricity consumption information from users in the social layer and power generation information from the physical generation equipment in the physical layer, and uploads the electricity consumption information and power generation information to the information layer. It also executes the scheduling instructions issued by the information layer and feeds back the execution results to the information layer.

[0096] The information layer receives electricity consumption and generation information, and uses cloud-edge collaborative technology to process and calculate the electricity consumption and generation information. Based on the calculation results, it performs decision simulation, generates scheduling instructions and guidance instructions, sends the scheduling instructions to the information layer, sends the guidance instructions to the user layer, and further optimizes the simulation decision based on the execution results fed back by the information layer and the user layer.

[0097] The social layer includes operators and users. Operators interact with users, execute guidance instructions to adjust users' electricity consumption behavior, and feed the results back to the information layer, thereby achieving a balance between supply and demand between users and operators.

[0098] Example 3

[0099] An application of a cloud-edge collaborative control CPSS system in microgrid energy management, taking interactive energy management between users and operators as an example.

[0100] The user-side database in the interactive energy management process of the CPSS system includes data from the network, user information, equipment data, and load data. User information (including electricity usage intentions and behavioral information) can be collected by the cloud control center via internet apps and uploaded to the cloud control center database. Basic user electricity usage information is collected by signal receivers at the physical layer, and the physical layer terminal devices upload the collected basic equipment information and user load information to the edge server database.

[0101] In the interactive energy management process of the CPSS system, the operator mainly receives guidance information and electricity price information from the cloud control center, and then distributes this information to users through the Internet, APP, etc., to incentivize users to consume electricity.

[0102] The edge server in the interactive energy management process of the CPSS system includes an edge server database, optimization objectives, and optimization strategies. The optimization objective of the edge server is to achieve optimal edge cluster control strategy and maximum economic efficiency. Optimization strategies include edge computing technology, preprocessing database information to form resource external characteristic models, and machine learning. The database stores user information and device information collected from the physical layer, and uploads the formed resource external characteristic models, controllable resource types, and controllable ranges to the cloud control center database. The edge server receives tasks and control commands from the cloud control center and controls the physical layer terminal devices.

[0103] The CPSS system's interactive energy management process utilizes a cloud-based control center, which includes a cloud control center database, optimization objectives, and optimization strategies. The optimization objective of the cloud control center is to maximize overall economic efficiency and minimize operational processes. The optimization strategies include electricity pricing, guidance information, and physical strategies. The database includes resource external characteristic models uploaded from edge servers, as well as adjustable resource types, adjustable ranges, and physical equipment data; and user electricity consumption intention information uploaded to the cloud control center via the internet. The cloud control center interacts with the database in the virtual artificial intelligence (VAI) system to obtain simulated decisions. After implementing these decisions, the center feeds back the information to the VAI system, leading to better control decisions and guidance information. These control decisions and guidance information are then distributed to the edge servers and operators, respectively.

[0104] The CPSS system's interactive energy management process utilizes a virtual artificial system, which comprises three main modules: a database module, a feature extraction module, and a computation and simulation module. The database module receives various data from the cloud control center and categorizes and organizes it across multiple dimensions, including time, space, different physical labels, and social labels. The feature extraction module employs big data technology to process and mine data from the database, and utilizes machine learning and artificial intelligence techniques to extract features from various data types. The computation and simulation module is the core stage of the virtual artificial system. It models the extracted data features, conducts computational experiments, transmits the obtained optimized control strategies and guidance information to the cloud control center, and further optimizes the control strategies based on feedback from the cloud control center.

[0105] In the interactive energy management process of the CPSS system, the power equipment is the physical layer terminal equipment, which receives control commands from the edge servers to supply power to users. Each edge server aims for its own optimal benefit, while the cloud control center's decision-making objective is global optimality, that is, maximizing the operator's overall benefit.

[0106] The model is constructed as follows:

[0107] 1)

[0108] Where B is the total profit of the microgrid operator, I is the total revenue of the microgrid operator, and C is the total cost of the microgrid operator;

[0109] Total Revenue:

[0110] 2)

[0111] Introducing renewable energy utilization rate:

[0112] 3)

[0113] in, P users，t This refers to the amount of electricity sold by a microgrid operator to users within one hour; M users，t This refers to the electricity price that a microgrid operator sells to users within one hour; P s,g,t This refers to the amount of electricity sold by a microgrid operator to the grid within one hour. M s,g,t This refers to the price at which a microgrid operator sells electricity to the grid within one hour; P res It is a renewable energy source that is consumed;

[0114] 4)

[0115] in, This refers to the user's initial electrical load; It is the response quantity after the guidance information is provided;

[0116] 5)

[0117] in, This refers to the discount ratio coefficient for the guidance information;

[0118] The price elasticity of electricity demand refers to the responsiveness of relative changes in demand to relative changes in electricity prices. It reflects the sensitivity of users to changes in electricity prices and is widely used in user-response pricing models. The price elasticity coefficient is... express.

[0119] Total cost to the operator:

[0120] 6)

[0121] in, This refers to the amount of electricity that operators purchase from the power grid. This refers to the electricity price that operators pay when purchasing electricity from the grid. This refers to the real-time electricity price charged by the operator to users within one hour. This refers to the scheduling cost coefficient. This refers to the scheduling volume; ΔP t This refers to the number of responses following the guidance information within one hour; η t This refers to the discount rate coefficient for information displayed within one hour;

[0122] Set constraints:

[0123] During time period t, supply and demand are balanced:

[0124] 7)

[0125] User response volume is less than renewable energy generation:

[0126] 8)

[0127] in, P e,i This refers to the total power generation of the edge servers. This refers to the amount of electricity sold by microgrid operators to users; P s,g This refers to the amount of electricity that microgrid operators sell to the grid.

[0128] The cloud-edge collaborative algorithm built into the above model is shown in the attached figure. Figure 3 As shown, the algorithm aims at global economic optimization and finds the optimal strategy by analyzing the relative benefits between edge cooperation and guidance information.

[0129] First, determine the algebraic relationship between the power generation of the physical power generation equipment controlled by each edge server and the electricity consumption of users within the server's range. If the power generation of the physical power generation equipment is less than the electricity consumption of users, record it as "-"; otherwise, record it as "+"; if they are exactly equal, record it as "0". The output external characteristic model includes the types and quantities of schedulable data.

[0130] Secondly, each edge server optimizes itself to maximize its own performance, and after meeting its own needs, uploads its external characteristic model to the cloud control center. The cloud center then performs global optimization with the goal of achieving the optimal global economy.

[0131] Finally, the optimal simulation decision-making and guidance information from the cloud control center are obtained.

[0132] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Those skilled in the art can readily implement the present invention based on the accompanying drawings and the above description. However, any modifications, alterations, or variations made by those skilled in the art without departing from the scope of the present invention, utilizing the disclosed technical content, are equivalent embodiments of the present invention. Furthermore, any modifications, alterations, or variations made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the present invention.

Claims

1. A CPSS system based on cloud-edge collaborative control, characterized in that, The architecture of the CPSS system includes a physical layer, an information layer, and a social layer. The physical layer is used to collect electricity consumption information of users in the social layer and power generation information of power generation physical equipment in the physical layer, and upload the electricity consumption information and the power generation information to the information layer, execute the scheduling instructions issued by the information layer, and feed back the execution results to the information layer; The social layer includes operators and users. The operators are used to interact with the users, execute guidance instructions to adjust the users' electricity consumption behavior, and feed back the execution results to the information layer. The information layer is built on a cloud-edge-device architecture, including a cloud control center, a pipeline communication system, edge servers, and a virtual artificial system. The pipeline communication system is used to connect the physical layer, the cloud control center, and the edge server, and transmits the power consumption information and power generation information of the physical layer to the cloud control center and the edge server, respectively. The edge server is equipped with multiple edge computing nodes. It receives electricity consumption and power generation information, divides it into smaller, more manageable units for processing, and performs edge computing on the electricity consumption and power generation information based on the multiple edge computing nodes to establish an equivalent model of the cluster. This equivalent model is then uploaded to the cloud control center. The edge server also receives scheduling and guidance instructions from the cloud control center, controls the physical layer and the operator to execute them, and feeds back the execution results to the cloud control center. The cloud control center is used to set up edge computing nodes on the edge server through cloud-edge collaboration technology; it is used to receive user information and power generation information and collect equivalent models, and use cloud computing, big data, artificial intelligence and blockchain to perform data cleaning, classification, modeling and storage to generate a cloud dynamic aggregation model. The cloud dynamic aggregation model calculates data information through cloud-edge collaboration technology, uploads the data information to the virtual artificial system, receives simulated decisions generated by the virtual artificial system, decomposes the simulated decisions into scheduling instructions and guidance instructions and sends them to the edge server, and receives feedback on the execution results and transmits the feedback results to the virtual artificial system. The virtual artificial intelligence system is used to receive and organize data information uploaded by the cloud control center, extract features from the data information, perform modeling, calculation and simulation based on the extracted features, generate simulated decisions and transmit them to the cloud control center, and further optimize the simulated decisions based on the feedback from the cloud control center.

2. The CPSS system based on cloud-edge collaborative control according to claim 1, characterized in that, The edge server is also used to execute the rules formulated by the cloud control center and feed back the execution results to the cloud control center; the cloud control center is also used to formulate rules on the edge server and receive feedback on the execution results.

3. The CPSS system based on cloud-edge collaborative control according to claim 1, characterized in that, The cloud control center is also used to collect user information via the Internet.

4. The CPSS system based on cloud-edge collaborative control according to claim 1, characterized in that, The edge server includes a task management module, a rule management module, and a data management module; The task management module is used to receive scheduling instructions and guidance instructions issued by the cloud control center, control the physical layer and the operator to execute them, and feed back the execution results to the cloud control center; The data management module is used to receive electricity consumption information and power generation information, summarize and integrate them, conduct preliminary evaluation and analysis, establish an equivalent model of the cluster, and then report the integration results, analysis results and equivalent model to the cloud control center. The rule management module is used to execute rules pre-set in the cloud control center at the edge and feed back the execution results to the cloud control center.

5. The CPSS system based on cloud-edge collaborative control according to claim 1, characterized in that, The virtual artificial intelligence system includes a database module, a feature extraction module, and a calculation and simulation module; The database module is used to receive various data information from the cloud control center and classify and organize it from multiple dimensions such as time, space, different physical tags and social tags. The feature extraction module is used to process and mine data in the database using big data technology, and to extract features from various types of data using machine learning and artificial intelligence technology. The computation and simulation module is used to model the extracted data features, conduct computational experiments, obtain simulated decisions and transmit them to the cloud control center, and further optimize the simulated decisions based on the feedback from the cloud control center.

6. The CPSS system based on cloud-edge collaborative control according to claim 1, characterized in that, The physical layer includes physical devices and terminal devices. The physical devices include power generation physical devices such as photovoltaic power generation, wind power generation, hydropower generation, thermal power generation, and energy storage units, as well as terminal devices such as smart meters, mobile phones, and computers. The power generation physical equipment is used to collect real-time electricity consumption information and power generation information, including operating characteristic parameters, output data, and load demand, through the technology of the terminal equipment. The power generation physical equipment constructs its own control model based on the collected data, and transmits the collected data to the edge server and the cloud control center, and executes the scheduling instructions transmitted by the edge server.

7. The CPSS system based on cloud-edge collaborative control according to claim 6, characterized in that, The technologies of the terminal equipment include two-way metering, meter reading, anomaly monitoring, and contactless interaction.

8. A control method for a CPSS system based on cloud-edge collaborative control, characterized in that, The method is applied to the CPSS system based on cloud-edge collaborative control as described in any one of claims 1-7, wherein the architecture of the CPSS system includes a physical layer, an information layer, and a social layer; the method includes the following steps: The physical layer collects electricity consumption information from users in the social layer and power generation information from the physical generation equipment in the physical layer, and uploads the electricity consumption information and power generation information to the information layer. It also executes the scheduling instructions issued by the information layer and feeds back the execution results to the information layer. The information layer receives electricity consumption and generation information, and uses cloud-edge collaborative technology to process and calculate the electricity consumption and generation information. Based on the calculation results, it performs decision simulation, generates scheduling instructions and guidance instructions, sends the scheduling instructions to the information layer, sends the guidance instructions to the user layer, and further optimizes the simulation decision based on the execution results fed back by the information layer and the user layer. The social layer includes operators and users. Operators interact with users, execute guidance instructions to adjust users' electricity consumption behavior, and feed the results back to the information layer, thereby achieving a balance between supply and demand between users and operators.

9. An application of a cloud-edge collaborative control-based CPSS system in microgrid energy management, characterized in that, The application is based on the CPSS system based on cloud-edge collaborative control as described in any one of claims 1-7, and constructs a model with the goal of maximizing the overall revenue of the operator: 1) Where B is the total profit of the microgrid operator, I is the total revenue of the microgrid operator, and C is the total cost of the microgrid operator; Total Revenue: 2) Introducing renewable energy utilization rate: 3) in, P users，t This refers to the amount of electricity sold by a microgrid operator to users within one hour; M users，t This refers to the electricity price that a microgrid operator sells to users within one hour; P s,g,t This refers to the amount of electricity sold by a microgrid operator to the grid within one hour. M s,g,t This refers to the price at which a microgrid operator sells electricity to the grid within one hour; P res It is a renewable energy source that is consumed; 4) in, This refers to the user's initial electrical load; It is the response quantity after the guidance information is provided; 5) in, This refers to the discount ratio coefficient in the guidance information; The price elasticity of electricity demand refers to the responsiveness of relative changes in demand to relative changes in electricity prices. It reflects the sensitivity of users to changes in electricity prices and is widely used in user-response pricing models. The price elasticity coefficient is... express; Total cost to the operator: 6) in, This refers to the amount of electricity that operators purchase from the power grid. This refers to the electricity price that operators pay when purchasing electricity from the grid. This refers to the real-time electricity price charged by the operator to users within one hour. This refers to the scheduling cost coefficient. This refers to the scheduling volume; ΔP t This refers to the number of responses following the guidance information within one hour; η t This refers to the discount rate coefficient for information displayed within one hour; Set constraints: During time period t, supply and demand are balanced: 7) User response volume is less than renewable energy generation: 8) in, P e,i This refers to the total power generation of the edge servers; This refers to the amount of electricity sold by microgrid operators to users; P s,g This refers to the amount of electricity that microgrid operators sell to the grid.

Images