Energy-Efficient Edge Inference in Integrated Sensing, Communication, and Computation Networks

2025-03-01

AI Summary

Industrial Cyber-Physical Systems (ICPS) face dual challenges of energy-constrained edge devices and millisecond-level latency requirements for AI inference. Method: This paper proposes an energy-efficiency-first Integrated Sensing, Communication, and Computing (ISCC) edge inference framework. It establishes, for the first time, an explicit analytical approximation model characterizing the end-to-end ISCC pipeline’s impact on inference accuracy. The framework jointly optimizes tunable inference partitioning, structured model pruning, and low-bit feature quantization, and devises a convergence-guaranteed algorithm based on Karush–Kuhn–Tucker (KKT) condition analysis and alternating optimization. Contribution/Results: Experiments demonstrate that, under stringent latency and accuracy constraints, the proposed framework reduces edge inference energy consumption by up to 40% compared to state-of-the-art methods—achieving significant gains particularly in millisecond-critical industrial AI applications.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Task-oriented integrated sensing, communication, and computation (ISCC) is a key technology for achieving low-latency edge inference and enabling efficient implementation of artificial intelligence (AI) in industrial cyber-physical systems (ICPS). However, the constrained energy supply at edge devices has emerged as a critical bottleneck. In this paper, we propose a novel energy-efficient ISCC framework for AI inference at resource-constrained edge devices, where adjustable split inference, model pruning, and feature quantization are jointly designed to adapt to diverse task requirements. A joint resource allocation design problem for the proposed ISCC framework is formulated to minimize the energy consumption under stringent inference accuracy and latency constraints. To address the challenge of characterizing inference accuracy, we derive an explicit approximation for it by analyzing the impact of sensing, communication, and computation processes on the inference performance. Building upon the analytical results, we propose an iterative algorithm employing alternating optimization to solve the resource allocation problem. In each subproblem, the optimal solutions are available by respectively applying a golden section search method and checking the Karush-Kuhn-Tucker (KKT) conditions, thereby ensuring the convergence to a local optimum of the original problem. Numerical results demonstrate the effectiveness of the proposed ISCC design, showing a significant reduction in energy consumption of up to 40% compared to existing methods, particularly in low-latency scenarios.

Problem

• Energy-efficient AI inference at resource-constrained edge devices.
• Minimizing energy consumption under accuracy and latency constraints.
• Proposing a novel ISCC framework with adjustable split inference.

Innovation

• Adjustable split inference for energy efficiency
• Model pruning and feature quantization adaptation
• Iterative algorithm for optimal resource allocation