Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Summary With the grid's evolution, the end‐users demand becomes more vital for demand side management (DSM). Accurate load forecasting (LF) is critical for power system planning and using advanced demand response (DR) strategies. To design efficient and precise LF, information about various fac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International transactions on electrical energy systems Jg. 31; H. 9
Hauptverfasser: Waseem, Muhammad, Lin, Zhenzhi, Liu, Shengyuan, Jinai, Zhang, Rizwan, Mian, Sajjad, Intisar Ali
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Hoboken John Wiley & Sons, Inc 01.09.2021
Schlagworte:
Air conditioners
air conditioners (ACs)
Algorithms
Coefficient of variation
Correlation coefficient
Correlation coefficients
demand response (DR)
Economic forecasting
Electric power systems
electrical demand
load forecasting (LF)
optimal‐Bayesian regularization algorithm (BRA)
Regularization
Strategy
ISSN:2050-7038, 2050-7038
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Summary With the grid's evolution, the end‐users demand becomes more vital for demand side management (DSM). Accurate load forecasting (LF) is critical for power system planning and using advanced demand response (DR) strategies. To design efficient and precise LF, information about various factors that influence end‐users demand is required. In this paper, the impact of different factors on electrical demand and capacity of climatic factors existence and their variation is discussed and analysed. The Pearson correlation coefficient (PCC) is utilized to express the degree of electric demand correlation with metrological and calendar factors. Then, the optimal‐Bayesian regularization algorithm (BRA) based on ANN for LF is presented. The effect of the number of neurons in hidden layers on output is observed to select the most appropriate option. Additionally, heating degree days (HDDs) and cooling degree days (CDDs) indices are investigated to consider the impact of air conditioners' (ACs) loads in different seasons. Case studies on data from Dallas, Texas, USA, are used to demonstrate the influence of various factors on electrical demand. The proposed algorithm's effectiveness for LF and error formulations shows that optimal‐BRA‐enabled LF presents better accuracy than state‐of‐the‐art approaches. Thus, the proposed electric demand prediction strategy could help the system operator know DR potential at different times better, leading to optimal system resources dispatching through DR actions. This paper investigates the impact of different metrological and calendar factors on electrical demand in terms of the Pearson correlation coefficient. The optimal‐Bayesian regularization algorithm (BRA) based on ANN for load forecasting (LF) is presented and analysed. Furthermore, heating degree days and cooling degree days indices are examined to consider Air Conditioners loads' impact in different seasons. The proposed BRA based LF strategy could help the system operator to initiate different demand response (DR) actions and optimal dispatch of distributed energy resources.
Bibliographie:Funding information
National Natural Science Foundation of China, Grant/Award Number: 52077195
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2050-7038
2050-7038
DOI:10.1002/2050-7038.12967