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

Wind power is becoming an increasingly important source of renewable energyworldwide. However, wind farm power control faces significant challenges due tothe high system complexity inherent in these farms. A novel communication-basedmulti-agent deep reinforcement learning large-scale wind farm multivariatecontrol is proposed to handle this challenge and maximize power output. A windfarm multivariate power model is proposed to study the influence of windturbines (WTs) wake on power. The multivariate model includes axial inductionfactor, yaw angle, and tilt angle controllable variables. The hierarchicalcommunication multi-agent proximal policy optimization (HCMAPPO) algorithm isproposed to coordinate the multivariate large-scale wind farm continuouscontrols. The large-scale wind farm is divided into multiple wind turbineaggregators (WTAs), and neighboring WTAs can exchange information throughhierarchical communication to maximize the wind farm power output. Simulationresults demonstrate that the proposed multivariate HCMAPPO can significantlyincrease wind farm power output compared to the traditional PID control,coordinated model-based predictive control, and multi-agent deep deterministicpolicy gradient algorithm. Particularly, the HCMAPPO algorithm can be trainedwith the environment based on the thirteen-turbine wind farm and effectivelyapplied to larger wind farms. At the same time, there is no significantincrease in the fatigue damage of the wind turbine blade from the wake controlas the wind farm scale increases. The multivariate HCMAPPO control can realizethe collective large-scale wind farm maximum power output.

Collective Large-scale Wind Farm Multivariate Power Output Control Based on Hierarchical Communication Multi-Agent Proximal Policy Optimization