Probabilistic approach to handle uncertainties in load forecasting

Damitha K. Ranaweera; George G. Karady; R. G. Farmer

Probabilistic approach to handle uncertainties in load forecasting

Damitha K. Ranaweera, George G. Karady, R. G. Farmer

Electrical, Computer, and Energy Engineering, School of (IAFSE-ECEE)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Scopus citations

Abstract

This paper presents a novel method to include the uncertainties of weather variables in neural network based load forecasting models. The methodology is based on the probability distribution of uncertain variables. The proposed method consists of traditionally trained neural networks and a set of equations to calculate the mean forecast and the variance of the forecast. This method was tested for daily forecasts for one year. The test results indicated that in addition to the availability of the confidence interval, the new method also provides a more accurate mean forecast than traditional neural networks alone.

Original language	English (US)
Title of host publication	Proceedings of the American Power Conference
Editors	Anon
Publisher	Illinois Inst of Technology
Pages	1701-1706
Number of pages	6
Volume	57-2
State	Published - 1995
Event	Proceedings of the 57th Annual American Power Conference. Part 1 (of 3) - Chicago, IL, USA Duration: Apr 18 1995 → Apr 20 1995

Other

Other	Proceedings of the 57th Annual American Power Conference. Part 1 (of 3)
City	Chicago, IL, USA
Period	4/18/95 → 4/20/95

ASJC Scopus subject areas

Nuclear Energy and Engineering
Electrical and Electronic Engineering
Mechanical Engineering

Cite this

@inproceedings{633b490ce479450c8cb3a3c23fc9ecee,

title = "Probabilistic approach to handle uncertainties in load forecasting",

abstract = "This paper presents a novel method to include the uncertainties of weather variables in neural network based load forecasting models. The methodology is based on the probability distribution of uncertain variables. The proposed method consists of traditionally trained neural networks and a set of equations to calculate the mean forecast and the variance of the forecast. This method was tested for daily forecasts for one year. The test results indicated that in addition to the availability of the confidence interval, the new method also provides a more accurate mean forecast than traditional neural networks alone.",

author = "Ranaweera, {Damitha K.} and Karady, {George G.} and Farmer, {R. G.}",

year = "1995",

language = "English (US)",

volume = "57-2",

pages = "1701--1706",

editor = "Anon",

booktitle = "Proceedings of the American Power Conference",

publisher = "Illinois Inst of Technology",

note = "Proceedings of the 57th Annual American Power Conference. Part 1 (of 3) ; Conference date: 18-04-1995 Through 20-04-1995",

}

TY - GEN

T1 - Probabilistic approach to handle uncertainties in load forecasting

AU - Ranaweera, Damitha K.

AU - Karady, George G.

AU - Farmer, R. G.

PY - 1995

Y1 - 1995

N2 - This paper presents a novel method to include the uncertainties of weather variables in neural network based load forecasting models. The methodology is based on the probability distribution of uncertain variables. The proposed method consists of traditionally trained neural networks and a set of equations to calculate the mean forecast and the variance of the forecast. This method was tested for daily forecasts for one year. The test results indicated that in addition to the availability of the confidence interval, the new method also provides a more accurate mean forecast than traditional neural networks alone.

AB - This paper presents a novel method to include the uncertainties of weather variables in neural network based load forecasting models. The methodology is based on the probability distribution of uncertain variables. The proposed method consists of traditionally trained neural networks and a set of equations to calculate the mean forecast and the variance of the forecast. This method was tested for daily forecasts for one year. The test results indicated that in addition to the availability of the confidence interval, the new method also provides a more accurate mean forecast than traditional neural networks alone.

UR - http://www.scopus.com/inward/record.url?scp=0029211631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029211631&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029211631

VL - 57-2

SP - 1701

EP - 1706

BT - Proceedings of the American Power Conference

A2 - Anon, null

PB - Illinois Inst of Technology

T2 - Proceedings of the 57th Annual American Power Conference. Part 1 (of 3)

Y2 - 18 April 1995 through 20 April 1995

ER -

Probabilistic approach to handle uncertainties in load forecasting

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this