Carbon reduction and consumption reduction optimization method and device, electronic equipment and storage medium

Abstract

The invention discloses a carbon reduction and consumption reduction optimization method and device, electronic equipment and a storage medium, and relates to the field of carbon reduction and consumption reduction. The method comprises the following steps: acquiring energy carbon data of a carbon reduction and consumption reduction main body; analyzing the optimization space of the energy carbon data based on a preset classification dimension, and determining a first optimization analysis result of the energy carbon data; based on at least one of a configured optimization algorithm, the first optimization analysis result and a preset classification dimension, constructing an optimization grid in the problem space; and based on the characteristics of the energy-carbon data corresponding to each optimization grid and the optimization target corresponding to each optimization grid, deploying an optimization algorithm matched with the optimization grid, and optimizing the energy-carbon data corresponding to the corresponding optimization grid through the optimization algorithm. According to the method, a complex system optimization problem can be simplified, system-level optimization is realized through combination of a plurality of basic algorithms, efficient optimization and solution of the complex problem are further realized, and the optimization effect of reducing carbon and reducing consumption can be greatly improved.

Description

Technical Field

[0001] The present application relates to the technical field of carbon reduction and energy consumption reduction, and specifically to a carbon reduction and energy consumption reduction optimization method, device, electronic device and storage medium. Background Art

[0002] Carbon reduction and consumption reduction is a complex and long-term task. In order to meet the challenges of carbon reduction and consumption reduction, it requires the concerted efforts of multiple parties, and a digital and intelligent system is needed as a collaborative platform to coordinate and optimize the management of carbon reduction and consumption reduction work to meet multi-level and multi-dimensional needs, which is conducive to the management and optimization of carbon reduction and consumption reduction tasks throughout the life cycle. However, since carbon reduction and consumption reduction tasks involve all aspects of the main business activities and are relatively complex, carbon reduction and consumption reduction optimization systems are usually unable to accurately analyze such complex multi-dimensional system optimization problems, resulting in relatively poor optimization effects of carbon reduction and consumption reduction. Summary of the invention

[0003] The embodiments of the present application provide a carbon reduction and energy saving optimization method, device, electronic device and storage medium to improve the optimization effect of carbon reduction and energy saving.

[0004] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0005] In a first aspect, a method for optimizing carbon reduction and energy consumption reduction is provided, comprising:

[0006] Obtain energy and carbon data of entities that reduce carbon emissions;

[0007] Analyze the optimization space of the energy-carbon data based on a preset classification dimension to determine a first optimization analysis result of the energy-carbon data;

[0008] Based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions, constructing an optimization grid in the problem space;

[0009] Based on the characteristics of the energy-carbon data corresponding to each of the optimized grids and the optimization target corresponding to each of the optimized grids, an optimization algorithm adapted to the optimized grid is deployed, and the energy-carbon data corresponding to the corresponding optimized grid is optimized by the optimization algorithm.

[0010] In some embodiments, constructing an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions includes:

[0011] Determine a grid segmentation parameter based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions;

[0012] The problem space is segmented based on the grid segmentation parameters to obtain the optimized grid.

[0013] In some embodiments, segmenting the problem space based on the grid segmentation parameter to obtain the optimized grid includes:

[0014] Based on the grid segmentation parameters, the problem space is segmented once using a preset grid segmentation algorithm or calling a segmentation model from a configured model library to obtain multiple candidate grids;

[0015] If the candidate grid does not meet the preset segmentation stop condition, the candidate grid is continuously segmented using the grid segmentation algorithm or the segmentation model until each candidate grid obtained by segmentation meets the preset segmentation stop condition, and each candidate grid is determined as the optimized grid.

[0016] In some embodiments, the preset segmentation stop condition includes that the data can be optimized by an available algorithm and / or the data feature meets the target condition; determining that the candidate grid meets the preset segmentation stop condition includes:

[0017] If the energy-carbon data corresponding to the candidate grid can be optimized by an available algorithm and / or the characteristics of the energy-carbon data corresponding to the candidate grid meet the target condition, it is determined that the candidate grid meets the preset segmentation stop condition.

[0018] In some embodiments, the step of adjusting an optimization algorithm adapted to the optimization grid includes:

[0019] dispatching an optimization algorithm adapted to the optimization grid from a configured algorithm library;

[0020] If the scheduling is successful, the parameters of the optimization algorithm are configured;

[0021] If the scheduling fails, a demand algorithm is trained based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, and the demand algorithm is stored in the configured algorithm library.

[0022] In some embodiments, the training of a demand algorithm based on the energy-carbon data corresponding to the optimization grid and the optimization target corresponding to the optimization grid includes:

[0023] Establishing an optimization problem model based on the energy-carbon data corresponding to the optimization grid and the optimization target corresponding to the optimization grid;

[0024] Collecting training data corresponding to the optimization problem model, and using the training data to train and verify the optimization problem model;

[0025] The optimization problem model that has completed training is determined as the required algorithm.

[0026] In some embodiments, analyzing the optimization space of the energy-carbon data based on a preset classification dimension to determine a first optimization analysis result of the energy-carbon data includes:

[0027] Based on the preset classification dimension, the energy carbon data is divided into multiple groups of sub-data;

[0028] The optimization space of each group of the sub-data is analyzed to determine the first optimization analysis result of the energy-carbon data.

[0029] In some embodiments, analyzing the optimization space of each group of sub-data includes:

[0030] For any group of the sub-data, based on the corresponding group of the sub-data and the related group of the sub-data, analyzing the optimization space of the corresponding group of the sub-data, wherein the related group of the sub-data is configured to represent the sub-data related to the energy carbon type of the corresponding group of the sub-data;

[0031] and / or, analyzing the optimization space of the sub-data of the corresponding group based on the sub-data of the corresponding group and historical data;

[0032] and / or, analyzing the optimization space of the sub-data of the corresponding group based on the data of each link in the life cycle of the sub-data of the corresponding group;

[0033] And / or, based on the corresponding group of sub-data and corresponding benchmarks, analyzing the optimization space of the corresponding group of sub-data.

[0034] In some embodiments, the method further comprises:

[0035] If the optimization grid meets the update conditions, the optimization grid and / or the configured optimization algorithm are updated, and the update conditions include at least one of the following: the deviation between the optimization result of the energy-carbon data corresponding to the optimization grid and the corresponding optimization target exceeds a first preset threshold, the characteristic change of the energy-carbon data corresponding to the optimization grid exceeds a second preset threshold, and the preset classification dimension changes.

[0036] In some embodiments, the obtaining of energy and carbon data of a carbon reduction and consumption reduction subject includes:

[0037] Collecting operational data of the carbon reduction and consumption reduction entities;

[0038] The operation data is preprocessed, and the preprocessed data is analyzed and mined to obtain the energy carbon data.

[0039] In some embodiments, the preset classification dimensions include at least one of an industry type dimension, an organization dimension, a department dimension, a region dimension, a process dimension, an equipment dimension, and a time dimension.

