Back to Search
Start Over
Forecasting power consumption with an activation function combined grey model: A case study of China
- Source :
- International Journal of Electrical Power & Energy Systems. 130:106977
- Publication Year :
- 2021
- Publisher :
- Elsevier BV, 2021.
-
Abstract
- Accurate medium- and long-term power consumption forecast is the premise and foundation of secure scheduling and layout planning of power system, which are conducive to the coordinated development of various power generation channels so that renewable energy generation can be improved. In view of this problem, this paper analyzes power consumption intensity in different regions in China and proposes a modified grey model with novel initial condition to enhance its forecast accuracy. Influence of initial condition in grey model is analyzed synthetically by several commonly used models, and the Inverse Square Root Unit (ISRU) function with adjustable parameters is defined as the novel initial condition to better reveal the characteristics of data growth. Particle Swarm Optimization (PSO) algorithm is adopted to calculate the introduced coefficients. Using data available from National Bureau of Statistics of China from 2007 to 2014, consumption data of 31 provinces (municipalities) from 2015 to 2018 is forecasted to attest the efficiency and adaptability of ISRU-GM(1,1). Forecast results are compared with other improved prediction models as well. Potential power consumption ability in China in the next few years from provincial perspective is studied, which guides the layout planning of power system.
- Subjects :
- Consumption (economics)
Mathematical optimization
Computer science
business.industry
020209 energy
media_common.quotation_subject
020208 electrical & electronic engineering
Scheduling (production processes)
Energy Engineering and Power Technology
Particle swarm optimization
02 engineering and technology
Adaptability
Renewable energy
Electric power system
Electricity generation
0202 electrical engineering, electronic engineering, information engineering
Initial value problem
Electrical and Electronic Engineering
business
media_common
Subjects
Details
- ISSN :
- 01420615
- Volume :
- 130
- Database :
- OpenAIRE
- Journal :
- International Journal of Electrical Power & Energy Systems
- Accession number :
- edsair.doi...........451558cf605a85453f384faaf8cbbf8f