30 results about "Operation model" patented technology

The invention discloses an industrial park comprehensive energy system low-carbon planning method considering a production process, and the method comprises the following steps: 1, obtaining the production line condition of an industrial park, and constructing a production line model; 2, determining to-be-planned equipment and parameters, and constructing a lower-layer planning operation model considering short-term uncertainty; 3, determining medium and long term uncertainty parameters, and constructing a medium and long term uncertainty set; step 4, determining a multi-objective optimization model; 5, searching a Pareto leading edge by using multi-target reinforcement learning based on a decomposition technology; and 6, selecting a proper Pareto frontier solution, and substituting the Pareto frontier solution into the lower-layer planning operation model to obtain a corresponding planning result. The invention aims to realize low-carbon transformation of an integrated energy system (IRIES) in an industrial area so as to cope with carbon reduction, emission reduction and challenges in a carbon dense area.

The invention relates to a power distribution network variable time scale optimization method considering source-load-storage collaborative optimization. The method specifically comprises the following steps: step 1, constructing an excitation type load demand corresponding model, an energy storage comprehensive operation model, a day-ahead scheduling stage model and an intra-day multi-time scale scheduling model; step 2, through day-ahead-day-real-time continuous fine scheduling, fully excavating the adjustment potential of the energy storage device and the flexible load; 3, introducing a deviation reduction rate-cost increase rate dynamic game model through scheduling of a variable time scale, and adaptively adjusting the time scale in a real-time stage; 4, constructing a real-time variable time scale scheduling model; 5, improving a rolling optimization strategy, and classifying various resources to match corresponding time scales; step 6, performing instance analysis; the method has the advantages that the consumption rate is increased, the time scale is adaptively adjusted, the power quality is improved, the dynamic game model is introduced, and cooperative scheduling is realized.

Technological improvements are described for automatically generating crew and equipment schedules that are optimized for regulatory compliance and balanced according to goals or policies referred to as balance settings. Example systems and methods include building and maintaining a compliance library of regulations. A machine-learning operations model generates a schedule that complies with regulations and receives input data including a proposed schedule and the priority-weighted balance settings. Then, the operations model, using a set of recursive processes, generates a candidate schedule that is optimized based on the regulations and the balance settings. An auditor confirms the candidate schedule complies with regulations. The auditor evaluates real-time data to flag potential violations and generate compliance notices and compliance reports. The system includes a generative AI model trained using an industry-specific small language model (ISLM) for receiving textual and image data for use by the operations model and for generating responsive messages.

The invention discloses an intelligent production scheduling method and system based on a fixed sequence genetic algorithm. The method comprises the following steps: dividing independent production areas of a workshop; key operation is determined, and modeling is carried out on time of the key operation; generating a process set containing a fixed sequence key job based on a process path, performing crossover variation by using an improved genetic algorithm, and keeping the sequence of internal processes of a task unchanged to avoid an invalid solution; and calculating the shortest processing duration through population iteration, and generating a production scheduling Gantt chart. The system comprises a workshop function area module, a key operation type module, a key operation modeling module and a production scheduling result output module, so as to realize the output of an intelligent production scheduling result. The method improves the production scheduling efficiency and the applicability of the production scheduling result, and is suitable for complex production scenes such as electronic assembly and cabinet debugging.

The invention relates to a virtual power plant optimization scheduling method and system. The method comprises the following steps: establishing an operation model of a multi-type adjustable resource main body; constructing a master-slave game model of the aggregator and the resource main body, wherein the master-slave game model comprises an upper-layer model taking the aggregator as a leader and a lower-layer model taking the resource main body as a follower; solving a master-slave game model of the aggregator and the resource main body to obtain an optimal compensation price strategy and an optimal response power strategy, and constructing an optimal power scheduling plan according to the optimal response power strategy; the optimal power scheduling plan is used for being issued to each adjustable resource main body for execution so as to realize optimal scheduling of the virtual power plant. According to the method, the participation enthusiasm of the resource main body can be stimulated, the user participation degree can be improved, the scheduling instruction execution rate can be improved, the model accuracy can be improved, the cooperative capability of heterogeneous resources can be improved, and the overall operation economy and stability of the virtual power plant can be improved.

