Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Xingyu Feng, Chang Sun, Yuzhu Wang, Zhangbing Zhou, Chengwen Luo, Zhuangzhuang Chen, Xiaomin Ouyang, Huanqi Yang

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.

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

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.
Paper Structure (39 sections, 5 equations, 15 figures, 5 tables, 1 algorithm)

This paper contains 39 sections, 5 equations, 15 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background and Motivation
  3. Mobile Power Management Landscape
  4. LLMs as System-Level Reasoners
  5. Motivating Scenarios
  6. System Design
  7. Multi-Agent Power Management Loop
  8. Activity Agent.
  9. Policy Agent.
  10. Execution Agent.
  11. Feedback Agent.
  12. Decision Pipeline.
  13. Memory System for Personalization
  14. Short-Term Memory (STM)
  15. Long-Term Personal Memory (LPM)
  16. ...and 24 more sections

Figures (15)

  • Figure 1: Traditional power saver vs. PowerLens. Global rules degrade navigation by throttling GPS and dimming brightness; PowerLens preserves critical resources and learned preferences.
  • Figure 2: Preliminary studies on challenges of mobile power management.
  • Figure 3: Hardware activated during navigation. A single app engages components across the mainboard and daughter board, spanning all five parameter categories in Table \ref{['tab:power_params']}.
  • Figure 4: PowerLens system overview. Each cycle: ➊ Accessibility captures UI tree, ➋ Activity Agent recognizes context, ➌ Policy Agent generates strategy, ➍➎ Execution Agent verifies and applies via shell commands, ➏ Feedback Agent detects user overrides. The Memory System stores preferences for personalization.
  • Figure 5: Decision cycle example. The Policy Agent generates a structured JSON policy for an Instagram browsing session; the Execution Agent validates actions against PDL constraints and translates approved actions into root shell commands.
  • ...and 10 more figures