New MILP algorithm lifts battery levels from 2.7% to 68.6%

A new study published on arXiv (arXiv:2607.01462) tackles the challenge of managing distributed battery networks under connectivity and energy constraints. The authors—Pranay KC, Amin Taghieh, Maria Angel Palacios, Mohammadali Rashidioun, Petras Swissler, and SangWoo Park—introduce a battery-aware topology optimization algorithm that extends the GeoSteiner framework with a tailored Mixed-Integer Linear Program (MILP) for Full Steiner Tree (FST) aggregation. The formulation minimizes network length while prioritizing low-battery terminals through a weighted objective subject to a global budget constraint, enabling partial network formation under realistic resource limits. An overlap-correction term prevents double-counting when selected trees share terminals, and a graph-distance metric penalizes frequent topology changes, reducing reconfiguration cost by 72.2% compared to a baseline without penalty.

Simulations on a 20-terminal network demonstrate the algorithm's effectiveness: the lowest battery level improved from 2.7% to 68.6% over 30 iterations, while maintaining topology stability and 92% budget utilization. The framework offers a principled approach to designing energy-aware, adaptive connectivity in power-limited multi-agent systems, with applications in industrial automation, distributed energy, and multi-robot coordination. By dynamically reconfiguring connections based on battery levels and resource constraints, the method ensures that low-energy terminals receive timely replenishment without frequent costly topology changes. This research, accepted at the IISE Annual Conference & Expo 2026, provides a scalable solution for real-time battery network management.