Multi-energy collaborative optimization management system and method

Abstract

The invention provides a multi-energy collaborative optimization management system and method, and belongs to the technical field of collaborative optimization. The demand module is used for determining an energy object of the multi-energy collaborative optimization management system based on a target demand, and configuring a sensor to obtain real-time data of all energy types; the system design module is used for designing a multi-energy collaborative optimization management system architecture in a test environment and storing real-time data of all energy types into a real-time database; the algorithm module is used for configuring an initial model and training the initial model according to the real-time data of all the energy types and the historical data of the corresponding energy types to obtain a first model, and the first model is a system algorithm part; the packaging module is used for adding the main functions into the multi-energy collaborative optimization management system architecture to obtain a first system and packaging the first system to obtain a system packaging file; the resource efficiency is improved, the application of renewable energy sources is promoted, and the optimization improvement degree is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of collaborative optimization technology, and in particular to a multi-energy collaborative optimization management system and method. Background Art

[0002] At present, with the gradual development of big data, it is increasingly being used in various fields. Among them, energy management is an important cornerstone of various factory production. However, multi-energy systems involve multiple energy types. The data formats, collection frequencies and communication protocols of different energy sources are different, which leads to challenges in data integration and real-time analysis.

[0003] Therefore, the present invention proposes a multi-energy collaborative optimization management system and method. Summary of the invention

[0004] The present invention provides a multi-energy collaborative optimization management system and method, which is used to determine the target energy type of the system and obtain energy parameters according to sensors, design an optimization model algorithm, generate a system architecture, and configure the system to maintain and update the actual environment.

[0005] In one aspect, the present invention provides a multi-energy collaborative optimization management system, comprising:

[0006] Demand module: Based on target demand, determine the energy objects of the multi-energy collaborative optimization management system, and configure sensors to obtain real-time data of all energy types;

[0007] System design module: Design a multi-energy collaborative optimization management system architecture in the test environment and store real-time data of all energy types in a real-time database;

[0008] Algorithm module: configures an initial model, trains the initial model according to the real-time data of all energy types and the historical data of the corresponding energy types, and obtains a first model, which is the system algorithm part;

[0009] System packaging module: adding the main functions to the multi-energy collaborative optimization management system architecture to obtain the first system, and packaging to obtain the system packaging file;

[0010] Configuration module: configures the system package files to the actual environment and monitors the performance parameters of the first system for maintenance and updates.

[0011] On the other hand, the demand module includes:

[0012] Determine demand units: Determine all energy objects for system analysis based on pre-set target demand;

[0013] Screening unit: Prioritize energy objects with energy-saving potential greater than the national standard as the main monitoring objects.

[0014] On the other hand, the demand module includes:

[0015] Acquisition and analysis unit: Determine the monitoring parameter type and parameter requirements based on the main monitoring objects;

[0016] Sensor unit: Match the corresponding sensor according to the parameter type, determine the initial configuration parameters of the sensor according to the parameter requirements, configure all sensors to the specified installation location, and obtain real-time data of all energy types.

[0017] On the other hand, the system design module includes:

[0018] Architecture generation unit: Determine the system architecture mode according to the target requirements, and design the components of the multi-energy collaborative optimization management system, wherein the components include a function tree composed of main function components and sub-function components;

[0019] Database unit: initializes the system database according to the preset standard database field table, and refines the fields based on the target requirements and generates different functional databases, all of which constitute the real-time database component;

[0020] Storage unit: initializing the real-time data of all energy types acquired by the sensor to obtain first real-time data, and performing time standardization parameter corresponding processing on the real-time data of any energy type according to the standard time interval to obtain standard real-time data;

[0021] Store standard real-time data for all energy types into a real-time database.

[0022] On the other hand, the algorithm module includes:

[0023] Model unit: Construct a collaborative optimization objective function, with the goal of minimizing the operating cost of any energy type, and construct a single scheduling model as follows:

[0024] Among them, C i represents the total operating cost of the i-th energy source, A i0 represents the operating cost before energy optimization, A i1 Indicates that there is only a single operating parameter characteristic value of the energy source, ε i represents the parameter cost conversion coefficient of the i-th energy source, ρ i represents the operating error coefficient of the i-th energy source;

[0025] Then the initial dispatch optimization model for all energy sources is constructed as follows:

[0026] Where n represents a total of n energy sources participating in the optimization, C represents the preset cost threshold, σ irepresents the cost ratio of the i-th energy source;

[0027] The real-time data of all energy types are used as a test set, and the historical data of the corresponding energy types are used as a training set. The initial scheduling optimization model is trained according to the training set to obtain a training model;

[0028] The test set is input into the first model to obtain the actual result, the actual result is compared with the predicted result to evaluate the deviation of the model index and adjust the model parameters for retraining to obtain the first model, which is the system algorithm part.

