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

Volt-var control (VVC) is the problem of operating power distribution systemswithin healthy regimes by controlling actuators in power systems. Existingworks have mostly adopted the conventional routine of representing the powersystems (a graph with tree topology) as vectors to train deep reinforcementlearning (RL) policies. We propose a framework that combines RL with graphneural networks and study the benefits and limitations of graph-based policy inthe VVC setting. Our results show that graph-based policies converge to thesame rewards asymptotically however at a slower rate when compared to vectorrepresentation counterpart. We conduct further analysis on the impact of bothobservations and actions: on the observation end, we examine the robustness ofgraph-based policy on two typical data acquisition errors in power systems,namely sensor communication failure and measurement misalignment. On the actionend, we show that actuators have various impacts on the system, thus using agraph representation induced by power systems topology may not be the optimalchoice. In the end, we conduct a case study to demonstrate that the choice ofreadout function architecture and graph augmentation can further improvetraining performance and robustness.

A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems