Efficiency of Using Artificial Neural Network for Short-Term Load Forecasting

Svetlana Rodygina; Valentina Lyubchenko; Alexander Rodygin

doi:10.4028/www.scientific.net/AMM.792.312

Paper Titles

Phasor Measurements Application in Power Systems for Accelerated Power Flow Calculations in Emergency Control
p.286

Open Overhead Transmission Lines
p.293

Peculiarity of Determination of Economic Current Density Values for 6 – 35 kV Power Lines under Modern Conditions
p.300

Investigation of Defect Formation Process in Transmission and Distribution Equipment
p.305

Efficiency of Using Artificial Neural Network for Short-Term Load Forecasting
p.312

Decision Support System Based on the Concept of Hybrid Simulation for Dispatching Personnel of Electric Power Systems
p.317

Technical Diagnostics of Electric Equipment with the Use of Fuzzy Logic Models
p.324

Pre-Design Study for Construction of a Wind Power Station with the Capacity of 50 MW
p.330

Investigation of the Coal Char Conversion by Thermogravimetric Analysis
p.339

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 792Efficiency of Using Artificial Neural Network for...

Efficiency of Using Artificial Neural Network for Short-Term Load Forecasting

Abstract:

Using artificial neural networks (ANN) for short-term load forecasting is an efficient method to get the best result. Considered problem of short-term load forecasting shows that the accuracy of short-term forecasting models and methods significantly influences on the further planning of operating conditions at the modern electricity market. The obtained error for short-term load forecasting using the neural network algorithm is 2.78%.

You might also be interested in these eBooks

Energy Systems, Materials and Designing in Mechanical Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 792)

Pages:

312-316

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.792.312

Citation:

Cite this paper

Online since:

September 2015

Authors:

Svetlana Rodygina, Valentina Lyubchenko, Alexander Rodygin

Keywords:

Activation Function, Artificial Neural Network, Electrical Load, Forecasting, Learning Algorithm, Learning Error

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] V.A. Venikov, V.G. Zhuravlev, T.A. Filippova, Optimization of operating conditions for power plants and power systems, Energoatomizdat, Moscow, 1990 (in Russian).

Google Scholar

[2] S.V. Rodygina, Short-term electrical load forecasting for enterprises with the use of intelligent information technologies, PhD abstract, Novosibirsk, 2010 (in Russian).

Google Scholar

[3] V.A. Barinov, A.Z. Gamm, Yu.N. Kucherov, Automation of dispatching in the power industry, Edited by Yu.N. Rudenko and V.A. Semenov, Moscow Power Engineering Institute, Moscow, 2000 (in Russian).

Google Scholar

[4] V.F. Timchenko, A.M. Melamed, O.A. Skipko, Forecasting of power consumption for nonworking days, Power Stations Journal, 1987, vol. 5, pp.52-57 (in Russian).

Google Scholar