Troubleshooting and Traceability Method Based on MapReduce Big Data Platform and Improved Genetic Reduction Algorithm for Smart Substation
Hongxin Yu, Youqianq Zhang, Xin Wang, Yang Tian · 2019 IEEE Sustainable Power and Energy Conference (iSPEC) · 2019
Aiming at the management of a large number of state data of smart substation ,fast detection and accurate processing of smart substation fault based on massive data, a fault diagnosis and traceability method based on MapReduce big data programming architecture and improved genetic reduction algorithm is proposed in this paper. The MapReduce big data parallel architecture is used as a processing tool for processing substation state data, which effectively solves the problem of obtaining and managing massive monitoring data. Through the combination of data mining technology and genetic algorithm, it extracts effective information in a large amount of state information, reduces data size, thereby speeding up the processing of fault information and accurately determining equipment fault status, optimizing substation fault diagnosis function, and tracking the location of faults. In order to verify the algorithm, a distributed cluster hardware experiment platform is built. With proposed platform and algorithm, fault information is extracted and reduced from massive data. Fault type and location can be easily get from analysis result.