SWS Academic Research eLibraryEarth & Planetary Sciences

Scholarly record

ANN BASED MONTHLY POWER CONSUMPTION FORECASTING. CASE STUDY FOR A ROMANIAN ELECTRIC ENERGY DISTRIBUTION OPERATOR

Constantin Bărbulescu

First published: 2018-11-20https://doi.org/10.5593/sgem2018v/4.3/s11.054View metrics

Abstract

The load forecasting problem is very important for every distribution system operator. The network evolution, associated behavior, related policies, etc. are correlated with this subject. Thepaper is focusing on monthly load curves forecasting. Artificial intelligence based methods such as artificial neural networks and also conventional methods are appliedin order to perform the forecast. A comparison is accomplished in order to provide thebest approach. To achieve this goal several indices have been computed and discussed.A large set of load consumption data provided by the distribution system operator involved are used within the current paper. All the numerical results that are going tobe presented have been obtained using own developed software-tools. The distribution network managedby the involved distribution network operator is characterized by high degree of renewablesources penetration degree. The load curves are defined based on the power consumptionvalues for a specific hour and day for each of the 12 months of the year. The results are related to the 9:00 a.m. and 9:00 p.m. hours of the last Thursday, also of the 1st Tuesday and the 2ndWednesday of each month. Data are knownfor the period 2009-2016. The first 6 years (2009-2014) have been used in order to perform the forecast. The last twoones have been used in order to validate to forecast.

Publication Impact Profile

PlumX
  • Captures
  • Mendeley - Readers: 2
PLUMX see details

Publication details

Title
ANN BASED MONTHLY POWER CONSUMPTION FORECASTING. CASE STUDY FOR A ROMANIAN ELECTRIC ENERGY DISTRIBUTION OPERATOR
Authors
Constantin Bărbulescu
Proceedings
SGEM International Multidisciplinary Scientific GeoConference EXPO Proceedings; 18th SGEM International Multidisciplinary Scientific GeoConference SGEM2018, Energy and Clean Technologies
Publisher
STEF92 Technology
Year
2018
Pages
457-464
SWS Citekey
BARBULESCU201811457464
ISSN
1314-2704
ISBN
978-619-7408-70-6
Language
en
Publication type
Conference Paper
Keywords
load curveforecastartificial neural networksunconventional methods.
References0
0references registered for this publication

Structured references will appear here after the reference import pass. The count is preserved now so the scholarly record is not incomplete.

View or Download full articleAccess options
Full paper accessChoose SWS login, librarian support, or instant article download.

SWS access login

Login as SWS Scientific Committee

Authors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.

For librarian assistance: [email protected]

Purchase Instant Access

48-hour online accessComing soon
Online-only accessComing soon
Download the full article in PDF formatEUR 35
  • Article can be downloaded after successful payment.
  • Article may be used according to SWS library access terms.
  • Article cannot be redistributed.
Get full paper

Back to publication list