Paper Info
Title
Load Forecasting By Group Method Of Data Handling
Abstract
In today's competitive deregulated market, forecasting load demands and electricity sales prices is an important task for both, government and private electric utilities, as it helps them to take important decisions regarding load switching, load shedding, voltage control, network reconfiguration, energy purchasing, contract evaluation, fuel purchase and power infrastructure development. A variety of time series based techniques have been developed for accurate forecasting of load despite its nonlinear and dynamic nature. With many hidden patterns and correlations in bulk volumes of data, modern load time series forms an important part of big data analytics. In this paper, a novel self organizing machine learning technique called Group Method of Data Handling (GMDH) has been used for time series based monthly peak load forecasting. The proposed GMDH based model is first standardised using a monthly peak load data time series of a regional Chinese grid. Then, the model has been applied to forecast the peak load demand of Rajasthan state whose results have been further compared with the ones published by the Central Electricity Authority of India to showcase the superiority of the proposed technique.
Year
DOI
Venue
2019
10.1109/icccnt45670.2019.8944693
2019 10TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT)
Keywords
Field
DocType
GMDH, Big Data Analytics, Data Mining, Monthly Peak Load Forecasting, Artificial Intelligence
Industrial engineering,Electricity,Computer science,Load forecasting,Purchasing,Group method of data handling,Big data,Grid,Peak load,Load Shedding
Conference
ISSN
Citations 
PageRank 
2162-7665
0
0.34
References 
Authors
0
2
Name
Order
Citations
PageRank
Vaibhav Vaishnav100.34
Jayashri Vajpai200.34