Lifelong Control of Off-grid Microgrid with Model Based Reinforcement Learning

The lifelong control problem of an off-grid microgrid Centralized microgrid control is usually decomposed in four is composed of two tasks, namely estimation tasks: i) estimating the parameters of the microgrid devices of the condition of the microgrid devices and operational (for instance the charge efficiency of a battery storage device planning accounting for the uncertainties as a function of the state of charge and temperature, or the by forecasting the future consumption and actual capacity of a battery after a number of cycles), ii) the renewable production. The main challenge forecasting the consumption and the renewable production, for the effective control arises from the various iii) operational planning to anticipate weather effects and changes that take place over time. In this paper, human activities, and iv) real-time control to adapt planned we present an open-source reinforcement framework decisions to the current situation. These tasks are preformed for the modeling of an off-grid microgrid sequentially during the lifetime of a microgrid in order to for rural electrification. The lifelong control problem achieve near optimal operation and to maximize the benefits of an isolated microgrid is formulated as a arising from distributed generation.