Optimizing Energy Consumption in Stochastic Production Systems: Using a Simulation-Based Approach for Stopping Policy

2025-05-14

AI Summary

To address high uncertainty in thermal processing and low energy efficiency of static scheduling in lead-acid battery manufacturing, this paper proposes a simulation-based dynamic shutdown strategy. The method integrates Markov process modeling, Bayesian online energy consumption estimation, and full-factor discrete-event simulation to enable real-time optimization of batch processing durations. The framework robustly approaches the theoretical energy consumption lower bound even under sensor data distortion and process stochasticity, achieving a Pareto-optimal trade-off between energy consumption and inspection cost. Experimental results demonstrate 14–25% energy reduction compared to the industry’s current baseline, significant superiority over static optimization approaches, and—under certain operating conditions—statistical performance equivalence to an ideal scenario with perfect energy consumption knowledge.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In response to the escalating need for sustainable manufacturing, this study introduces a Simulation-Based Approach (SBA) to model a stopping policy for energy-intensive stochastic production systems, developed and tested in a real-world industrial context. The case company - an energy-intensive lead-acid battery manufacturer - faces significant process uncertainty in its heat-treatment operations, making static planning inefficient. To evaluate a potential sensor-based solution, the SBA leverages simulated sensor data (using a Markovian model) to iteratively refine Bayesian energy estimates and dynamically adjust batch-specific processing times. A full-factorial numerical simulation, mirroring the company's 2024 heat-treatment process, evaluates the SBA's energy reduction potential, configuration robustness, and sensitivity to process uncertainty and sensor distortion. Results are benchmarked against three planning scenarios: (1) Optimized Planned Processing Times (OPT); (2) the company's Current Baseline Practice; and (3) an Ideal Scenario with perfectly known energy requirements. SBA significantly outperforms OPT across all tested environments and in some cases even performs statistically equivalent to an Ideal Scenario. Compared to the Current Baseline Practice, energy input is reduced by 14-25%, depending on uncertainty and sensor accuracy. A Pareto analysis further highlights SBA's ability to balance energy and inspection-labour costs, offering actionable insights for industrial decision-makers.

Problem

• Optimizing energy use in stochastic production via simulation
• Reducing process uncertainty in battery heat-treatment operations
• Balancing energy and labor costs with dynamic stopping policies

Innovation

• Simulation-Based Approach for stopping policy optimization
• Bayesian energy estimates with simulated sensor data
• Dynamic adjustment of batch-specific processing times