Aiming at the problem of insufficient computing power in the analysis of flexible load under the condition of massive user data in distribution network, a flexible load analysis method based on big data is proposed. Firstly, the data fusion and feature extraction of the massive user data in distribution network are carried out to realize the preprocessing of the original data. Then, on the basis of MapReduce parallel computing model, the k-means algorithm is used to cluster the load characteristic data and calculate the industry flexibility coefficient and adjustable load. According to the results of load flexibility analysis based on the historical data of a power supply company in a certain city, this method can make statistics on load flexibility (load adjustable space) from industry dimension and time dimension, judge the current load flexibility level, and combine external data and temperature data to carry out load flexibility analysis. According to historical data, the adjustable load level of a certain area, a certain industry and a certain period in the future is predicted.
Feature Extraction
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask,hadoop Frontend :-python Backend:- MYSQL
₹10000 (INR)
2019