Autonomous Reservoir Management with Deep Reinforcement Learning

Summary The introduction of intelligent completion systems opens the opportunity to approach reservoir optimization as optimal control problem. Moreover, improving in Deep Reinforcement Learning make viable solving the optimal control problem to achieve autonomous control. We show how using intelligent completions and reservoir modeling, the task of autonomous choke control is solved. The present article is one of the first attempts to analyze and compare efficiency of novel DRL algorithms applied to autonomous reservoir control problem.