Fig. 1
From: A framework for researching energy optimization of factory operations
Structure of the \(eta\_utility\) framework. The rolling horizon optimization process is shown on the top left. Here, the algorithm selects actions \(A_k\) based on the current system state \(S_t\) and sends them to the environment, whereupon a new system state \(S_t+1\) is established. In DRL algorithms, a reward signal \(R_t\) or \(R_t+1\) is also transferred, which describes the quality of a system state. The modules are shown on the bottom and right