[0040] In a second aspect, a carbon reduction and consumption reduction optimization device is provided, comprising:

[0041] Data collection module, used to obtain energy and carbon data of carbon reduction and consumption reduction entities;

[0042] An optimization analysis module, used to analyze the optimization space of the energy-carbon data based on a preset classification dimension, and determine a first optimization analysis result of the energy-carbon data;

[0043] A grid segmentation module, configured to construct an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions;

[0044] The algorithm scheduling module is used to allocate an optimization algorithm adapted to the optimization grid based on the characteristics of the energy-carbon data corresponding to each of the optimization grids and the optimization target corresponding to each of the optimization grids, and optimize the energy-carbon data corresponding to the corresponding optimization grid through the optimization algorithm.

[0045] In some embodiments, the grid segmentation module is also connected to a configured model library, the model library is used to store segmentation models, and the grid segmentation module is used to search for the segmentation model from the model library.

[0046] In some embodiments, the algorithm scheduling module is also connected to a configured algorithm library, and the algorithm library is used to store the optimization algorithm.

[0047] In some embodiments, the apparatus further comprises:

[0048] An algorithm training module, the algorithm training module is respectively connected to the data acquisition module, the grid segmentation module and the algorithm scheduling module, and is used to train a demand algorithm based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, so that the algorithm scheduling module optimizes the energy-carbon data corresponding to the optimized grid through the demand algorithm.

[0049] According to a third aspect, an electronic device is provided, the electronic device comprising:

[0050] at least one processor; and a memory communicatively coupled to the at least one processor;

[0051] In which, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the carbon reduction and consumption reduction optimization method described in any one of the first aspects, or so that the processor can configure the carbon reduction and consumption reduction optimization device described in any one of the second aspects.

[0052] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable a processor to implement the carbon reduction and consumption reduction optimization method described in any one of the first aspect when executed, or the computer instructions are used to enable a processor to configure the carbon reduction and consumption reduction optimization device described in any one of the second aspect.

[0053] The present application discloses an optimization method for reducing carbon and reducing consumption, comprising: obtaining energy-carbon data of a subject of reducing carbon and reducing consumption; analyzing the optimization space of energy-carbon data based on a preset classification dimension, and determining a first optimization analysis result of the energy-carbon data; constructing an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions; deploying an optimization algorithm adapted to the optimization grid based on the characteristics of the energy-carbon data corresponding to each optimization grid and the optimization target corresponding to each optimization grid, and optimizing the energy-carbon data corresponding to the corresponding optimization grid through the optimization algorithm. The optimization method for reducing carbon and reducing consumption provided by the present application can divide the problem space into multiple optimization grids, and call an adapted optimization algorithm to find an optimization strategy in combination with the energy-carbon data corresponding to the optimization grid and the optimization target, so as to simplify complex system optimization problems, realize system-level optimization through a combination of multiple basic algorithms, and then realize efficient optimization and solution of complex problems, which can greatly improve the optimization effect of reducing carbon and reducing consumption.

[0054] A carbon reduction and consumption reduction optimization device applied in the present invention can simplify complex system optimization problems, realize system-level optimization through the combination of multiple basic algorithms, and then realize efficient optimization and solution of complex problems, which can greatly improve the optimization effect of carbon reduction and consumption reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 A schematic diagram of an overall process of the carbon reduction and energy consumption reduction optimization method according to an embodiment of the present application;

[0057] Figure 2An example schematic diagram of an optimized grid according to an embodiment of the present application;

[0058] Figure 3 A schematic diagram of an example flow chart of an optimized grid segmentation method according to an embodiment of the present application;

[0059] Figure 4 Another exemplary flow chart of the optimized grid segmentation method according to an embodiment of the present application;

[0060] Figure 5 It is a schematic diagram of an example flow of an optimization algorithm adapted to the optimized grid in the embodiment of the present application;

[0061] Figure 6 Another overall flow chart of the carbon reduction and energy saving optimization method according to an embodiment of the present application;

[0062] Figure 7 This is a schematic diagram of the overall structure of the carbon reduction and consumption reduction optimization device according to an embodiment of the present application;

[0063] Figure 8 This is a schematic diagram of an exemplary structure of a carbon reduction and energy consumption reduction optimization device according to an embodiment of the present application;

[0064] Fig. 9 This is another exemplary structural schematic diagram of the carbon reduction and consumption reduction optimization device according to an embodiment of the present application;

[0065] Fig.10 This is another exemplary structural diagram of the carbon reduction and consumption reduction optimization device according to an embodiment of the present application;

[0066] Fig.11 A schematic diagram of the structure of an electronic device according to an embodiment of the present application;

[0067] Reference numerals:

[0068] 11-processor; 12-read-only memory; 13-random access memory; 14-bus; 15-input / output interface; 16-input unit; 17-output unit; 18-storage unit; 19-communication unit; 701-data acquisition module; 702-optimization and analysis module; 703-grid segmentation module; 704-algorithm scheduling module; 705-model library; 706-algorithm library; 707-algorithm training module. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0070] In the description of the present application, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the present application, "multiple" means two or more, and at least one means one, two or more, unless otherwise clearly and specifically defined.

[0071] The embodiment of the present application provides a carbon reduction and consumption reduction optimization method. The method can be performed by a carbon reduction and consumption reduction optimization device, which can be implemented in the form of hardware and / or software, and the carbon reduction and consumption reduction optimization device can be configured in an electronic device.

[0072] This method can be applied to carbon reduction and consumption reduction systems such as zero-carbon systems, virtual power plant systems, integrated energy systems, photovoltaic storage and charging systems, and energy carbon management systems. This method can also be applied to various scenarios of energy carbon solutions, such as: energy carbon planning, value chain net zero emission planning, paths and plans to achieve energy carbon planning, plans to deal with carbon tariffs, supply chain carbon management plans, plans to reduce carbon emissions, plans to reduce carbon footprint, etc. This method can also be applied to energy carbon management in a variety of scenarios (such as factories, parks, hospitals, schools, transportation, buildings, etc.), such as: carbon inventory, energy management, energy efficiency management, organizational carbon management, carbon footprint management, supply chain carbon management, etc.

[0073] Among them, the energy carbon management system uses a digital and intelligent system as a collaborative platform to coordinate and optimize management to meet the various energy carbon tasks and the multi-level and multi-dimensional needs of all parties (including but not limited to carbon consulting, carbon verification and certification, carbon reduction management, carbon asset operation management, energy asset operation management, green financial services, etc.). In order to meet the energy carbon challenge, all professions and positions in various fields need to work together.

[0074] The zero-carbon system includes one or more carbon emission units and one or more carbon reduction units (including carbon offset) within a range. It achieves low carbon or even zero carbon within the above range and a certain time period by optimizing carbon emission management and carbon reduction operations.

[0075] The virtual power plant system is a power coordination management system that uses advanced information and communication technologies and software systems to achieve the aggregation and coordinated optimization of distributed energy resources (DER) such as distributed generation (DG), energy storage systems, controllable loads, and electric vehicles, so as to participate in the power market and power grid operation as a special power plant. The core of the concept of virtual power plant can be summarized as "communication" and "aggregation". Virtual power plants mainly include coordinated control technology, smart metering technology, and information and communication technology. Virtual power plants can aggregate distributed energy to participate in the operation of the power market and ancillary service market, and provide management and ancillary services for distribution networks and transmission networks. Virtual power plants can serve as "positive power plants" to supply power and peak load to the system, and can also serve as "negative power plants" to respond to the load side to cooperate with the system to fill the valley. When electricity is in short supply, virtual power plants can play the role of positive power plants, aggregate and optimize distributed new energy, energy storage systems, electric vehicles and other distributed energy to supply power to the power grid from the supply side to meet the load demand of traditional electricity. At the same time, they can also play the role of negative power plants, coordinate the peak load of controllable loads from the demand side, and alleviate the problem of tight power supply and demand.

