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

In Volt/Var control (VVC) of active distribution networks(ADNs), both slowtimescale discrete devices (STDDs) and fast timescale continuous devices(FTCDs) are involved. The STDDs such as on-load tap changers (OLTC) and FTCDssuch as distributed generators should be coordinated in time sequence. Such VCCis formulated as a two-timescale optimization problem to jointly optimize FTCDsand STDDs in ADNs. Traditional optimization methods are heavily based onaccurate models of the system, but sometimes impractical because of theirunaffordable effort on modelling. In this paper, a novel bi-level off-policyreinforcement learning (RL) algorithm is proposed to solve this problem in amodel-free manner. A Bi-level Markov decision process (BMDP) is defined todescribe the two-timescale VVC problem and separate agents are set up for theslow and fast timescale sub-problems. For the fast timescale sub-problem, weadopt an off-policy RL method soft actor-critic with high sample efficiency.For the slow one, we develop an off-policy multi-discrete soft actor-critic(MDSAC) algorithm to address the curse of dimensionality with various STDDs. Tomitigate the non-stationary issue existing the two agents' learning processes,we propose a multi-timescale off-policy correction (MTOPC) method by adoptingimportance sampling technique. Comprehensive numerical studies not onlydemonstrate that the proposed method can achieve stable and satisfactoryoptimization of both STDDs and FTCDs without any model information, but alsosupport that the proposed method outperforms existing two-timescale VVCmethods.

Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices