-
Read more: Recurrent neural networks, hidden states and beliefs in partially observable environments
Despite achieving impressive performances on various tasks, modern artificial intelligence (AI) systems have become complex black box models. A growing body of work aspires to open the box and understand its internal functioning. In this new article (Lambrechts et al.,…
-
The Graph-Based Optimization Modeling Language (GBOML)
Read more: The Graph-Based Optimization Modeling Language (GBOML)The decarbonisation of energy systems is one of the main challenges of our century. Finding the optimal technological mix to achieve that goal is a major concern for policy and decision makers alike. These problems are known as energy system…
-
Gym-ANM: Reinforcement learning environments for active network management tasks in electricity distribution systems
Read more: Gym-ANM: Reinforcement learning environments for active network management tasks in electricity distribution systemsDownload the paper Summary: Active network management (ANM) of electricity distribution networks include many complex stochastic sequential optimization problems. These problems need to be solved for integrating renewable energies and distributed storage into future electrical grids. In this work, we…
-
Remote Renewable Hubs for Carbon-Neutral Fuel Production
Read more: Remote Renewable Hubs for Carbon-Neutral Fuel ProductionDecarbonising sectors such as aviation, heating and industry has proved difficult via direct electrification. Hence, the synthesis of carbon-neutral fuels and feedstocks from renewable electricity has received much attention in recent years. However, in European countries such as Belgium, the…
-
Sector coupling for the energy transition: the case of the Dutch energy system
Read more: Sector coupling for the energy transition: the case of the Dutch energy systemThe topic of sector coupling and the role it may play in the energy transition has recently received a great deal of attention in European energy policy circles. In particular, power-to-gas technologies, which enable the production of hydrogen via water…
-
An Artificial Intelligence Solution for Electricity Procurement in Forward Markets
Read more: An Artificial Intelligence Solution for Electricity Procurement in Forward MarketsDownload the research paper Retailers and major consumers of electricity generally purchase a critical percentage of their estimated electricity needs years ahead on the forward markets. This long-term electricity procurement task consists of determining when to buy electricity so that…
-
An Application of Deep Reinforcement Learning to Algorithmic Trading
Read more: An Application of Deep Reinforcement Learning to Algorithmic TradingDownload the research paper This research paper presents a novel deep reinforcement learning (DRL) solution to the decision-making problem behind algorithmic trading in the stock markets: selecting the appropriate trading action (buy, hold or sell shares) without human intervention. Naturally,…
-
A Deep Reinforcement Learning Framework for Continuous Intraday Market Bidding
Read more: A Deep Reinforcement Learning Framework for Continuous Intraday Market BiddingDownload the research paper This paper addresses a key issue in the context of the Energy Transition: the computation of trading strategies for valorizing storage units in markets with large renewable energy integration. In particular, we focus on (short-term) intra-day…
-
Annulation de la loi de prolongation des centrales nucléaires de Doel 1 et Doel 2. Et maintenant ?
Read more: Annulation de la loi de prolongation des centrales nucléaires de Doel 1 et Doel 2. Et maintenant ?La cour constitutionnelle annule la loi prolongation de Doel 1 et Doel 2 votée en 2015. Cette loi prolongeait ces deux unités jusqu’en 2025. Raison de l’annulation : aucune consultation du public et aucune étude d’incidence environnementale n’ont été réalisées…
-
La transition énergétique peut réunir tous les Belges
Read more: La transition énergétique peut réunir tous les BelgesTribune publiée dans le journal L’Echo le 29-02-2020. Téléchargez une version pdf. La discorde n’est souvent que le reflet d’un manque de rationalité et la rationalité peut émerger à partir de situations bien chiffrées. Venons-en donc de manière chiffrée au problème…