English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent years have witnessed an exponential growth in developing deep learning(DL) models for the time-series electricity forecasting in power systems.However, most of the proposed models are designed based on the designers'inherent knowledge and experience without elaborating on the suitability of theproposed neural architectures. Moreover, these models cannot be self-adjustedto the dynamically changing data patterns due to an inflexible design of theirstructures. Even though several latest studies have considered application ofthe neural architecture search (NAS) technique for obtaining a network with anoptimized structure in the electricity forecasting sector, their trainingprocess is quite time-consuming, computationally expensive and not intelligent,indicating that the NAS application in electricity forecasting area is still atan infancy phase. In this research study, we propose an intelligent automatedarchitecture search (IAAS) framework for the development of time-serieselectricity forecasting models. The proposed framework contains two primarycomponents, i.e., network function-preserving transformation operation andreinforcement learning (RL)-based network transformation control. In the firstcomponent, we introduce a theoretical function-preserving transformation ofrecurrent neural networks (RNN) to the literature for capturing the hiddentemporal patterns within the time-series data. In the second component, wedevelop three RL-based transformation actors and a net pool to intelligentlyand effectively search a high-quality neural architecture. After conductingcomprehensive experiments on two publicly-available electricity load datasetsand two wind power datasets, we demonstrate that the proposed IAAS frameworksignificantly outperforms the ten existing models or methods in terms offorecasting accuracy and stability.

An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development