Better wind forecasting using Evolutionary Neural Architecture search driven Green Deep Learning

Mitra, Kishalay (2023) Better wind forecasting using Evolutionary Neural Architecture search driven Green Deep Learning. Expert Systems with Applications, 214. p. 119063. ISSN 0957-4174

Text
1-s2.0-S0957417422020814-main.pdf - Published Version
Download (18MB)

Abstract

Climate Change heavily impacts global cities, the downsides of which can be minimized by adopting renewables like wind energy. However, despite its advantages, the nonlinear nature of wind renders the forecasting approaches to design and control wind farms ineffective. To expand the research horizon, the current study a) analyses and performs statistical decomposition of real-world wind time-series data, b) presents the application of Long Short-Term Memory (LSTM) networks, Nonlinear Auto-Regressive (NAR) models, and Wavelet Neural Networks (WNN) as efficient models for accurate wind forecasting with a comprehensive comparison among them to justify their application and c) proposes an evolutionary multi-objective strategy for Neural Architecture Search (NAS) to minimize the computational cost associated with training and inferring the networks which form the central theme of Green Deep Learning. Balancing the trade-off between parsimony and prediction accuracy, the proposed NAS strategy could optimally design NAR, WNN, and LSTM models with a mean test accuracy of 99%. The robust methodologies discussed in this work not only accurately model the wind behavior but also provide a green & generic approach for designing Deep Neural Networks.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Mitra, Kishalay	http://orcid.org/0000-0001-5660-6878

Item Type:

Article

Uncontrolled Keywords:

Effective wind farm design; Green deep learning; Neural architecture search; Renewable energy; Wind characteristics forecasting; Long short-term memory; Climate change; Deep neural networks; Economic and social effects; Electric utilities; Network architecture; Time series analysis; Wavelet decomposition; Weather forecasting; Wind power; Effective wind farm design; Green deep learning; Neural architecture search; Neural architectures; Neural-networks; Renewable energies; Wind characteristic forecasting; Wind characteristics; Wind farm; Wind forecasting

Subjects:

Chemical Engineering
Chemical Engineering > Ceramic and allied technologies

Divisions:

Department of Chemical Engineering

Depositing User:

Mr Nigam Prasad Bisoyi

Date Deposited:

26 Aug 2023 11:04

Last Modified:

26 Aug 2023 11:04

URI:

http://raiithold.iith.ac.in/id/eprint/11623