This work discusses the development of a multi-physics simulated model, in the frame of the decarbonization and energy efficiency objectives of the European Commission. Its central feature is the interconnection, through a microgrid, of a distributed PV installation and of several electric dispatchable loads, thus powering a Collective Self-Consumption network. The simulator presented within this document aims to serve as a technological enabler for the design and testing of On-Site DR strategies, which actuate directly on the connection status of the loads, before their deployment on the target, real-world systems. The simulator supports the design and validation of such strategies by generating realistic simulated data of certain loads that present monitoring difficulties, taking into account online, real external weather conditions. All the elements described and modeled in the current work belong to a real-world installation, which is a university campus—ESTIA, Bidart, France— composed by several buildings with DER.

No abstract

Warehouse Management Systems have been evolving and improving thanks to new Data Intelligence techniques. However, many current optimizations have been applied to specific cases or are in great need of manual interaction. Here is where Reinforcement Learning techniques come into play, providing automatization and adaptability to current optimization policies. In this paper, we present Storehouse, a customizable environment that generalizes the definition of warehouse simulations for Reinforcement Learning. We also validate this environment against state-of-the-art reinforcement learning algorithms and compare these results to human and random policies.

No abstract