[0029] On the other hand, the system packaging module includes:

[0030] Main functional units: Using energy Internet technology, various main functions are connected together through the http protocol, multi-data interaction is realized through the API interface, and added to the multi-energy collaborative optimization management system architecture to obtain the first system;

[0031] Packaging unit: deploys the first system in the test environment, integrates and tests the first system and verifies the correctness of the data flow. If there is a data flow anomaly, handles the location where the anomaly occurs and updates the first system to obtain the second system.

[0032] The second system is packaged based on the packaging tool and the dependencies to obtain a system packaging file.

[0033] On the other hand, the configuration module includes:

[0034] Configuration unit: transfers the system package file from the test environment to the actual environment, configures the system parameter items based on the actual environment, and then completes the installation and starts the multi-energy collaborative optimization management system in the actual environment;

[0035] Monitoring unit: monitors the operation log of key performance parameters of the multi-energy collaborative optimization management system in real time based on the system monitoring tool;

[0036] Maintenance unit: Centrally manages operation logs and evaluates system performance, modifies packaging in the test environment based on the location of performance anomalies, updates system versions, and deploys configurations to the actual environment.

[0037] In another aspect, the present invention provides a multi-energy collaborative optimization management method, comprising:

[0038] Step 1: Based on the target requirements, determine the energy objects of the system and configure sensors to obtain real-time data of all energy types;

[0039] Step 2: Design a multi-energy collaborative optimization management system architecture in the test environment and store real-time data of all energy types in a real-time database;

[0040] Step 3: Configure the initial model, train the initial model according to the real-time data of all energy types and the historical data of the corresponding energy types, and obtain the first model, which is the system algorithm part;

[0041] Step 4: Add the main functions to the multi-energy collaborative optimization management system architecture to obtain the first system, and package it to obtain a system package file;

[0042] Step 5: Configure the system package file to the actual environment and monitor the system's performance parameters for maintenance and updates.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention provides a multi-energy collaborative optimization management system and method, which is used to determine the target energy type of the system and obtain energy parameters according to sensors, design an optimization model algorithm, generate a system architecture, and configure the system to maintain and update the actual environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a structural diagram of a multi-energy collaborative optimization management system provided by an embodiment of the present invention;

[0047] Figure 2 It is a flow chart of a multi-energy collaborative optimization management method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0049] Embodiment 1:

[0050] like Figure 1 As shown, an embodiment of the present invention provides a multi-energy collaborative optimization management system, including:

[0051] Demand module: Based on target demand, determine the energy objects of the multi-energy collaborative optimization management system, and configure sensors to obtain real-time data of all energy types;

[0052] System design module: Design a multi-energy collaborative optimization management system architecture in the test environment and store real-time data of all energy types in a real-time database;

[0053] Algorithm module: configures an initial model, trains the initial model according to the real-time data of all energy types and the historical data of the corresponding energy types, and obtains a first model, which is the system algorithm part;

[0054] System packaging module: adding the main functions to the multi-energy collaborative optimization management system architecture to obtain the first system, and packaging to obtain the system packaging file;

[0055] Configuration module: configures the system package files to the actual environment and monitors the performance parameters of the first system for maintenance and updates.

[0056] In this embodiment, the target requirements define the functions and performance that the system needs to achieve, and also provide a clear direction and framework for the design, development and implementation of the system.

[0057] In this embodiment, the multi-energy collaborative optimization management system is an integrated technology platform designed to monitor, manage and optimize multiple energy resources in real time.

[0058] In this embodiment, energy objects refer to various energy resources that need to be monitored and managed in the system, including: electricity, thermal energy, renewable energy (such as solar energy, wind energy), gas, etc.

[0059] In this embodiment, real-time data refers to various energy-related information that is collected, transmitted and processed in a timely and continuous manner during the operation of the system.

