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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Artificial Intelligence (AI) techniques continue to broaden acrossgovernmental and public sectors, such as power and energy - which serve ascritical infrastructures for most societal operations. However, due to therequirements of reliability, accountability, and explainability, it is risky todirectly apply AI-based methods to power systems because society cannot affordcascading failures and large-scale blackouts, which easily cost billions ofdollars. To meet society requirements, this paper proposes a methodology todevelop, deploy, and evaluate AI systems in the energy sector by: (1)understanding the power system measurements with physics, (2) designing AIalgorithms to forecast the need, (3) developing robust and accountable AImethods, and (4) creating reliable measures to evaluate the performance of theAI model. The goal is to provide a high level of confidence to energy utilityusers. For illustration purposes, the paper uses power system event forecasting(PEF) as an example, which carefully analyzes synchrophasor patterns measuredby the Phasor Measurement Units (PMUs). Such a physical understanding leads toa data-driven framework that reduces the dimensionality with physics andforecasts the event with high credibility. Specifically, for dimensionalityreduction, machine learning arranges physical information from differentdimensions, resulting inefficient information extraction. For eventforecasting, the supervised learning model fuses the results of differentmodels to increase the confidence. Finally, comprehensive experimentsdemonstrate the high accuracy, efficiency, and reliability as compared to otherstate-of-the-art machine learning methods.

The Powerful Use of AI in the Energy Sector: Intelligent Forecasting