[0076] An integrated energy system refers to a new integrated energy system that uses advanced physical information technology and innovative management models to integrate multiple energy sources such as coal, oil, natural gas, electricity, and heat energy in a certain area, realize coordinated planning, optimized operation, collaborative management, interactive response, and mutual complementation among multiple heterogeneous energy subsystems, and effectively improve energy utilization efficiency and promote sustainable energy development while meeting the diversified energy demand within the system. An integrated energy system specifically refers to an integrated energy production, supply, and marketing system formed by organically coordinating and optimizing the generation, transmission, and distribution (energy network), conversion, storage, and consumption of energy during the planning, construction, and operation process. It is mainly composed of energy supply networks (such as power supply, gas supply, cooling / heat supply, etc.), energy exchange links (such as generator sets, boilers, air conditioners, heat pumps, etc.), energy storage links (electricity storage, gas storage, heat storage, cooling storage, etc.), terminal integrated energy supply and use units (such as microgrids), and a large number of terminal users.

[0077] The following is an explanation of relevant terms in the field of carbon reduction and energy consumption reduction.

[0078] Among them, product carbon footprint is the statistics of all greenhouse gas emissions generated by a product at each stage of its life cycle. There are two main carbon emission calculation methods with different boundaries: "from cradle to gate" and "from cradle to grave". The former refers to the carbon emissions generated from resource extraction, processing, manufacturing to product manufacturing and delivery, while the latter also includes the carbon emissions generated by the entire life cycle of product distribution, use, maintenance, etc. to the final waste treatment stage. Product carbon labeling is to mark the amount of carbon dioxide consumed by a product from raw material procurement, transportation, production to sales with a quantitative index on the product packaging, promote low-carbon emission technology, and inform consumers of the carbon information of the product in the form of labels. Environmental Product Declaration (EPD) is a standardized and standardized Type III environmental declaration based on Life Cycle Assessment (LCA). Through an effective EPD management mechanism, countries, regions and industries can increase the control of corporate environmental information, improve the transparency and traceability of product environmental impacts, and increase the reliability of data and calculation models. EPD, also known as Type III Environmental Declaration, is a systematic document that has been audited and registered by a third party. It provides transparent and comparable information on the impact of the product life cycle on the environment. Such statements are prepared and reviewed in accordance with the international standard ISO 14025 and are based on the results of life cycle assessments in accordance with ISO 14040 and ISO 14044. Net-zero emission refers to the balance between greenhouse gas emissions and greenhouse gas removals caused by human activities over a certain period of time. Carbon neutrality refers to the balance between carbon dioxide emissions caused by human activities and the amount of carbon dioxide absorbed and removed through technologies such as CCUS and carbon sinks over a certain period of time. Climate neutrality means that human activities have no net impact on the climate system, and it is necessary to consider the balance between greenhouse gas emissions, removals and physical effects in specific areas.

[0079] Since carbon reduction and consumption reduction is a long-term task that requires long-term continuous operation and management, the carbon reduction and consumption reduction system needs to manage and optimize the carbon reduction and consumption reduction tasks throughout their life cycle. However, carbon reduction and consumption reduction tasks involve all aspects of the main business activities and are relatively complex. When faced with the optimization needs of complex problems, the optimization needs of the entire life cycle of carbon reduction and consumption reduction tasks, and the needs of constantly adapting to the rapid development and changes of carbon reduction and consumption reduction policies, standards, regulations, and technologies, and continuous optimization, the carbon reduction and consumption reduction optimization system is usually unable to accurately analyze such complex multi-dimensional system optimization problems, resulting in poor actual carbon reduction and consumption reduction optimization effects of the optimization strategies generated by the carbon reduction and consumption reduction system, and the value of the algorithm is not fully utilized.

[0080] In view of this, an embodiment of the present application provides an optimization method for carbon reduction and consumption reduction, which divides the complex system optimization problem into discrete optimization grids, combines the energy-carbon data corresponding to the optimization grids and the optimization objectives to call an adaptive optimization algorithm to find an optimization strategy, thereby simplifying the complex system optimization problem, and achieving system-level optimization through a combination of multiple basic algorithms, thereby achieving efficient optimization and solution of complex problems, thereby solving at least part of the above-mentioned technical problems.

[0081] See also Figure 1 , Figure 1 This is a schematic diagram of an overall process of the carbon reduction and consumption reduction optimization method of the embodiment of the present application. The carbon reduction and consumption reduction optimization method includes the following steps:

[0082] Step 101: Obtain energy and carbon data of the carbon reduction and consumption reduction subject.

[0083] Specifically, the carbon reduction and consumption reduction subjects may include all kinds of organizations, enterprises, households and individuals that need to carry out carbon reduction and consumption reduction work. Energy carbon data refers to data related to energy consumption and carbon emissions. Exemplarily, energy carbon data may include at least one of external policy data, regulatory data, standard data, industry data, and internal business field data, equipment data, energy data, and carbon emission data.

[0084] In some embodiments, the energy carbon data may be obtained by the following steps:

[0085] Step 1: Collect operational data of entities involved in carbon reduction and energy consumption reduction.

[0086] Specifically, operational data may be data on all aspects of the operation of the entity involved in carbon reduction and energy consumption reduction.

[0087] In some examples, operational data may be collected through at least one of sensors, monitoring equipment, data collection platforms, database queries, and file imports.

[0088] In other words, after determining the specific type and source of the mobile phone's operational data, it can be obtained through sensors, monitoring equipment, data collection platforms, database queries, file imports, etc.

[0089] Step 2: Preprocess the operational data and perform data analysis and mining on the preprocessed data to obtain energy and carbon data.

[0090] Specifically, the data analysis and mining techniques can be set according to the specific data. For example, statistical analysis, machine learning and other methods can be used to extract features, which is not specifically limited in the embodiments of the present application.

[0091] Exemplarily, preprocessing may include integration, cleaning and normalization operations, so as to ensure the accuracy and consistency of the data.

[0092] Step 102: Analyze the optimization space of the energy-carbon data based on the preset classification dimension to determine the first optimization analysis result of the energy-carbon data.

[0093] Specifically, the preset classification dimensions can be set based on the business domain, different scenarios and time of the carbon reduction and consumption reduction subject.

[0094] In some examples, the preset classification dimensions may include at least one of an industry type dimension, an organization dimension, a department dimension, a region dimension, a process dimension, an equipment dimension, and a time dimension.

[0095] In some embodiments, step 102 may be implemented by:

[0096] Step 1: Divide the energy carbon data into multiple groups of sub-data based on the preset classification dimensions.

[0097] For example, energy carbon data can be grouped according to factors such as industry type, department, region, product, process flow, equipment type, etc.

[0098] Step 2: Analyze the optimization space of each group of sub-data and determine the first optimization analysis result of the energy-carbon data.

[0099] Specifically, the optimization space is used to represent aspects that can be optimized and methods of improvement. The optimization space can be the optimization space of at least one of energy efficiency, carbon efficiency improvement, energy saving, carbon reduction, and fee reduction. Analysis of the optimization space usually requires a combination of data analysis, domain knowledge, and professional technology. In other words, the first optimization analysis result includes the optimization space of energy and carbon data in different business domains, different scenarios, and different time dimensions.

[0100] In some examples, the optimization space of each group of sub-data can be specifically analyzed by the following steps:

[0101] For any group of sub-data, based on the corresponding group sub-data and the related group sub-data, the optimization space of the corresponding group sub-data is analyzed, and the related group sub-data is configured to represent the sub-data related to the energy carbon type of the corresponding group sub-data. And / or, based on the corresponding group sub-data and historical data, the optimization space of the corresponding group sub-data is analyzed. And / or, based on the data of each link in the life cycle of the corresponding group sub-data, the optimization space of the corresponding group sub-data is analyzed. And / or, based on the corresponding group sub-data and the corresponding benchmark, the optimization space of the corresponding group sub-data is analyzed.

[0102] Specifically, each group of sub-data after segmentation based on business domains and scenarios can be normalized, for example, to obtain energy consumption per unit of output, carbon emissions per unit of output, energy consumption per unit of output value, carbon emissions per unit of output value, etc., and then the sub-data of similar industry types, similar departments, similar regions, similar products, similar production lines or similar equipment can be compared horizontally to obtain corresponding benchmarks, such as taking the lowest energy consumption per unit of output in the horizontal comparison as a benchmark, etc. Finally, the optimization space of each group of sub-data can be obtained based on the difference between each group of sub-data and the corresponding benchmark, and then the second optimization analysis result of each group of sub-data can be determined.

[0103] Each group of sub-data can also be compared with historical data. For example, the energy efficiency data of the equipment in the past three years can be compared with the current energy efficiency data to obtain the corresponding benchmark. Finally, the optimization space of each group of sub-data can be obtained based on the difference between each group of sub-data and the corresponding benchmark, and then the second optimization analysis result of each group of sub-data can be determined.

[0104] It is also possible to collect energy consumption comparisons of each process link based on the data of each link in the life cycle of each group of sub-data, such as the energy consumption of the process flow, to obtain the corresponding benchmark, and finally obtain the optimization space based on the difference between each group of sub-data and the corresponding benchmark, and then determine the second optimization analysis result of each group of sub-data.

[0105] It is also possible to directly obtain the benchmark of each group of sub-data, and then obtain the optimization space of each group of sub-data according to the difference between each group of sub-data and the corresponding benchmark, and then determine the second optimization analysis result of each group of sub-data.

[0106] In addition, other methods can also be used to analyze the optimization space of each group of sub-data. For example, different analysis methods can be used for the optimization spaces of different groups of sub-data, such as horizontally comparing any group of sub-data with related groups of sub-data to obtain the corresponding benchmark of the group of sub-data, and obtaining the optimization space based on the difference between the group of sub-data and the corresponding benchmark, and then determining the second optimization analysis result of the group of sub-data, comparing another group of sub-data with historical data to obtain the corresponding benchmark, and then obtaining the optimization space of another group of sub-data, obtaining the corresponding benchmark based on the data of each link in the life cycle of another group of sub-data, and then obtaining the optimization space of another group of sub-data, and directly obtaining the corresponding benchmark of another group of sub-data, and then obtaining the optimization space of another group of sub-data, etc. That is to say, each group of sub-data can select the corresponding optimization space analysis method according to the specific situation, and the optimization space analysis methods between different groups of sub-data can be the same or different, and the embodiments of the present application do not make specific limitations on this.

[0107] Through the above scheme, different parts or operations of the carbon reduction and consumption reduction subject can be distinguished, and targeted analysis can be carried out according to their characteristics, so as to facilitate more accurate optimization in the future.

[0108] Step 103: construct an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions.

[0109] Specifically, the problem space refers to the set of all possible states, variables, and factors involved in solving optimization problems. Optimization problems can come from the overall plan and annual goals of carbon reduction and consumption reduction. For example, if the operating goals for 2028 have been planned, and the annual carbon reduction goals can be known based on the benchmark, then the optimization problem can be how to optimize the annual overall carbon reduction to meet the carbon reduction goals.

[0110] According to the characteristics and constraints of the optimization problem, an optimization grid can be constructed in the problem space. The characteristics of the optimization problem refer to the energy consumption characteristics, and the constraints refer to the restrictions or limitations on variables or systems in specific problems or situations, such as energy network capacity restrictions, equipment rated power restrictions, budget restrictions or regulatory requirements. The optimization grid is a grid structure established on one or more dimensions, such as industry type dimension, organizational dimension, departmental dimension, regional dimension, process dimension, equipment dimension, time dimension, etc., which is used to coordinate optimization activities. In the grid, you can set optimization goals, assign optimization tasks, collect data, etc. For example, if the optimization grids correspond to air compressors and lighting equipment respectively, then the optimization goals can be to reduce the energy consumption of air compressors by a certain proportion, and to reduce the energy consumption of lighting equipment by a certain proportion. The optimization grid can be a data structure or algorithm used to represent the combination of different optimization segmentation schemes and evaluate their effects.

[0111] The configured optimization algorithms may be stored in an algorithm library, in which a plurality of optimization algorithms may be pre-stored. Different optimization algorithms are used to perform different optimization operations.

[0112] In some embodiments, through data sharing, communication and collaboration, data can be exchanged between optimization grids, thereby helping to improve the overall optimization effect. A data sharing and communication mechanism can also be established within the optimization grid, for example, cloud platforms, Internet of Things technologies, etc. can be used to achieve real-time data sharing and communication, which helps to promote information flow and communication.

[0113] In some embodiments, step 103 may be implemented by:

[0114] Step 1: Determine a grid segmentation parameter based on a configured optimization algorithm, a first optimization analysis result, and at least one of a preset classification dimension.

[0115] Exemplarily, the grid segmentation parameters are used to characterize the segmentation method for establishing the optimized grid. According to the first optimization analysis result, the preset classification dimensions can be further subdivided or merged to obtain the grid segmentation parameters, and the grid segmentation parameters can also be determined in combination with the data type required by the configured optimization algorithm. It is understandable that the configuration of the grid will affect the performance of the algorithm, so a reasonable segmentation of the optimized grid helps to better exert the performance of the algorithm.

[0116] Step 2: divide the problem space based on the grid segmentation parameters to obtain the optimized grid.

[0117] See also Figure 2 , Figure 2 This is an example schematic diagram of an optimized grid according to an embodiment of the present application. In some examples, the optimized grid can be obtained by segmentation in the following manner:

[0118] Based on the grid segmentation parameters, the problem space Q is segmented once using the preset grid segmentation algorithm or calling the segmentation model from the configured model library to obtain multiple candidate grids Q1~Q m If the alternative grid Q i (i is a positive integer, and 1≤i≤m) If the preset segmentation stop condition is not met, the grid segmentation algorithm or segmentation model will continue to be used to segment the candidate grid Q i Divide and obtain the candidate grid Q i.1 ~Q i.n , and continue to determine the candidate grid Q i.1 ~Q i.n Whether the preset segmentation stop condition is met, the iteration cycle continues until each candidate grid Q obtained by segmentation i.1.1 ~Q i.n.k All the candidate grids Q i.1.1 ~Q i.n.k Determine the optimized grid. In this way, by gradually dividing from the whole to the local, the optimization problem of a complex large system can be divided into discrete grids, which is convenient for subsequent efficient optimization solutions.

