Title: Power consumption prediction with K-nearest-neighbours and XGBoost algorithm

Authors: Zheng Liu; Qingsheng Kong; Lirong Yang

Addresses: Intelligent Control Research Lab, Department of Electronic Engineering, Fudan University, Shanghai 200433, China ' Intelligent Control Research Lab, Department of Electronic Engineering, Fudan University, Shanghai 200433, China ' Bao Wu Iron and Steel Group, Shanghai 200941, China

Abstract: Power consumption problem is an important part of economic development. Nowadays, power consumption of companies is rocketing as time goes. Power consumption prediction is an essential problem for power companies before supplying power. In this paper, we solve a power consumption prediction problem in Yangzhong High Tech Zone with K-nearest-neighbours and XGBoost algorithm. More importantly, we research on useful features for power consumption problems that can guide power companies to supply appropriate amount of power. It will play an important role in regional construction in future.

Keywords: energy consumption prediction; time analysis; KNN; XGBoost.

DOI: 10.1504/IJWMC.2018.097162

International Journal of Wireless and Mobile Computing, 2018 Vol.15 No.4, pp.374 - 381

Received: 11 Jan 2018
Accepted: 26 Aug 2018
Published online: 02 Jan 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article