The present application relates to the technical field of retail management, and particularly refers to a lean operation model for clothing retail stores from the perspective of data empowerment. The model comprises a four-dimensional health degree evaluation module, a data report generation module, a store manager interview consensus module and a closed-loop execution review module. The four-dimensional health degree evaluation module constructs a mathematical model based on four dimensions of sales efficiency, human efficiency quality, member value and product efficiency and their subordinate indicators, and outputs an overall health degree score OHS to realize quality diagnosis of store operation. The data report generation module generates five key business reports to convert raw data into visual insights. The store manager interview consensus module realizes the integration of data and experience through a structured eight-step process and generates a SMART rectification plan. The closed-loop execution review module realizes the PDCA cycle through an agile review mechanism. The present application solves problems such as low operation efficiency, decision-making relying on experience and insufficient rectification execution of clothing retail stores through the deep integration of data-driven and lean operation.

Technological improvements are described for automatically generating crew and equipment schedules that are optimized for regulatory compliance and balanced according to goals or policies referred to as balance settings. Example systems and methods include building and maintaining a compliance library of regulations. A machine-learning operations model generates a schedule that complies with regulations and receives input data including a proposed schedule and the priority-weighted balance settings. Then, the operations model, using a set of recursive processes, generates a candidate schedule that is optimized based on the regulations and the balance settings. An auditor confirms the candidate schedule complies with regulations. The auditor evaluates real-time data to flag potential violations and generate compliance notices and compliance reports. The system includes a generative AI model trained using an industry-specific small language model (ISLM) for receiving textual and image data for use by the operations model and for generating responsive messages.

The invention discloses an integrated production operation platform based on digital and intelligent twinning, relates to the technical field of production operation, and establishes a digital and intelligent twinning operation model of a physical execution layer and a virtual mapping layer by constructing state characteristic parameters of operation nodes and fusing multi-source time sequence data. A state consistency constraint function is introduced to represent the synchronization deviation between the two layers; on the basis, performing real-time iterative calculation on the target job execution model to obtain a state deviation value of each job node, and checking state consistency based on signal sequential logic and a robust online monitoring algorithm to generate an abnormal state judgment result; further executing instruction delay, path re-planning or state rollback according to the exception type to realize dynamic correction and closed-loop control of the operation process; according to the invention, the accuracy of abnormity identification and the timeliness of processing in complex production operation can be effectively improved, and the stability and the safety of overall operation of the system are enhanced.

The application relates to the technical field of equipment operation and maintenance decision and optimization, and discloses a multi-modal knowledge driven production equipment system multi-objective operation mode optimization method, which comprises the following steps: constructing a production demand change prediction model based on periodical trend decomposition; constructing a multi-modal knowledge graph model; constructing a production equipment system operation quality evaluation index system and determining optimization targets; constructing a data driven equipment operation model based on an extended random flow network model; evaluating each optimization target of the production equipment system; constructing a multi-objective reward function based on a knowledge driven Pareto distance method; constructing an operation and maintenance management and mode optimization joint strategy optimization model; identifying and selecting key optimization targets and operation and maintenance technologies based on multi-modal production demand and production equipment operation data driven multi-modal knowledge graphs; and performing production equipment mode optimization and operation and maintenance management strategy joint optimization by using a deep deterministic policy gradient, so that operation and maintenance strategy dynamic optimization solving is realized.

The invention discloses a multi-agricultural machinery collaborative operation method and system, electronic equipment and a storage medium, and the method comprises the steps: building a field operation model of a target farmland based on the boundary information and geographic information of the target farmland; dividing the field operation model into a plurality of operation sub-regions according to the operation capability parameters of each agricultural machine participating in the collaborative operation, allocating at least one operation sub-region to each agricultural machine, and generating an initial operation path covering all the corresponding operation sub-regions for each agricultural machine; and establishing communication connection among a plurality of agricultural machines participating in collaborative operation, and dynamically scheduling operation sub-region distribution and an initial operation path corresponding to each agricultural machine based on real-time position information and operation state information, shared in real time, of each agricultural machine. According to the method, the problems of unreasonable scheduling, frequent conflict of operation paths and insufficient dynamic adjustment capability in collaborative operation of the multiple agricultural machines are solved, and the collaborative operation efficiency and overall robustness of the multiple agricultural machines are greatly improved.