[0119] In some examples, the preset segmentation stop condition includes that the data can be optimized by an algorithm and / or the data features meet the target condition. Then, if the energy carbon data corresponding to the candidate grid can be optimized by an algorithm and / or the features of the energy carbon data corresponding to the candidate grid meet the target condition, it is determined that the candidate grid meets the preset segmentation stop condition.

[0120] Specifically, to determine whether the energy and carbon data corresponding to the candidate grid can be optimized by the algorithm, factors such as the objective function of the problem, feasible solution space, computability, and data volume and complexity can be considered. The characteristics of the data refer to the attributes, characteristics or descriptions of the data itself. The target conditions can be set from the aspects of achieving a predetermined goal, achieving a feasible solution, achieving a computing resource limit, and achieving a time limit. The embodiments of the present application do not specifically limit this.

[0121] See also Figure 3 , Figure 3 The following is a flow chart of an example of an optimized grid segmentation method according to an embodiment of the present application. For example, first, the grid segmentation parameters are initialized, and then the problem space is segmented once using a preset grid segmentation algorithm to obtain multiple candidate grids, and then each candidate grid is segmented multiple times using the preset grid segmentation algorithm until each candidate grid can be optimized using the algorithm to obtain each optimized grid after segmentation.

[0122] See also Figure 4 , Figure 4 Another example flow chart of the optimized grid segmentation method of the embodiment of the present application. Exemplarily, first, the grid segmentation parameters are initialized, and then the segmentation model is called from the configured model library to segment the problem space once to obtain multiple candidate grids, and then the segmentation model is used to continue to segment each candidate grid multiple times until the characteristics of the data corresponding to each candidate grid meet the target conditions, and each optimized grid after subdivision is obtained.

[0123] It is understandable that the above-mentioned various preset segmentation stop conditions and segmentation tools can be used flexibly in combination with each other, that is, different candidate grids can select different segmentation methods according to the actual characteristics of the data in the grid, and the embodiments of the present application do not make specific limitations on this.

[0124] Through the above solution, we can deconstruct the problem from beginning to end, and then seek optimization strategies based on the collected data corresponding to the segmented network. This will make the optimization more targeted and easier to implement.

[0125] Step 104: Based on the characteristics of the energy-carbon data corresponding to each optimized grid and the optimization target corresponding to each optimized grid, an optimization algorithm adapted to the optimized grid is deployed, and the energy-carbon data corresponding to the corresponding optimized grid is optimized by the optimization algorithm.

[0126] Specifically, the energy-carbon data corresponding to the corresponding optimization grid is optimized by the optimization algorithm, which means that the data collected in the optimization grid is used for data-driven optimization. By analyzing the energy-carbon data of different organizations or regions in the grid, existing problems and optimization opportunities are identified, and corresponding optimization strategies and measures are formulated to obtain the optimal value that meets the allocated optimization objectives.

[0127] It is understandable that after the optimization grid is constructed, real-time data from the optimization grid can still be continuously collected, and the data can be cleaned, processed and converted. In other words, the acquisition of energy carbon data in the embodiment of the present application is real-time and continuous.

[0128] See also Figure 5 , Figure 5 This is an example flow chart of an optimization algorithm adapted to the optimized grid in the embodiments of the present application. In some embodiments, the optimization algorithm adapted to the optimized grid can be implemented by the following steps:

[0129] Step 1: dispatch an optimization algorithm that is compatible with the optimization grid from the configured algorithm library.

[0130] Specifically, first, the optimization tasks and constraints need to be clearly defined. The optimization task refers to the indicator or goal that needs to be optimized. According to the actual situation, single-objective optimization or multi-objective optimization can be defined, such as minimizing energy consumption or reducing carbon emissions. At the same time, possible constraints also need to be considered. Then, the optimization tasks are allocated according to business needs and optimization grid design. According to the characteristics and capabilities of each unit in the grid, the optimization tasks are reasonably allocated to each unit, and they work together to achieve the optimization goals. Then, according to specific problems and needs, select appropriate optimization algorithms from the algorithm library. For example: light storage and charging optimization algorithm, demand response algorithm, demand optimization algorithm, air compression optimization algorithm, cooling and heating optimization algorithm, office lighting algorithm, etc. Each type of algorithm has one or more algorithms to adapt to different business areas, different scenarios, different working conditions, and different times. For example: air compressor low load energy saving algorithm, air compressor medium load energy saving algorithm, air compressor high load energy saving algorithm. These algorithms can find the optimal solution through search, iteration, evolution, etc. Finally, check whether the scheduling is successful.

[0131] Step 2: If the scheduling is successful, configure the parameters of the optimization algorithm.

[0132] Specifically, configuration parameters refer to setting appropriate parameters for the selected optimization algorithm, such as: grid electricity price, photovoltaic grid-connected electricity price, carbon market price, adjustable resources, adjustable capacity, etc. Adjustment of these parameters will affect the performance and operation mode of the algorithm and need to be optimized according to actual conditions.

[0133] Step three: if the scheduling fails, the demand algorithm is trained based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, and the demand algorithm is stored in the configured algorithm library.

[0134] In some examples, algorithm training can be performed according to the following steps:

[0135] The first step is to establish an optimization problem model based on the energy-carbon data corresponding to the optimization grid and the optimization target corresponding to the optimization grid.

[0136] Specifically, we can choose the appropriate optimization model structure according to the characteristics of the problem, such as neural network, decision tree, operations optimization, etc. We can transform the optimization objectives and constraints into mathematical models and use historical data to build the model. We can also transform the optimization problem into a loss function minimization problem to measure the gap between the model output and the true value.

[0137] The second step is to collect the training data corresponding to the optimization problem model, and use the training data to train and verify the optimization problem model.

[0138] Specifically, data related to the optimization problem corresponding to the optimization grid can be collected, including historical data and real-time data, such as resource utilization, performance indicators, constraints, production plans and operation data, personnel scheduling and execution data, equipment data, energy consumption data, carbon emission data, production indicator data, optimization tasks and execution data, etc., and the input features and target variables in the data used for training can also be determined at the same time.

[0139] During the training process, the model parameters are optimized using the training data, and the model parameters are continuously adjusted to find the optimal solution. This may involve back propagation algorithms, gradient descent, random search, etc. You can also choose a suitable model optimization algorithm based on the characteristics of the problem, such as particle swarm optimization, gradient descent, genetic algorithm, simulated annealing, etc. Depending on the specific situation, the algorithm can also be improved and customized to enhance its adaptability and performance.

[0140] After training, the trained model is evaluated using validation sets or cross-validation techniques to ensure its generalization ability on unknown data. The model parameters are tuned based on the evaluation results. Simulation methods, experimental comparison methods, etc. can be used to tune the parameters to find the best parameter combination. The model parameters involve algorithm parameters, constraints, etc. The trained model is used to predict and make decisions on optimization tasks to evaluate the performance of the required algorithm and the effect on the optimization target. In addition, the evaluation results can be visualized to better understand the optimization effect.

[0141] The third step is to determine the trained optimization problem model as the required algorithm.

[0142] Specifically, after the demand algorithm is stored in the database, the demand algorithm is continuously deployed, and the optimization grid is optimized through the demand algorithm.

[0143] In some examples, for large-scale data and complex optimization problems, parallel processing technology (such as distributed computing, GPU acceleration, etc.) can be used between optimization grids to process, which can greatly improve the efficiency of algorithm execution.

[0144] Through the above scheme, when there is no adapted optimization algorithm in the configured algorithm library, the required algorithm can be obtained by combining relevant data training, so that the optimization solution process is more in line with the actual situation of the optimization grid, and the maximum value of the optimization algorithm can be fully exerted, avoiding the situation where the optimization accuracy is affected by the use of inappropriate optimization algorithms, thereby making the overall optimization accuracy higher.

[0145] It is understandable that the method of the embodiment of the present application can divide the problem space into multiple optimization grids, and call the adaptive optimization algorithm to find the optimization strategy in combination with the energy and carbon data corresponding to the optimization grid and the optimization target, so as to simplify the complex system optimization problem, so that the solution space can be searched in the optimization grid using efficient and low-cost algorithms. Through the combination of multiple basic algorithms to achieve system-level optimization, and then achieve efficient optimization and solution of complex problems, the optimization effect of carbon reduction and consumption reduction can be greatly improved, as well as the efficiency and refinement of system optimization.

[0146] See also Figure 6 , Figure 6 Another overall flow chart of the carbon reduction and energy saving optimization method of the embodiment of the present application is shown in FIG. In some embodiments, after executing step 104, the method of the embodiment of the present application further includes the following steps:

[0147] Step 105: If the optimized grid meets the update condition, the optimized grid is updated and / or the configured optimization algorithm is updated.

[0148] The update condition includes at least one of the following: the deviation between the optimization result of the energy carbon data corresponding to the optimization grid and the corresponding optimization target exceeds a first preset threshold, the characteristic change of the energy carbon data corresponding to the optimization grid exceeds a second preset threshold, and the preset classification dimension changes. The first preset threshold and the second preset threshold can be set in combination with specific energy carbon characteristics and scenarios, and the embodiments of the present application are not limited to this.

[0149] For example, if the industry type of the main body of carbon reduction and consumption reduction changes, the energy carbon data will also change, and then the classification dimension and data characteristics will also change, and the optimized grid will need to be rebuilt; or the energy consumption type in summer and the energy consumption type in winter will also be quite different, and the characteristics of the energy carbon data will also change greatly, and the optimized grid will also need to be rebuilt at this time.

[0150] It is understandable that if the optimized mesh does not meet the update condition, there is no need to update it, and the original optimized mesh can be maintained.

[0151] Exemplarily, if the deviation between the optimization result of the energy carbon data corresponding to the optimized grid and the corresponding optimization target exceeds the first preset threshold, the configured optimization algorithm is updated and the optimization is performed again at least once. If after re-optimization, the deviation between the optimization result of the energy carbon data corresponding to the optimized grid and the corresponding optimization target still exceeds the first preset threshold, the optimized grid needs to be updated, that is, the optimized grid needs to be re-divided. If the characteristic change of the energy carbon data corresponding to the optimized grid exceeds the second preset threshold and / or the preset classification dimension changes, the optimized grid is updated. Among them, updating the optimization algorithm refers to adjusting the parameter configuration of the optimization algorithm to improve the algorithm effect and convergence speed. Updating the optimized grid may involve operations such as dynamically adjusting the grid division and updating the weights of the segmentation model. It is also possible to predict the state and future trends of the optimized grid according to the optimization target, and make corresponding decisions and measures. Specifically, real-time data stream processing technology, rule engines, etc. can be used to realize the functions of real-time prediction and decision-making.

[0152] In other words, according to the algorithm execution effect and actual business needs, feedback information and new data can be continuously collected, the optimization algorithm can be continuously iterated, the algorithm parameters can be adjusted, and the optimization grid can be updated to continuously improve the optimization ability and adaptability of the algorithm. Feedback information can be obtained through evaluation indicators, user feedback, experimental comparison, etc. Among them, feedback information including optimization results is fed back to the system control or management end, which can be implemented through API interfaces (Application Programming Interface, application programming interface), message queues, etc., to achieve real-time decision-making and adjustment.

[0153] Through the above scheme, grid segmentation, algorithm scheduling configuration and / or training optimization algorithm are all dynamic and sustainable, so that when the carbon data, optimization target and grid segmentation parameter data of carbon reduction and consumption reduction change, they can be updated according to the results. In other words, grid segmentation, algorithm scheduling configuration and algorithm training model and training method can be continuously upgraded according to standards, history, real-time data, similar case data, evaluation feedback data, etc., so that carbon reduction and consumption reduction optimization is more in line with the actual situation and more accurate.

[0154] For example, a monitoring system can be set up to monitor the execution performance and result quality of the optimization algorithm through the monitoring system, so as to facilitate timely discovery and resolution of problems. The monitoring system can also track the energy use and carbon emissions of the carbon reduction and consumption reduction subject in real time, and adjust the optimization grid or strategy as needed.

[0155] Exemplarily, a timed task or trigger may be set to periodically or on demand start the execution of the aforementioned steps 101 to 104. In this way, it is ensured that the system can continue to operate and respond to changes in a timely manner, and continuously collect data, execute optimization algorithms, and update results.

[0156] Exemplarily, the method provided in the embodiment of the present application can establish an appropriate data storage and management system to store and archive the collected data. In this way, technologies such as databases and data warehouses can be used to ensure the security and integrity of the data and support rapid retrieval and access to the data. In addition, automation technology and automated decision-making can also be used to implement the execution and update of the optimization algorithm. For example, an automated system and a machine learning algorithm are used to automatically analyze and make decisions to improve optimization efficiency and accuracy.

[0157] It can be understood that the method of the embodiment of the present application can realize the continuous updating and optimization of the optimization algorithm and the grid to adapt to the real-time changing environment and needs, thereby realizing the overall consideration of the full life cycle and multi-dimensional optimization of the carbon reduction and consumption reduction tasks, and the degree of refinement is high, which can realize the efficient optimization and solution of complex problems and improve the carbon reduction and consumption reduction effect of the carbon reduction and consumption reduction solution.

[0158] Accordingly, see Figure 7 , Figure 7 The overall structure diagram of the carbon reduction and consumption reduction optimization device according to the embodiment of the present application is as follows: The carbon reduction and consumption reduction optimization device according to the embodiment of the present application comprises: a data acquisition module 701 , an optimization analysis module 702 , a grid segmentation module 703 and an algorithm scheduling module 704 .

