Open Access Repository

Development a partially observable Markov decision processes-based intelligent assistant for power grids using Monte Carlo tree search

Tomin, NV, Kurbatsky, V and Negnevitsky, M ORCID: 0000-0002-5130-419X 2019 , 'Development a partially observable Markov decision processes-based intelligent assistant for power grids using Monte Carlo tree search', in M Kolcun and I Kolcunova and J Kurimsky (eds.), Proceedings of the 10th International Scientific Symposium on Electrical Power Engineering , Technical University of Kosice, Stara Lesna, Slovakia, pp. 389-393 .

Full text not available from this repository.

Abstract

Autonomous control systems will make much ”smarter” used automatic controls of modern power grids, as well as partially or completely replace the system operator, which may not be able sometimes to adequately respond to critical conditions due to psychological stress. Development of such systems can be solved by Monte-Carlo tree search algorithm that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree. We use the formalism of POMDPs (Partially Observable Markov Decision Processes) as the core of an intelligent assistant for power system control and dispatch. We demonstrate the feasibility of the approach to resolve the voltage and reactive power control in substation.

Item Type: Conference Publication
Authors/Creators:Tomin, NV and Kurbatsky, V and Negnevitsky, M
Keywords: power system, monte carlo tree search, control partially observable, markov decision processes, reinforcement learning
Journal or Publication Title: Proceedings of the 10th International Scientific Symposium on Electrical Power Engineering
Publisher: Technical University of Kosice
Copyright Information:

Copyright 2019 Elsevier

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP