Published July 1, 2018 | Version v1
Journal article Metadata-only

Application of Deep Neural Network in Monthly Electric Demand Forecasting

Creators

  • 1. Qindao Power Supply Company of State Grid Shandong Electric Power Company, Qingdao 266002 (China)
  • 2. School of Shandong University, Jinan 250061 (China)

Description

According to the load characteristics of electric power system in medium term and the nonlinear identification function of DNN, this paper proposed a monthly electric demand forecasting method using the depth of neural network, used in qingdao province's actual users monthly electricity consumption data to predict the future. The experimental results show that the algorithm has good feasibility and accuracy. (paper)

Availability note (English)

Available from http://dx.doi.org/10.1088/1757-899X/394/4/042123

Additional details

Identifiers

DOI
10.1088/1757-899X/394/4/042123;

Publishing Information

Journal Title
IOP Conference Series. Materials Science and Engineering (Online)
Journal Volume
394
Journal Issue
4
Journal Page Range
[5 p.]
ISSN
1757-899X

Conference

Title
5. International Conference on Advanced Composite Materials and Manufacturing Engineering
Dates
16-17 Jun 2018
Place
Xishuangbanna (China)

INIS

Country of Publication
United Kingdom
Country of Input or Organization
International Atomic Energy Agency (IAEA)
INIS RN
52092061
Subject category
S29: ENERGY PLANNING, POLICY AND ECONOMY; S97: MATHEMATICAL METHODS AND COMPUTING;
Resource subtype / Literary indicator
Conference
Descriptors DEI
ALGORITHMS; ELECTRIC POWER; ELECTRICITY; ENERGY DEMAND; FORECASTING; LOAD ANALYSIS; NEURAL NETWORKS
Descriptors DEC
DEMAND; MATHEMATICAL LOGIC; POWER