[0060] In this embodiment, the energy type refers to different types of energy resources in the system, including: electricity, thermal energy, renewable energy (such as solar energy, wind energy), gas, etc.

[0061] In this embodiment, the test environment refers to an independent environment used to develop, test and verify software or system functions.

[0062] In this embodiment, architecture refers to the overall structure and design of the system, involving the relationship between different components, data flow, division of functional modules, and technology selection.

[0063] In this embodiment, the real-time database is a database system specially designed for processing and storing real-time data.

[0064] In this embodiment, the initial model refers to a preliminary decision model built based on existing data (real-time data and historical data).

[0065] In this embodiment, the first model refers to a preliminary algorithm model that has been trained and constructed.

[0066] In this embodiment, the first system refers to a preliminary complete system formed after the design and implementation of each module.

[0067] In this embodiment, the system packaging file integrates the main functional modules of the entire system and their configurations, dependencies, documents, etc. into a deployable and installable file during the development of the multi-energy collaborative optimization management system.

[0068] In this embodiment, the actual environment refers to the specific physical environment in which the system runs in the real world.

[0069] In this embodiment, the performance parameters are key indicators used to evaluate system performance, including: response time, data throughput, system availability, resource utilization, etc.

[0070] In this embodiment, maintenance and update

[0071] The working principle and beneficial effects of the above technical solution are: through real-time data acquisition and model training, efficient energy management and optimized decision-making can be achieved, sustainable development can be supported, operating costs can be reduced, system performance can be improved, and resource utilization can be maximized.

[0072] Embodiment 2:

[0073] Based on the above embodiment 1, the demand module includes:

[0074] Determine demand units: Determine all energy objects for system analysis based on pre-set target demand;

[0075] Screening unit: Prioritize energy objects with energy-saving potential greater than the national standard as the main monitoring objects.

[0076] In this embodiment, energy saving potential refers to the amount of energy savings that can be achieved by implementing energy-saving measures in a specific energy usage scenario.

[0077] In this embodiment, the national standard refers to a standard formulated and issued by the Standardization Administration Committee (SAC).

[0078] In this embodiment, the main monitoring object refers to the energy object selected as the key monitoring and management in the system analysis.

[0079] The working principle and beneficial effects of the above technical solution are: by clarifying the demand units and energy-saving potential screening, giving priority to monitoring high-efficiency energy objects, achieving accurate analysis and resource optimization, promoting energy conservation and emission reduction, enhancing system compliance, and promoting sustainable development and environmental protection.

[0080] Embodiment 3:

[0081] Based on the above embodiment 2, the demand module includes:

[0082] Acquisition and analysis unit: Determine the monitoring parameter type and parameter requirements based on the main monitoring objects;

[0083] Sensor unit: Match the corresponding sensor according to the parameter type, determine the initial configuration parameters of the sensor according to the parameter requirements, configure all sensors to the specified installation location, and obtain real-time data of all energy types.

[0084] In this embodiment, the parameter type refers to various indicators and data used to quantify and evaluate the main monitoring objects, such as power, electricity, heat, flow, temperature, etc.

[0085] In this embodiment, parameter requirements refer to specific conditions and standards that need to be met for each monitoring parameter during the monitoring and acquisition process, such as accuracy, sampling frequency, range, etc.

[0086] In this embodiment, the initial parameters

[0087] The working principle and beneficial effects of the above technical solution are: by clarifying monitoring parameters and accurately configuring sensors, real-time data collection of energy can be achieved, data accuracy and management efficiency can be improved, support can be provided for intelligent decision-making and energy-saving optimization, and sustainable development can be promoted.

[0088] Embodiment 4:

[0089] Based on the above embodiment 1, the system design module includes:

[0090] Architecture generation unit: Determine the system architecture mode according to the target requirements, and design the components of the multi-energy collaborative optimization management system, wherein the components include a function tree composed of main function components and sub-function components;

[0091] Database unit: initializes the system database according to the preset standard database field table, and refines the fields based on the target requirements and generates different functional databases, all of which constitute the real-time database component;

[0092] Storage unit: initializing the real-time data of all energy types acquired by the sensor to obtain first real-time data, and performing time standardization parameter corresponding processing on the real-time data of any energy type according to the standard time interval to obtain standard real-time data;

[0093] Store standard real-time data for all energy types into a real-time database.

[0094] In this embodiment, the system architecture mode refers to a system structure and organization method used when designing and building a system.

[0095] In this embodiment, a component refers to an independent module or part that constitutes a system, and each component has its specific functions and responsibilities.

[0096] In this embodiment, the preset standard database field table is a key component in the multi-energy collaborative optimization management system, defining the database structure and fields to be used in the system.

[0097] In this embodiment, the system database is a core component in the multi-energy collaborative optimization management system, and is responsible for data storage, management and access.

[0098] In this embodiment, initialization refers to creating a corresponding database and its table structure according to a preset standard database field table, thus laying a foundation for data storage.

[0099] In this embodiment, the first real-time data refers to a collection of various energy data collected by the sensor for the first time after the system is started.

[0100] In this embodiment, the standard time interval refers to a preset time period for performing time standardization processing on real-time data.

[0101] In this embodiment, the time standardization parameter correspondence processing is to convert irregular data into a regular data format to ensure the consistency of the data in the time dimension.

[0102] In this embodiment, the standard real-time data refers to energy usage data generated according to a preset standard time interval after time standardization processing.

[0103] The working principle and beneficial effects of the above technical solution are: through componentized design and standardized data processing, multi-energy coordinated optimization management is achieved, system flexibility and data consistency are improved, efficient decision-making is supported, and energy management capabilities are enhanced.

[0104] Embodiment 5:

[0105] Based on the above embodiment 1, the algorithm module includes:

[0106] Model unit: Construct a collaborative optimization objective function, with the goal of minimizing the operating cost of any energy type, and construct a single scheduling model as follows:

[0107] Among them, C irepresents the total operating cost of the i-th energy source, A i0 represents the operating cost before energy optimization, A i1 Indicates that there is only a single operating parameter characteristic value of the energy source, ε i represents the parameter cost conversion coefficient of the i-th energy source, ρ l represents the operating error coefficient of the i-th energy source;

[0108] Then the initial dispatch optimization model for all energy sources is constructed as follows:

[0109] Where n represents a total of n energy sources participating in the optimization, C represents the preset cost threshold, σ i represents the cost ratio of the i-th energy source;

[0110] The real-time data of all energy types are used as a test set, and the historical data of the corresponding energy types are used as a training set. The initial scheduling optimization model is trained according to the training set to obtain a training model;

[0111] The test set is input into the first model to obtain the actual result, the actual result is compared with the predicted result to evaluate the deviation of the model index and adjust the model parameters for retraining to obtain the first model, which is the system algorithm part.

[0112] In this embodiment, the test set refers to a data set used to evaluate the performance of the trained model.

[0113] In this embodiment, the training set is a data set used to train a machine learning model.

[0114] In this embodiment, the operating cost refers to the energy consumption generated by operating a certain energy type under specific conditions.

[0115] In this embodiment, the actual result refers to the actual operating cost and output data of each energy type obtained after the model is run under specific conditions.

[0116] In this embodiment, the prediction result refers to the estimated operating cost and output of each energy type under specific conditions obtained by model calculation.

[0117] In this embodiment, the model indicators are used to compare the difference between the model prediction results and the actual results, and to measure the overall performance of the model, such as mean square error, mean absolute error, cost ratio, etc.

[0118] In this embodiment, the deviation refers to the difference between the model prediction result and the actual result.

[0119] The working principle and beneficial effects of the above technical solution are: by building a scheduling optimization framework with the goal of minimizing operating costs, using real-time and historical data for training and adjustment, improving energy utilization efficiency and scheduling accuracy, and achieving systematic energy management and cost control.

[0120] Embodiment 6:

[0121] Based on the above embodiment 5, the system packaging module includes:

[0122] Main functional units: Using energy Internet technology, various main functions are connected together through the http protocol, multi-data interaction is realized through the API interface, and added to the multi-energy collaborative optimization management system architecture to obtain the first system;

[0123] Packaging unit: deploys the first system in the test environment, integrates and tests the first system and verifies the correctness of the data flow. If there is a data flow anomaly, handles the location where the anomaly occurs and updates the first system to obtain the second system.

[0124] The second system is packaged based on the packaging tool and the dependencies to obtain a system packaging file.