The application discloses a microbial early warning and prediction system and method, the system comprises a data integration module, an operation modeling module, a model verification module and a total evaluation module, the data integration module associates public microbial information with customer information, and transmits the associated data to the operation modeling module; the operation modeling module operates and models the associated data, and transmits the result to the model verification module, the model verification module is used for verifying the accuracy and rationality of the individualized customized model, and transmitting the processed information to the total evaluation module, finally, the total evaluation module outputs a risk index, a risk description and a recommended improvement scheme according to the information of the operation modeling module. Due to the adoption of the above technology, the application comprehensively, systematically and multi-dimensionally analyzes various aspects of products and factories, achieves the purposes that prediction and recommended results are more accurate, application fields are more extensive, interpretation modes are more detailed and convenient, and the like.

The invention relates to a virtual power plant scheduling optimization method and device, computer equipment, a computer readable storage medium and a computer program product. Comprising the following steps: solving a day-ahead scheduling model according to a random variable generated by an uncertainty parameter model under the limitation of power constraint and energy balance constraint in combination with an operation cost model of a synchronous unit, an income model of a day-ahead market, an income model of a standby market and an operation model of a pumped storage unit, so as to obtain a current scheduling model; and determining the generated power, the adjustment reserve capacity and the expected profit of each component in the virtual power plant when the expected profit of the virtual power plant is maximum during scheduling. By adopting the method, the day-ahead market and the standby market are comprehensively considered, and collaborative scheduling optimization is realized. Therefore, the virtual power plant can reasonably arrange the operation strategy of each component in an uncertain environment so as to realize profit maximization. The method can adapt to a randomly changing market environment, and improves the robustness of an operation strategy and the operation reliability of the virtual power plant.

The invention discloses a robot unstacking and stacking method, and belongs to the technical field of industrial robots. Determining an unstacking area and a stacking area of the materials; according to the size parameters of the materials, an unstacking pile and a stacking pile of the materials are simulated and generated; according to the unstacking pile of the materials and the unstacking mode of the materials, an unstacking model of the materials is constructed in the unstacking area; the unstacking model is used for indicating an unstacking track and an unstacking sequence of the robot for unstacking the materials; according to the stacking pile of the materials, the unstacking mode of the materials and the stacking mode of the materials, a stacking model of the materials is constructed in the stacking area; and according to the unstacking model of the materials and the stacking model of the materials, the robot is controlled to unstack and stack the materials. A user only needs to input the material size, the pile type parameters and the operation mode, a complete operation model and a motion instruction can be automatically generated, efficient configuration of unstacking and stacking tasks is achieved, and the method is particularly suitable for industrial scenes such as flexible manufacturing, intelligent storage and logistics sorting which have high requirements for the automation degree.

The invention relates to a virtual power plant scheduling strategy obtaining method and device and computer equipment. The method comprises the following steps: acquiring energy parameters, historical operation data and energy conversion efficiency of each component of a target virtual power plant; constructing an operation model of each component according to the energy parameters of each component of the target virtual power plant; sampling to generate a plurality of operation modes of the target virtual power plant according to the historical operation data; determining a risk index and a resource consumption index of the virtual power plant in each operation mode according to the operation data of each operation mode; determining a target operation model of the target virtual power plant based on the operation model of each component, each operation mode, the corresponding risk index and resource consumption index, and the energy conversion efficiency; and determining a scheduling strategy of each component of the target virtual power plant according to the target operation model of the target virtual power plant. By adopting the method, the operation efficiency and stability of the virtual power plant in a complex environment can be effectively improved.

This invention discloses a long-term optimized operation method for a regional integrated energy system considering the physical properties of hydrogen and multi-mode utilization. The steps are as follows: 1) Clustering source-load data using a clustering algorithm to obtain k typical days and the correspondence between typical days and actual operating days, k = h(r); 2) Establishing an equipment operation model based on equipment operating parameters; 3) Establishing a hydrogen utilization model under medium- and long-term multi-mode utilization; 4) Linearizing the equipment operation model; 5) Establishing a long-term optimized operation model of the Energy System (IES) considering LHS (Local Hybridization System); 8) Obtaining real-time operating data of the energy system and inputting it into the long-term optimized operation model of the IES considering LHS to obtain a long-term optimized operation scheme for the energy system. This invention can be widely applied to the evaluation of new energy AGC (Automatic Generation Control) power plants with different installed capacities, in different regions, and with different frequency regulation performance. It can provide a useful reference for the operation control of new energy participating in the secondary frequency regulation of the power system and the distribution of revenue in the auxiliary frequency regulation market.

