Research on Optimization of Data Compression for Power Grid Operation and Dispatch Monitoring
In the context of big data,the rapid increase in data volume makes it more difficult to monitor data information for power grid operation scheduling,which will seriously hinder the timeliness of scheduling.Therefore,in order to improve the efficiency of power grid operation scheduling monitoring data,a genetic optimization clustering algorithm was designed based on genetic algorithm combined with K-means clustering algorithm.Then,a monitoring data compression method for power grid operation scheduling was designed by combining genetic optimization clustering algorithm with gated recurrent neural network.The results showed that the cluster space before compression was 32.8GB,while the compression method based on genetic optimization clustering only occupied 0.09GB,reducing it by 99.72%.The compression rate of the optimized algorithm reached 13.7%,which is 13.5%,18.0%,and 9.3%lower than that of ordinary K-means clustering,DBSCAN clustering,and HC clustering algorithms,respectively.In summary,it can be seen that the research on data compression optimization based on power grid operation scheduling monitoring has effectively saved storage space and improved data scheduling efficiency.
power gridgenetic algorithmdata compressionmonitoringK-means clustering
万方数据
维普
