B
Bert Claessens
Researcher at Flemish Institute for Technological Research
Publications - 76
Citations - 3233
Bert Claessens is an academic researcher from Flemish Institute for Technological Research. The author has contributed to research in topics: Reinforcement learning & Smart grid. The author has an hindex of 28, co-authored 75 publications receiving 2674 citations. Previous affiliations of Bert Claessens include Katholieke Universiteit Leuven & United States Department of Energy.
Papers
More filters
Journal ArticleDOI
Flexibility of a combined heat and power system with thermal energy storage for district heating
Thomas Nuytten,Thomas Nuytten,Bert Claessens,Bert Claessens,Kristof Paredis,Johan Van Bael,Johan Van Bael,Daan Six,Daan Six +8 more
TL;DR: In this article, a model that determines the theoretical maximum of flexibility of a combined heat and power system coupled with a thermal energy storage solution that can be either centralized or decentralized is presented.
Journal ArticleDOI
Residential Demand Response of Thermostatically Controlled Loads Using Batch Reinforcement Learning
Frederik Ruelens,Bert Claessens,Stijn Vandael,Bart De Schutter,Robert Babuska,Ronnie Belmans +5 more
TL;DR: The experiments show that batch RL techniques provide a valuable alternative to model-based controllers and that they can be used to construct both closed-loop and open-loop policies.
Journal ArticleDOI
A Scalable Three-Step Approach for Demand Side Management of Plug-in Hybrid Vehicles
TL;DR: Results show that the proposed three-step approach is able to charge PHEVs with comparable quality to optimal, centrally computed charging plans, while significantly improving scalability.
Journal ArticleDOI
The dimensioning of PV-battery systems depending on the incentive and selling price conditions
Grietus Mulder,Grietus Mulder,Daan Six,Bert Claessens,Thijs Broes,Noshin Omar,Joeri Van Mierlo +6 more
TL;DR: In this paper, the optimal PV-battery system is determined as a function of the remuneration (discerning a subsidised region, a "market" price region and no fees at all), the investment year (2012, 2017 and 2021) and the electricity price increase rate (0, 4, 6%) (including the general inflation rate).
Journal ArticleDOI
Reinforcement Learning of Heuristic EV Fleet Charging in a Day-Ahead Electricity Market
TL;DR: This paper addresses the problem of defining a day-ahead consumption plan for charging a fleet of electric vehicles (EVs), and following this plan during operation, and shows that the approach is able to find a day's consumption plan with comparable quality to the benchmark solution, without requiring an exact day- Ahead model of each EVs charging flexibility.