[0159] Data collection module 701, used to obtain energy and carbon data of carbon reduction and consumption reduction subjects;

[0160] The optimization analysis module 702 is used to analyze the optimization space of the energy-carbon data based on the preset classification dimension to determine the first optimization analysis result of the energy-carbon data;

[0161] A grid segmentation module 703 is used to construct an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions;

[0162] The algorithm scheduling module 704 is used to allocate an optimization algorithm adapted to the optimization grid based on the characteristics of the energy-carbon data corresponding to each optimization grid and the optimization target corresponding to each optimization grid, and optimize the energy-carbon data corresponding to the corresponding optimization grid through the optimization algorithm.

[0163] See also Figure 8 , Figure 8 This is a schematic diagram of an example structure of the carbon reduction and consumption reduction optimization device of the embodiment of the present application. In some examples, the grid segmentation module 703 is also connected to the configured model library 705, the model library 705 is used to store the segmentation model, and the grid segmentation module 703 is used to search the segmentation model from the model library 705.

[0164] See also Fig. 9 , Fig. 9 Another exemplary structural diagram of the carbon reduction and consumption reduction optimization device of the embodiment of the present application. In other examples, the algorithm scheduling module 704 is also connected to the configured algorithm library 706, and the algorithm library 706 is used to store the optimization algorithm.

[0165] Specifically, when the grid segmentation module 703 is connected to the model library 705, the algorithm library 706 can be connected to the model library 705 to achieve data sharing and communication. The algorithm library 706 may not be connected to the model library 705, and the embodiment of the present application does not make specific limitations on this.

[0166] See also Fig.10 , Fig.10 Another example structural diagram of the carbon reduction and consumption reduction optimization device of the embodiment of the present application. In some other examples, the device also includes: an algorithm training module 707, which is connected to the data acquisition module 701, the grid segmentation module 703 and the algorithm scheduling module 704 respectively, and is used to train the demand algorithm based on the energy carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, so that the algorithm scheduling module 704 optimizes the energy carbon data corresponding to the corresponding optimized grid through the demand algorithm.

[0167] In some embodiments, the grid segmentation module 703 is specifically used to:

[0168] Determine a grid segmentation parameter based on a configured optimization algorithm, a first optimization analysis result, and at least one of a preset classification dimension;

[0169] The problem space is divided based on the grid segmentation parameters to obtain the optimized grid.

[0170] In some embodiments, the grid segmentation module 703 is specifically used to:

[0171] Based on the grid segmentation parameters, the problem space is segmented once using a preset grid segmentation algorithm or calling a segmentation model from the configured model library 705 to obtain multiple candidate grids;

[0172] If the candidate grid does not meet the preset segmentation stop condition, the candidate grid is continuously segmented using the grid segmentation algorithm or segmentation model until each candidate grid obtained by segmentation meets the preset segmentation stop condition, and each candidate grid is determined as an optimized grid.

[0173] In some embodiments, the preset segmentation stop condition includes that the data can be optimized by an available algorithm and / or the data features meet the target conditions; the grid segmentation module 703 is specifically used to:

[0174] If the energy-carbon data corresponding to the candidate grid can be optimized by an available algorithm and / or the characteristics of the energy-carbon data corresponding to the candidate grid meet the target conditions, it is determined that the candidate grid meets the preset segmentation stop condition.

[0175] In some embodiments, the algorithm scheduling module 704 is specifically used to:

[0176] Dispatching an optimization algorithm adapted to the optimization grid from the configured algorithm library 706;

[0177] If the scheduling is successful, configure the parameters of the optimization algorithm;

[0178] If the scheduling fails, the algorithm training module 707 trains the demand algorithm based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, and the algorithm scheduling module 704 stores the demand algorithm in the configured algorithm library 706.

[0179] In some embodiments, the algorithm training module 707 is specifically used to:

[0180] Based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, an optimization problem model is established;

[0181] Collect training data corresponding to the optimization problem model, and use the training data to train and verify the optimization problem model;

[0182] The optimization problem model that has completed training is determined as the required algorithm.

[0183] In some embodiments, the optimization analysis module 702 is specifically used to:

[0184] Based on the preset classification dimensions, the energy and carbon data are divided into multiple groups of sub-data;

[0185] Analyze the optimization space of each group of sub-data and determine the first optimization analysis result of energy-carbon data.

[0186] In some embodiments, the optimization analysis module 702 is specifically used to:

[0187] For any group of sub-data, based on the corresponding group sub-data and related group sub-data, analyze the optimization space of the corresponding group sub-data, where the related group sub-data is configured to represent sub-data related to the energy carbon type of the corresponding group sub-data; and / or, based on the corresponding group sub-data and historical data, analyze the optimization space of the corresponding group sub-data; and / or, based on data from each link in the life cycle of the corresponding group sub-data, analyze the optimization space of the corresponding group sub-data; and / or, based on the corresponding group sub-data and corresponding benchmarks, analyze the optimization space of the corresponding group sub-data.

[0188] In some embodiments, the apparatus further comprises:

[0189] An iterative update module is used to update the optimized grid and / or update the configured optimization algorithm if the optimized grid meets the update conditions. The update conditions include at least one of the deviation between the optimization result of the energy-carbon data corresponding to the optimized grid and the corresponding optimization target exceeds a first preset threshold, the characteristic change of the energy-carbon data corresponding to the optimized grid exceeds a second preset threshold, and the preset classification dimension changes.

[0190] In some embodiments, the data acquisition module 701 is specifically used for:

[0191] Collect operational data of entities involved in carbon reduction and energy consumption reduction;

[0192] The operational data is preprocessed, and the preprocessed data is analyzed and mined to obtain energy and carbon data.

[0193] In some embodiments, the data acquisition module 701 is specifically used for:

[0194] Operational data is collected through at least one of sensors, monitoring equipment, data collection platforms, database queries, and file imports.

[0195] In some embodiments, the preset classification dimensions include at least one of an industry type dimension, an organization dimension, a department dimension, a region dimension, a process dimension, an equipment dimension, and a time dimension.

[0196] It can be understood that the device of the embodiment of the present application can simplify complex system optimization problems, achieve system-level optimization through the combination of multiple basic algorithms, and then achieve efficient optimization and solution of complex problems, which can greatly improve the optimization effect of carbon reduction and consumption reduction.

[0197] Accordingly, the present application embodiment also provides an electronic device. Fig.11 , Fig.11Schematic diagram of the structure of an electronic device of an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0198] The electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor 11, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14. Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0199] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods described in the aforementioned embodiments, such as the carbon reduction and consumption reduction optimization method, or the processor 11 can configure the carbon reduction and consumption reduction optimization device described in the aforementioned embodiments.

[0200] In some embodiments, the carbon reduction and consumption reduction optimization method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the carbon reduction and consumption reduction optimization method described in the aforementioned embodiment may be performed, or the processor 11 may be enabled to configure the carbon reduction and consumption reduction optimization device of the aforementioned embodiment. Alternatively, in other embodiments, the processor 11 may be configured to execute the carbon reduction and consumption reduction optimization method in any other appropriate manner (e.g., by means of firmware).

[0201] In the context of the present application embodiment, computer readable storage medium can be a tangible medium, which can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer readable storage medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the above. Alternatively, computer readable storage medium can be a machine readable signal medium. A more specific example of a machine readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0202] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0203] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0204] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in the embodiments of the present application can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present application can be achieved, and this document is not limited here.

[0205] The above is a detailed introduction to a carbon reduction and consumption reduction optimization method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the technical solution and core idea of ​​the present application; ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A carbon reduction and energy consumption reduction optimization method, characterized in that: include: Obtain energy and carbon data of entities that reduce carbon emissions; Analyze the optimization space of the energy-carbon data based on a preset classification dimension to determine a first optimization analysis result of the energy-carbon data; Based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions, constructing an optimization grid in the problem space; Based on the characteristics of the energy-carbon data corresponding to each of the optimized grids and the optimization target corresponding to each of the optimized grids, an optimization algorithm adapted to the optimized grid is deployed, and the energy-carbon data corresponding to the corresponding optimized grid is optimized by the optimization algorithm.

2. The carbon reduction and consumption reduction optimization method according to claim 1 is characterized in that: The constructing an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions includes: Determine a grid segmentation parameter based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions; The problem space is segmented based on the grid segmentation parameters to obtain the optimized grid.

3. The carbon reduction and energy saving optimization method according to claim 2 is characterized in that: The problem space is segmented based on the grid segmentation parameter to obtain the optimized grid, including: Based on the grid segmentation parameters, the problem space is segmented once using a preset grid segmentation algorithm or calling a segmentation model from a configured model library to obtain multiple candidate grids; If the candidate grid does not meet the preset segmentation stop condition, the candidate grid is continuously segmented using the grid segmentation algorithm or the segmentation model until each candidate grid obtained by segmentation meets the preset segmentation stop condition, and each candidate grid is determined as the optimized grid.

4. The carbon reduction and energy consumption reduction optimization method according to claim 3 is characterized in that: The preset segmentation stop condition includes that the data can be optimized by an available algorithm and / or the data characteristics meet the target conditions; Determining whether the candidate grid satisfies the preset segmentation stop condition includes: If the energy-carbon data corresponding to the candidate grid can be optimized by an available algorithm and / or the characteristics of the energy-carbon data corresponding to the candidate grid meet the target condition, it is determined that the candidate grid meets the preset segmentation stop condition.

5. The carbon reduction and energy saving optimization method according to claim 1, characterized in that: The optimizing algorithm adapted to the optimized grid comprises: dispatching an optimization algorithm adapted to the optimization grid from a configured algorithm library; If the scheduling is successful, the parameters of the optimization algorithm are configured; If the scheduling fails, a demand algorithm is trained based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, and the demand algorithm is stored in the configured algorithm library.

6. The carbon reduction and energy saving optimization method according to claim 5, characterized in that: The training to obtain a demand algorithm based on the energy-carbon data corresponding to the optimization grid and the optimization target corresponding to the optimization grid includes: Establishing an optimization problem model based on the energy-carbon data corresponding to the optimization grid and the optimization target corresponding to the optimization grid; Collecting training data corresponding to the optimization problem model, and using the training data to train and verify the optimization problem model; The optimization problem model that has completed training is determined as the required algorithm.

7. The carbon reduction and energy saving optimization method according to claim 1, characterized in that: The analyzing the optimization space of the energy-carbon data based on the preset classification dimension to determine the first optimization analysis result of the energy-carbon data includes: Based on the preset classification dimension, the energy carbon data is divided into multiple groups of sub-data; Analyze the optimization space of each group of sub-data to determine the first optimization analysis result of the energy-carbon data.

8. The carbon reduction and energy consumption reduction optimization method according to claim 7, characterized in that: The analyzing the optimization space of each group of sub-data includes: For any group of the sub-data, based on the corresponding group of the sub-data and the related group of the sub-data, analyzing the optimization space of the corresponding group of the sub-data, wherein the related group of the sub-data is configured to represent the sub-data related to the energy carbon type of the corresponding group of the sub-data; and / or, analyzing the optimization space of the sub-data of the corresponding group based on the sub-data of the corresponding group and historical data; and / or, analyzing the optimization space of the sub-data of the corresponding group based on the data of each link in the life cycle of the sub-data of the corresponding group; And / or, based on the corresponding group of sub-data and corresponding benchmarks, analyzing the optimization space of the corresponding group of sub-data.

9. The carbon reduction and energy consumption reduction optimization method according to claim 1, characterized in that: The method further comprises: If the optimization grid meets the update conditions, the optimization grid and / or the configured optimization algorithm are updated, and the update conditions include at least one of the following: the deviation between the optimization result of the energy-carbon data corresponding to the optimization grid and the corresponding optimization target exceeds a first preset threshold, the characteristic change of the energy-carbon data corresponding to the optimization grid exceeds a second preset threshold, and the preset classification dimension changes.

10. The carbon reduction and energy consumption reduction optimization method according to claim 1, characterized in that: The obtaining of energy and carbon data of the carbon reduction and consumption reduction subject includes: Collecting operational data of the carbon reduction and consumption reduction entities; The operation data is preprocessed, and the preprocessed data is analyzed and mined to obtain the energy carbon data.

11. The carbon reduction and energy consumption reduction optimization method according to claim 1, characterized in that: The preset classification dimensions include at least one of an industry type dimension, an organization dimension, a department dimension, a region dimension, a process dimension, an equipment dimension, and a time dimension.

12. A carbon reduction and consumption reduction optimization device, characterized in that: include: Data collection module, used to obtain energy and carbon data of carbon reduction and consumption reduction entities; An optimization analysis module, used to analyze the optimization space of the energy-carbon data based on a preset classification dimension, and determine a first optimization analysis result of the energy-carbon data; A grid segmentation module, configured to construct an optimization grid in the problem space based on the configured optimization algorithm, the first optimization analysis result, and at least one of the preset classification dimensions; The algorithm scheduling module is used to allocate an optimization algorithm adapted to the optimization grid based on the characteristics of the energy-carbon data corresponding to each of the optimization grids and the optimization target corresponding to each of the optimization grids, and optimize the energy-carbon data corresponding to the corresponding optimization grid through the optimization algorithm.

13. The carbon reduction and consumption reduction optimization device according to claim 12, characterized in that: The grid segmentation module is also connected to a configured model library, the model library is used to store segmentation models, and the grid segmentation module is used to search for the segmentation model from the model library.

14. The carbon reduction and consumption reduction optimization device according to claim 12 or 13, characterized in that: The algorithm scheduling module is also connected to a configured algorithm library, and the algorithm library is used to store the optimization algorithm.

15. The carbon reduction and consumption reduction optimization device according to claim 13, characterized in that: The device also includes: An algorithm training module, the algorithm training module is respectively connected to the data acquisition module, the grid segmentation module and the algorithm scheduling module, and is used to train a demand algorithm based on the energy-carbon data corresponding to the optimized grid and the optimization target corresponding to the optimized grid, so that the algorithm scheduling module optimizes the energy-carbon data corresponding to the optimized grid through the demand algorithm.

16. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; In which, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the carbon reduction and consumption reduction optimization method described in any one of claims 1-11, or so that the processor can configure the carbon reduction and consumption reduction optimization device described in any one of claims 12-15.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the carbon reduction and consumption reduction optimization method described in any one of claims 1-11 when executed, or the computer instructions are used to enable a processor to configure the carbon reduction and consumption reduction optimization device described in any one of claims 12-15.

Images