PowerLens: Taming LLM Agents for Safe and Personalized Mobile Power Management

TL;DR

PowerLens leverages large language models to create safe, personalized, and context-aware power management policies for Android devices, significantly improving energy efficiency and user satisfaction without explicit configuration.

Contribution

The paper introduces PowerLens, a novel system that uses LLMs for zero-shot, personalized power management on mobile devices, integrating a multi-agent architecture, a constraint framework, and implicit feedback learning.

Findings

Achieves 81.7% action accuracy in policy execution.

Saves 38.8% energy compared to stock Android.

Converges to user preferences within 3-5 days.

Abstract

Battery life remains a critical challenge for mobile devices, yet existing power management mechanisms rely on static rules or coarse-grained heuristics that ignore user activities and personal preferences. We present PowerLens, a system that tames the reasoning power of Large Language Models (LLMs) for safe and personalized mobile power management on Android devices. The key idea is that LLMs' commonsense reasoning can bridge the semantic gap between user activities and system parameters, enabling zero-shot, context-aware policy generation that adapts to individual preferences through implicit feedback. PowerLens employs a multi-agent architecture that recognizes user context from UI semantics and generates holistic power policies across 18 device parameters. A PDL-based constraint framework verifies every action before execution, while a two-tier memory system learns individualized preferences from implicit user overrides through confidence-based distillation, requiring no explicit configuration and converging within 3--5 days. Extensive experiments on a rooted Android device show that PowerLens achieves 81.7% action accuracy and 38.8% energy saving over stock Android, outperforming rule-based and LLM-based baselines, with high user satisfaction, fast preference convergence, and strong safety guarantees, with the system itself consuming only 0.5% of daily battery capacity.