[0125] In this embodiment, energy Internet technology is an emerging technical architecture that aims to achieve intelligent management and optimal allocation of energy resources through the deep integration of information and communication technology and energy technology.

[0126] In this embodiment, the http protocol is a protocol used to transmit data on the World Wide Web.

[0127] In this embodiment, the API interface is a set of rules and protocols for interaction and communication between different components.

[0128] In this embodiment, the integration test is used to verify whether the interaction and collaboration of various modules or components in the system after integration are normal.

[0129] In this embodiment, data flow refers to the process in which data flows from one location to another in a computer system, network, or application.

[0130] In this embodiment, the packaging tool and dependencies, the packaging tool is used to package the application and its dependencies into a deployable unit, which is an external library or framework required for the application to run, such as: database framework, web framework, etc.

[0131] The working principle and beneficial effects of the above technical solution are: integrating energy management functions through HTTP protocol and API interface, verifying the correctness of data flow and handling exceptions, and finally packaging and generating system files to ensure efficient integration, accuracy and flexible deployment, and support future functional expansion and system upgrades.

[0132] Embodiment 7:

[0133] Based on the above embodiment 1, the configuration module includes:

[0134] Configuration unit: transfers the system package file from the test environment to the actual environment, configures the system parameter items based on the actual environment, and then completes the installation and starts the multi-energy collaborative optimization management system in the actual environment;

[0135] Monitoring unit: monitors the operation log of key performance parameters of the multi-energy collaborative optimization management system in real time based on the system monitoring tool;

[0136] Maintenance unit: Centrally manages operation logs and evaluates system performance, modifies packaging in the test environment based on the location of performance anomalies, updates system versions, and deploys configurations to the actual environment.

[0137] In this embodiment, the system parameter items refer to variables and settings that need to be configured during the operation of the system, such as: host address, port, database name, user credentials and other information.

[0138] In this embodiment, the system monitoring tool is an application program for real-time tracking, analyzing and reporting system performance and operating status, such as Nagios, Zabbix, Grafana, etc.

[0139] In this embodiment, the operation log refers to various events, operations and status information recorded by the system during operation.

[0140] In this embodiment, system performance refers to the ability and efficiency of a system to complete tasks under specific conditions, including response time, throughput, resource utilization, etc.

[0141] The working principle and beneficial effects of the above technical solution are: the deployment and parameter configuration of system packaging files are realized through the configuration unit, the monitoring unit tracks key performance parameters in real time, and the maintenance unit centrally manages the operation log and performs system performance evaluation to ensure efficient operation, continuous improvement and stability of the system.

[0142] Embodiment 8:

[0143] like Figure 2 As shown, a multi-energy collaborative optimization management method provided by an embodiment of the present invention includes:

[0144] Step 1: Based on the target requirements, determine the energy objects of the system and configure sensors to obtain real-time data of all energy types;

[0145] Step 2: Design a multi-energy collaborative optimization management system architecture in the test environment and store real-time data of all energy types in a real-time database;

[0146] Step 3: Configure the initial model, train the initial model according to the real-time data of all energy types and the historical data of the corresponding energy types, and obtain the first model, which is the system algorithm part;

[0147] Step 4: Add the main functions to the multi-energy collaborative optimization management system architecture to obtain the first system, and package it to obtain a system package file;

[0148] Step 5: Configure the system package file to the actual environment and monitor the system's performance parameters for maintenance and updates.

[0149] The working principle and beneficial effects of the above technical solution are: through real-time data acquisition and model training, efficient energy management and optimized decision-making can be achieved, sustainable development can be supported, operating costs can be reduced, system performance can be improved, and resource utilization can be maximized.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-energy collaborative optimization management system, characterized in that: include: Demand module: Based on target demand, determine the energy objects of the multi-energy collaborative optimization management system, and configure sensors to obtain real-time data of all energy types; System design module: Design a multi-energy collaborative optimization management system architecture in the test environment and store real-time data of all energy types in a real-time database; Algorithm module: configures an initial model, trains the initial model according to the real-time data of all energy types and the historical data of the corresponding energy types, and obtains a first model, which is the system algorithm part; System packaging module: adding the main functions to the multi-energy collaborative optimization management system architecture to obtain the first system, and packaging to obtain the system packaging file; Configuration module: configures the system package files to the actual environment and monitors the performance parameters of the first system for maintenance and updates.

2. A multi-energy collaborative optimization management system according to claim 1, characterized in that: The demand module includes: Determine demand units: Determine all energy objects for system analysis based on pre-set target demand; Screening unit: Prioritize energy objects with energy saving potential greater than the national standard as the main monitoring objects.

3. A multi-energy collaborative optimization management system according to claim 2, characterized in that: The demand module includes: Acquisition and analysis unit: Determine the monitoring parameter type and parameter requirements based on the main monitoring objects; Sensor unit: Match the corresponding sensor according to the parameter type, determine the initial configuration parameters of the sensor according to the parameter requirements, configure all sensors to the specified installation location, and obtain real-time data of all energy types.

4. The multi-energy collaborative optimization management system according to claim 1 is characterized in that: The system design module includes: Architecture generation unit: Determine the system architecture mode according to the target requirements, and design the components of the multi-energy collaborative optimization management system, wherein the components include a function tree composed of main function components and sub-function components; Database unit: initializes the system database according to the preset standard database field table, and refines the fields based on the target requirements and generates different functional databases, all of which constitute the real-time database component; Storage unit: initializing the real-time data of all energy types acquired by the sensor to obtain first real-time data, and performing time standardization parameter corresponding processing on the real-time data of any energy type according to the standard time interval to obtain standard real-time data; Store standard real-time data for all energy types into a real-time database.

5. The multi-energy collaborative optimization management system according to claim 1 is characterized in that: The algorithm module comprises: Model unit: Construct a collaborative optimization objective function, with the goal of minimizing the operating cost of any energy type, and construct a single scheduling model as follows: Among them, C i represents the total operating cost of the i-th energy source, A i0 represents the operating cost before energy optimization, A i1 Indicates that there is only a single operating parameter characteristic value of the energy source, ε i represents the parameter cost conversion coefficient of the i-th energy source, ρ i represents the operating error coefficient of the i-th energy source; Then the initial dispatch optimization model for all energy sources is constructed as follows: Where n represents a total of n energy sources participating in the optimization, C represents the preset cost threshold, σ i represents the cost ratio of the i-th energy source; The real-time data of all energy types are used as a test set, and the historical data of the corresponding energy types are used as a training set. The initial scheduling optimization model is trained according to the training set to obtain a training model; The test set is input into the first model to obtain the actual result, the actual result is compared with the predicted result to evaluate the deviation of the model index and adjust the model parameters for retraining to obtain the first model, which is the system algorithm part.

6. A multi-energy collaborative optimization management system according to claim 5, characterized in that: The system packaging module includes: Main functional units: Using energy Internet technology, various main functions are connected together through the http protocol, multi-data interaction is realized through the API interface, and added to the multi-energy collaborative optimization management system architecture to obtain the first system; Packaging unit: deploys the first system in the test environment, integrates and tests the first system and verifies the correctness of the data flow. If there is a data flow anomaly, it handles the location where the anomaly occurs and updates the first system to obtain the second system. The second system is packaged based on the packaging tool and the dependencies to obtain a system packaging file.

7. The multi-energy collaborative optimization management system according to claim 1 is characterized in that: The configuration module includes: Configuration unit: transfers the system package file from the test environment to the actual environment, configures the system parameter items based on the actual environment, and then completes the installation and starts the multi-energy collaborative optimization management system in the actual environment; Monitoring unit: monitors the operation log of key performance parameters of the multi-energy collaborative optimization management system in real time based on the system monitoring tool; Maintenance unit: Centrally manages operation logs and evaluates system performance, modifies packaging in the test environment based on the location of performance anomalies, updates system versions, and deploys configurations to the actual environment.

8. A multi-energy collaborative optimization management method, characterized in that: include: Step 1: Based on the target requirements, determine the energy objects of the system and configure sensors to obtain real-time data of all energy types; Step 2: Design a multi-energy collaborative optimization management system architecture in the test environment and store real-time data of all energy types in a real-time database; Step 3: Configure the initial model, train the initial model according to the real-time data of all energy types and the historical data of the corresponding energy types, and obtain the first model, which is the system algorithm part; Step 4: Add the main functions to the multi-energy collaborative optimization management system architecture to obtain the first system, and package it to obtain a system package file; Step 5: Configure the system package file to the actual environment and monitor the system's performance parameters for maintenance and updates.

Images