The invention discloses a micro-grid-multi-EV aggregator mixed game optimization method considering low-carbon economic operation. The method comprises the following steps: constructing a single EV slow charge capacity boundary model considering user travel uncertainty; constructing a carbon transaction model considering a certificate-carbon fusion mechanism; an operation model is optimized based on a mixed game: an optimal energy selling price strategy of a regional user aggregator is determined through a master-slave game, and a micro-grid operator solves an equilibrium solution for minimizing the comprehensive cost of the two parties based on a pricing boundary; and secondly, each aggregator obtains electric energy transaction payment in the alliance through cooperative game solution based on the transaction power determined in the previous stage, allocates interests of each user according to asymmetric Nash negotiations with different user contribution degrees, and finally forms a multi-agent cooperation mechanism giving consideration to market benefits and environmental benefits.

This invention relates to the fields of software engineering and artificial intelligence, and particularly to an automated management system for the entire software development lifecycle, including a requirements analysis and architecture design module, a development and testing integration module, a deployment and operation monitoring module, and a visual management module. In the requirements phase, the invention performs semantic parsing of natural language requirements to generate structured documents, intelligently matches historical architecture patterns, and establishes a two-way traceability relationship. In the development and testing phase, it automatically generates code frameworks and test cases, performs incremental code review based on a defect prediction model, and automatically completes log cleaning, fault location, root cause analysis, and defect ticket closure when tests fail. In the deployment and operation phase, it intelligently generates canary release strategies, constructs a digital twin operation model, and enables multi-dimensional tracing and rapid handling of operational anomalies. This invention breaks down data barriers throughout the entire process with a unified digital mainline data layer, significantly improving software development and delivery efficiency and system operational stability.

According to the cross-domain digital twin system based on the DIKWP model, the limitation that traditional twin only maps physical data is broken through, and a smart image covering five layers of data, information, knowledge, wisdom and intention is constructed. The system synchronizes sensing and business data of an entity in real time, dynamically calibrates an operation model, and embeds a decision strategy and a macroscopic target into a twinborn body to realize virtual-real consistency verification. The system has the functions of virtual-real comparison, trend prediction, abnormity early warning, decision evaluation and cross-department collaboration, interconnection and intercommunication of twins (such as traffic and energy) in different fields are achieved through a standard semantic interface, and system-level joint simulation is supported. Multiple technical achievements are integrated, a comprehensive management solution for complex systems such as smart cities and smart factories is formed, the cross-domain collaboration and intelligent decision-making ability is improved, and the method has wide application value and innovativeness.

The invention belongs to the technical field of new energy consumption cost calculation, and relates to a new energy consumption cost quantitative calculation method in a market environment. The method comprises the following steps: S1, extracting and constructing a new energy multi-dimensional characteristic vector; s2, establishing a mapping relation between the multi-dimensional feature vectors and the clearing boundaries of the power market, and calculating the demand up-regulation amount of each clearing boundary; s3, constructing an operation model corresponding to each time scale, and forming an operation constraint set; s4, identifying and classifying additional cost to form a consumption cost list; and S5, cost quantitative measurement and calculation are carried out, an operation simulation model and a long-term planning model are constructed and solved, the total system cost of the reference scene and the actual new energy characteristic scene is calculated and compared, and the difference value is the total consumption cost caused by the new energy characteristics. According to the method, the physical characteristics of new energy can be converted into quantifiable economic signals, so that more economical, efficient and safe novel power system transformation is supported and realized in multiple key fields such as power market construction, power grid planning and operation, energy policy making and the like.

This application provides a medium- to long-term power system planning method that considers the flexible production mode of nuclear power. The method includes constructing a system operation model with multiple power source categories based on resource data and power parameters, and constructing a capacity planning model with the objective of minimizing the annualized comprehensive cost of the system, combined with first-cost data. Constraints include nuclear power flexibility operation constraints, power supply and demand balance constraints, system reserve constraints, installed capacity constraints, cross-sectional constraints, carbon emission constraints, and energy storage operation constraints. Based on the nuclear power flexibility operation constraints and output data, the system operation model is used to perform production simulation to obtain load forecast data and second-cost data. Based on the load forecast data and second-cost data, the capacity planning model is solved to obtain the power system planning scheme. This method simultaneously considers economic efficiency, low carbon emissions, and flexible regulation capabilities, achieving multi-objective collaborative planning and providing scientific support for the optimization of the power source structure of new power systems.

The application relates to the technical field of medical training models, in particular to a preoperative simulation operation model device. In view of the fact that the model device in the prior art is inconvenient for storing a 3D model and is inconvenient for automatically sterilizing the 3D model, thereby increasing the workload of staff, the following scheme is proposed, which comprises a base, four moving wheels, a fixed frame, a moving frame, a workbench, two first connecting shafts and two bidirectional screws. The four moving wheels are installed at the bottom of the base; the fixed frame is fixedly installed at the top of the base; the moving frame is slidably installed on the fixed frame; the top of the moving frame is fixedly installed with the workbench; the inner wall of the moving frame is slidably installed with the two first connecting shafts; the two bidirectional screws are rotatably installed at the top of the base. The application is convenient for storing the 3D model and is convenient for automatically sterilizing the 3D model, thereby reducing the workload of staff.

The invention discloses an energy scheduling method applying the Internet of Things and artificial intelligence. The method comprises the steps of S1, collecting operation data of different distributed energy devices in a region in real time through an Internet of Things system; s2, processing the operation data of each energy device through an artificial intelligence model, constructing a standardized operation model of each energy device, and aggregating the standardized operation model into a schedulable virtual unit; s3, collecting real-time price information of the electricity market, and generating a scheduling strategy through a rolling optimization algorithm in combination with new energy actual power generation power prediction, load demand prediction and electricity price prediction; and S4, controlling corresponding energy equipment to work through a multi-level control system according to a scheduling instruction of the scheduling strategy, and feeding back execution data, thereby realizing source network load storage collaborative optimization, improving resource utilization rate and scheduling flexibility, and improving competitiveness and income level of a virtual power plant in an electric power market.

The invention discloses a distributed energy storage virtualization sharing system scheduling method based on a target cascade method. The method comprises the following steps: 1, constructing an operation model comprising a production and disappearing person community containing distributed energy storage and a production and disappearing person community renting virtual energy storage; 2, establishing a service life model of the generator set, and establishing an operation model of an operator by using an interactive power equivalent calculation strategy of distributed energy storage-virtual energy storage; 3, establishing a three-layer optimization model of the distributed energy storage virtualization sharing system; and 4, solving the three-layer optimization model based on a target cascade method, and solving a scheduling scheme of the distributed energy storage virtualization sharing system. According to the method, a distributed energy storage-virtual energy storage interaction power equivalence method is introduced, and a distributed target cascade optimization method is combined to solve a three-layer optimization model of the distributed energy storage virtualization sharing system, so that on the basis of ensuring the safe operation boundary of a power network and equipment, the distributed energy storage-virtual energy storage interaction power equivalence is realized; the carbon emission of the system is effectively reduced, and the utilization rate of distributed energy storage is improved.

The invention discloses a bidding decision-making method, system and device for participation of an integrated energy park in a spot-carbon market in consideration of internal production characteristics, and a storage medium, and relates to the technical field of energy management optimization, and the method comprises the steps: inputting industrial user information, and constructing an output model of an industrial user according to the production characteristics of the industrial user, internal production constraint description of the park is formed; based on the output model, synchronously inputting comprehensive energy park information and market information, respectively constructing an operation model of the comprehensive energy park and a comprehensive clearing model of the spot-carbon market, and forming parallel description of park operation constraints and market clearing constraints; the output model, the operation model and the comprehensive clearing model are constructed into a combined double-layer model, a gurobi commercial solver is called in Matlab for solving, and a bidding decision is output; according to the method, through optimization of power production and carbon emission management, benefit maximization under double constraints of the power market and the carbon market is realized, and the economic benefit of the park is improved.

