A Forecasting Method of Electricity Sales Considering the User Churn Rate in a Power Market Environment

Zhaoyang Qu, Wanxin Wang, Nan Qu, Yuqing Liu, Hongbo Lv, Kewei Hu, Jianyou Yu, Manyang Gao, Jiajun Song

Research output: Contribution to journalArticle

Abstract

In order to improve the accuracy of forecasts of the electricity sales of power sales companies, a depth forecast model of electricity sales based on the characteristics of the power market is proposed. First, based on survival analysis, the calculation method of the user churn rate in the electricity market is given, and the number of users at a certain moment in the future is predicted. Then, users’ electricity consumption that calculated by the deep belief network and the predicted quantity of users are combined to design a forecast model of electricity sales. Finally, the model is solved utilizing the weighting algorithm of adaptive inertia. The analysis of the example shows that the proposed method achieves a significant improvement in the accuracy of power sales forecasting.

Original languageEnglish
Pages (from-to)1585-1596
JournalJournal of Electrical Engineering and Technology
Volume14
Issue number4
Early online date29 May 2019
DOIs
Publication statusPublished - 31 Jul 2019

Keywords

  • Churn rate of users
  • Deep belief network
  • Electricity market
  • Electricity sales

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A Forecasting Method of Electricity Sales Considering the User Churn Rate in a Power Market Environment. / Qu, Zhaoyang; Wang, Wanxin; Qu, Nan; Liu, Yuqing; Lv, Hongbo; Hu, Kewei; Yu, Jianyou; Gao, Manyang; Song, Jiajun.

In: Journal of Electrical Engineering and Technology, Vol. 14, No. 4, 31.07.2019, p. 1585-1596.

Research output: Contribution to journalArticle

Qu, Zhaoyang ; Wang, Wanxin ; Qu, Nan ; Liu, Yuqing ; Lv, Hongbo ; Hu, Kewei ; Yu, Jianyou ; Gao, Manyang ; Song, Jiajun. / A Forecasting Method of Electricity Sales Considering the User Churn Rate in a Power Market Environment. In: Journal of Electrical Engineering and Technology. 2019 ; Vol. 14, No. 4. pp. 1585-1596.
@article{a14ffd536a214e2ebb021c5e5f37aec8,
title = "A Forecasting Method of Electricity Sales Considering the User Churn Rate in a Power Market Environment",
abstract = "In order to improve the accuracy of forecasts of the electricity sales of power sales companies, a depth forecast model of electricity sales based on the characteristics of the power market is proposed. First, based on survival analysis, the calculation method of the user churn rate in the electricity market is given, and the number of users at a certain moment in the future is predicted. Then, users’ electricity consumption that calculated by the deep belief network and the predicted quantity of users are combined to design a forecast model of electricity sales. Finally, the model is solved utilizing the weighting algorithm of adaptive inertia. The analysis of the example shows that the proposed method achieves a significant improvement in the accuracy of power sales forecasting.",
keywords = "Churn rate of users, Deep belief network, Electricity market, Electricity sales",
author = "Zhaoyang Qu and Wanxin Wang and Nan Qu and Yuqing Liu and Hongbo Lv and Kewei Hu and Jianyou Yu and Manyang Gao and Jiajun Song",
year = "2019",
month = "7",
day = "31",
doi = "10.1007/s42835-019-00215-9",
language = "English",
volume = "14",
pages = "1585--1596",
journal = "Journal of Electrical Engineering and Technology",
issn = "1975-0102",
publisher = "Springer, Singapore",
number = "4",

}

TY - JOUR

T1 - A Forecasting Method of Electricity Sales Considering the User Churn Rate in a Power Market Environment

AU - Qu, Zhaoyang

AU - Wang, Wanxin

AU - Qu, Nan

AU - Liu, Yuqing

AU - Lv, Hongbo

AU - Hu, Kewei

AU - Yu, Jianyou

AU - Gao, Manyang

AU - Song, Jiajun

PY - 2019/7/31

Y1 - 2019/7/31

N2 - In order to improve the accuracy of forecasts of the electricity sales of power sales companies, a depth forecast model of electricity sales based on the characteristics of the power market is proposed. First, based on survival analysis, the calculation method of the user churn rate in the electricity market is given, and the number of users at a certain moment in the future is predicted. Then, users’ electricity consumption that calculated by the deep belief network and the predicted quantity of users are combined to design a forecast model of electricity sales. Finally, the model is solved utilizing the weighting algorithm of adaptive inertia. The analysis of the example shows that the proposed method achieves a significant improvement in the accuracy of power sales forecasting.

AB - In order to improve the accuracy of forecasts of the electricity sales of power sales companies, a depth forecast model of electricity sales based on the characteristics of the power market is proposed. First, based on survival analysis, the calculation method of the user churn rate in the electricity market is given, and the number of users at a certain moment in the future is predicted. Then, users’ electricity consumption that calculated by the deep belief network and the predicted quantity of users are combined to design a forecast model of electricity sales. Finally, the model is solved utilizing the weighting algorithm of adaptive inertia. The analysis of the example shows that the proposed method achieves a significant improvement in the accuracy of power sales forecasting.

KW - Churn rate of users

KW - Deep belief network

KW - Electricity market

KW - Electricity sales

UR - http://www.scopus.com/inward/record.url?scp=85066610242&partnerID=8YFLogxK

U2 - 10.1007/s42835-019-00215-9

DO - 10.1007/s42835-019-00215-9

M3 - Article

VL - 14

SP - 1585

EP - 1596

JO - Journal of Electrical Engineering and Technology

JF - Journal of Electrical Engineering and Technology

SN - 1975-0102

IS - 4

ER -