Electric load data characterising and forecasting based on trend index and auto‐encoders. Issue 17 (31st October 2018)

• Record Type: Journal Article
• Authors: Lu, Shixiang; Lin, Guoying; Que, Huakun; Chen, Liang; Liu, Hanlin; Ye, Chengjin; Yi, Ding
• Is Part Of: Journal of engineering. Volume 2018:Issue 17(2018)
• Page Start: 1915
• Page End: 1921
• Publication Date: 2018-10-31
• Subjects: load forecasting -- neural nets -- power markets -- demand side management -- power system economics -- power engineering computing -- smart power grids -- power consumption; electricity consumption data -- high‐quality meters -- smart grids -- load data volume -- advanced market‐based applications -- demand response -- load service entities -- trend‐based load characterising approach -- load description -- stochastic oscillator -- stacked auto‐encoders -- input historical trend indexes -- trend‐based method -- electric load data characterization -- moving average convergence; Engineering -- Periodicals; Engineering; Electronic journals; Periodicals; 620.005
• DOI: 10.1049/joe.2018.8350
• Languages: English
• ISSNs: 2051-3305

Abstract

Abstract : Electricity consumption data are collected more frequently by high‐quality meters in smart grids. Therefore, the load data volume and length increase dramatically. On the other hand, for advanced market‐based applications, e.g. demand response, load service entities hope to identify or classify users better. In this study, a trend‐based load characterising approach is proposed. Firstly, the concept of the candlestick chart is utilised as an innovative tool for load description. In addition, electricity trend indexes, e.g. stochastic oscillator and moving average convergence/divergence, are introduced as parameters for load characterising. Secondly, the stacked auto‐encoders are utilised to forecast the future load based on the input historical trend indexes. Case studies in Guangdong province demonstrate that the proposed trend‐based method is more applicable than existing approaches both in physical significance and accuracy.