The application discloses an integrated production operation platform based on digital twin, relates to the technical field of production operation, and establishes a digital twin operation model of a physical execution layer and a virtual mapping layer by constructing state characteristic parameters of operation nodes and fusing multi-source time sequence data, and introduces a state consistency constraint function to represent the synchronization deviation between the two layers; on the basis, real-time iterative calculation is performed on a target operation execution model to obtain state deviation values of each operation node, and state consistency is checked based on signal time sequence logic and a robust online monitoring algorithm to generate an abnormal state judgment result; further, according to the abnormal type, instruction delay, path re-planning or state rollback are executed to realize dynamic correction and closed-loop control of the operation process; the application can effectively improve the accuracy of abnormal identification and the timeliness of processing in complex production operation, and enhance the stability and safety of the overall operation of the system.

This application provides a cost optimization method for an electric-thermal coupled virtual power plant based on stochastic optimization. The method includes: obtaining historical operating parameters; constructing physical simulation models of each component based on the historical operating parameters to obtain a power plant operation model; constructing operating cost models of each component based on the historical operating parameters to obtain a power plant cost model; determining the uncertainty parameters of the virtual power plant based on the historical operating parameters and constructing a stochastic model; constructing a set of objective constraints based on the power plant operation model; obtaining the first and second uncertainties based on the system uncertainties using the IGDT method for risk avoidance and opportunity seeking; further solving for the power plant control parameters; and controlling the operation of the virtual power plant based on the power plant control parameters. This method addresses the problem in the prior art of lacking a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture, and electrical conversion equipment to meet low-cost and low-carbon requirements.

The invention relates to the technical field of equipment operation and maintenance decision and optimization, and discloses a multi-modal knowledge-driven production equipment system multi-target operation mode optimization method, which comprises the following steps: constructing a production demand change prediction model based on periodic trend decomposition; constructing a multi-modal knowledge graph model; constructing a production equipment system operation quality evaluation index system, and determining an optimization target; based on the extended random flow network model, constructing a data-driven equipment operation model; evaluating each optimization target of the production equipment system; constructing a multi-target reward function based on a knowledge-driven superior and inferior solution distance method; constructing an operation and maintenance control and mode optimization combined strategy optimization model; based on the multi-modal knowledge graph, key optimization target and operation and maintenance technology identification and selection driven by multi-modal production requirements and production equipment operation data are carried out; a depth deterministic strategy gradient is adopted, production equipment mode optimization and operation and maintenance management and control strategy joint optimization are carried out, and dynamic optimization solution of an operation and maintenance strategy is achieved.

To provide a technique for managing an investment fund by a portfolio obtained by combining a plurality of investment strategies.SOLUTION: An investment model management device includes: a sub-investment model management section for managing a plurality of sub-investment models which are individually operated according to predetermined investment strategies; a main investment model management section for managing a main investment model which operates an investment fund; and a portfolio determination section which determines a portfolio for allocating the investment fund of the main investment model to the plurality of sub-investment models on the basis of investment performance information of each sub-investment model.SELECTED DRAWING: Figure 1

Computer program products, systems containing computer program products, and methods are disclosed for considering rig equipment asset life and maintenance costs in decisions related to well construction / operations planning. A method may include utilizing sensor measurements to generate and record condition indicators for equipment over time and using the condition indicators to develop / refine a digital avatar including a model correlating operation of the equipment with a progression of the condition indicators to predict changes in equipment condition. The method may further include calculating costs / profits based on a well construction / operation plan and predicting a progression of conditions of the equipment during operation of the plan. The digital avatar or comprehensive operations model may enable comparison of costs / profits from resource production with a cost of service delivery (COSD) for the equipment, and may advantageously enable plan changes to be proposed to reduce / minimize costs and / or to increase / maximize profit.

The invention discloses an optimization regulation and control method for interaction between an industrial load cluster containing multiple production modes and a power grid and a medium, and belongs to the technical field of interaction between the industrial load cluster and the power grid in the multiple production modes. The method comprises the following steps: based on acquired industrial load information, performing data processing through an industrial load data preprocessing model to obtain industrial load parameters; constructing an industrial load operation model of multiple production modes based on the industrial load parameters; based on the industrial load operation model of the multi-production mode, constructing a multi-objective optimization model; and solving the multi-objective optimization model by using a multi-objective optimization algorithm, and outputting an optimized regulation and control operation time sequence result based on the industrial load operation model of the multi-production mode. According to the method, industrial loads of multiple production modes are considered, an aggregation cluster refinement model is established, optimal regulation and control and diversified target requirements between the power grid and the industrial load cluster are achieved, and economic, green and low-carbon coordinated development of the power grid and the industrial loads is promoted.