Multi-objective economic load dispatch method based on data mining technology for large coal-fired power plants

Coal-fired power plants occupy a dominant position in the power system and are the key sector of energy consumption and pollutant emission. A fallacious load dispatching scheme for the power plant will have a negative impact on energy use and emission reduction. This paper proposes a multi-objective economic load dispatch method for the coal-fired power plant based on data mining technology. The core of the method is to mine the optimal decision-making samples from the offline database to guide the online economic load dispatching, according to the load demand of the power grid. Thus, in the big data environment, a hierarchical clustering and retrieval strategy based on the fuzzy c-means clustering algorithm is proposed to construct the offline database, which can lower the online calculation amount of sample retrieval while balancing the retrieval accuracy. Moreover, the multiple attribute decision-making method, which comprehensively considers multiple objectives, is used to mining the optimal decision-making samples from the offline database to guide the load dispatching scheme for the power plant. The database maintenance strategy is utilized to optimize and update the offline database. Finally, the proposed method is applied to an on-duty coal-fired power plant to verify its effectiveness. The results show that the data-mining-based method can achieve the plant-level optimal load dispatching while meeting the actual requirements of the grid.