Large-scale constraint scheduling method and system for coal mine integrated energy system

By combining multi-type sensors and machine learning prediction with search direction learning evolutionary optimization algorithms, the problem of high dimensionality of decision variables and complex constraints in coal mine integrated energy systems has been solved. This has achieved efficient energy supply and demand balance and system optimization, generated a Pareto optimal solution set for multi-objective optimization, and improved the operating efficiency and intelligence level of coal mine integrated energy systems.

CN122453028AActive Publication Date: 2026-07-24CHINA UNIV OF MINING & TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202610584526.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-29
Publication Date
2026-07-24
Estimated Expiration
2046-04-29

AI Technical Summary

Technical Problem

The high dimensionality of decision variables and the complexity of constraints in coal mine integrated energy systems lead to low search efficiency and difficulty in balancing multiple optimization objectives such as economic costs and carbon emissions. Traditional multi-objective evolutionary optimization algorithms are unable to effectively explore in large-scale search spaces, thus making it difficult to find scheduling schemes that meet safety, economy, environmental protection and reliability requirements.

Method used

Data is collected in real time using multiple types of sensors, and key parameters for the next 24 hours are predicted using machine learning methods. A 24-hour scheduling optimization model for the coal mine integrated energy system is constructed, and a search-direction learning evolution optimization algorithm is used to solve the model, generating a Pareto optimal solution set. Scheduling instructions are then issued through a standardized communication protocol.

Benefits of technology

It enables efficient guidance of the search direction in a large-scale decision variable space, significantly improves the convergence speed and solution quality, generates multiple optional scheduling schemes, meets equipment operation constraints and power balance, ensures the safety and feasibility of the coal mine integrated energy system, and improves the system's operational robustness and intelligence level.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a coal mine integrated energy system large-scale constraint scheduling method and system, and belongs to the technical field of intelligent mine and energy system optimization scheduling. The method comprises the steps of S1, collecting various data required by energy system scheduling in real time through multiple types of sensors in combination with an information system, and completing key parameter prediction in the next 24 hours based on a machine learning method; s2, constructing a 24-hour scheduling optimization model of the coal mine integrated energy system based on a prediction result of the step S1, and solving the model by adopting a search direction learning evolutionary optimization algorithm; and S3, converting and verifying the optimization scheme obtained in the step S2, forming an executable instruction, issuing the executable instruction to each energy device, and monitoring an execution effect. By adopting the large-scale constraint scheduling method and system for the coal mine integrated energy system, dynamic balance of energy supply and demand and economic operation of the system can be realized.
Need to check novelty before this filing date? Find Prior Art