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

Load forecasting is a crucial topic in energy management systems (EMS) due toits vital role in optimizing energy scheduling and enabling more flexible andintelligent power grid systems. As a result, these systems allow power utilitycompanies to respond promptly to demands in the electricity market. Deeplearning (DL) models have been commonly employed in load forecasting problemssupported by adaptation mechanisms to cope with the changing pattern ofconsumption by customers, known as concept drift. A drift magnitude thresholdshould be defined to design change detection methods to identify drifts. Whilethe drift magnitude in load forecasting problems can vary significantly overtime, existing literature often assumes a fixed drift magnitude threshold,which should be dynamically adjusted rather than fixed during system evolution.To address this gap, in this paper, we propose a dynamic drift-adaptive LongShort-Term Memory (DA-LSTM) framework that can improve the performance of loadforecasting models without requiring a drift threshold setting. We integrateseveral strategies into the framework based on active and passive adaptationapproaches. To evaluate DA-LSTM in real-life settings, we thoroughly analyzethe proposed framework and deploy it in a real-world problem through acloud-based environment. Efficiency is evaluated in terms of the predictionperformance of each approach and computational cost. The experiments showperformance improvements on multiple evaluation metrics achieved by ourframework compared to baseline methods from the literature. Finally, we presenta trade-off analysis between prediction performance and computational costs.

DA-LSTM: A Dynamic Drift-Adaptive Learning Framework for Interval Load Forecasting with LSTM Networks