Active Inference Meeting Energy-Efficient Control of Parallel and Identical Machines

TL;DR

This paper explores using deep active inference, a neuroscience-inspired probabilistic framework, to develop energy-efficient control agents for manufacturing systems, specifically focusing on parallel identical machines.

Contribution

It introduces tailored enhancements like multi-step transition and hybrid horizon methods to improve deep active inference agents for energy-efficient machine control.

Findings

Enhanced control performance with proposed methods

Effective energy savings demonstrated in experiments

Potential for scalable manufacturing system control

Abstract

We investigate the application of active inference in developing energy-efficient control agents for manufacturing systems. Active inference, rooted in neuroscience, provides a unified probabilistic framework integrating perception, learning, and action, with inherent uncertainty quantification elements. Our study explores deep active inference, an emerging field that combines deep learning with the active inference decision-making framework. Leveraging a deep active inference agent, we focus on controlling parallel and identical machine workstations to enhance energy efficiency. We address challenges posed by the problem's stochastic nature and delayed policy response by introducing tailored enhancements to existing agent architectures. Specifically, we introduce multi-step transition and hybrid horizon methods to mitigate the need for complex planning. Our experimental results demonstrate the effectiveness of these enhancements and highlight the potential of the active inference-based approach.