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

Electrical energy is essential in today's society. Accurate electrical loadforecasting is beneficial for better scheduling of electricity generation andsaving electrical energy. In this paper, we propose theory-guided deep-learningload forecasting 2.0 (TgDLF2.0) to solve this issue, which is an improvedversion of the theory-guided deep-learning framework for load forecasting viaensemble long short-term memory (TgDLF). TgDLF2.0 introduces the deep-learningmodel Transformer and transfer learning on the basis of dividing the electricalload into dimensionless trends and local fluctuations, which realizes theutilization of domain knowledge, captures the long-term dependency of the loadseries, and is more appropriate for realistic scenarios with scarce samples.Cross-validation experiments on different districts show that TgDLF2.0 isapproximately 16% more accurate than TgDLF and saves more than half of thetraining time. TgDLF2.0 with 50% weather noise has the same accuracy as TgDLFwithout noise, which proves its robustness. We also preliminarily mine theinterpretability of Transformer in TgDLF2.0, which may provide future potentialfor better theory guidance. Furthermore, experiments demonstrate that transferlearning can accelerate convergence of the model in half the number of trainingepochs and achieve better performance.

TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learning