Online Multi-Task Offloading for Semantic-Aware Edge Computing Systems

2024-06-28

arXiv.org

AI Summary

To address uplink bandwidth congestion caused by multimodal task offloading in mobile edge computing (MEC), this paper proposes a semantics-aware collaborative offloading framework. The method introduces a novel semantic extraction factor for joint communication and computation resource optimization; designs a unified Quality-of-Experience (QoE) metric integrating execution latency, computational energy consumption, and task performance; and develops an online joint decision-making mechanism based on Multi-Agent Proximal Policy Optimization (MAPPO). By deeply integrating Markov Decision Process (MDP) modeling with multimodal task representation, the framework supports configurable user preferences. Experimental results demonstrate that, compared to a semantics-agnostic baseline, the proposed approach reduces execution latency by 18.1% and energy consumption by 12.9%, significantly improving both resource utilization efficiency and task service quality.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Mixed Discrete/Continuous 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: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Mobile edge computing (MEC) provides low-latency offloading solutions for computationally intensive tasks, effectively improving the computing efficiency and battery life of mobile devices. However, for data-intensive tasks or scenarios with limited uplink bandwidth, network congestion might occur due to massive simultaneous offloading nodes, increasing transmission latency and affecting task performance. In this paper, we propose a semantic-aware multi-modal task offloading framework to address the challenges posed by limited uplink bandwidth. By introducing a semantic extraction factor, we balance the relationship among transmission latency, computation energy consumption, and task performance. To measure the offloading performance of multi-modal tasks, we design a unified and fair quality of experience (QoE) metric that includes execution latency, energy consumption, and task performance. Lastly, we formulate the optimization problem as a Markov decision process (MDP) and exploit the multi-agent proximal policy optimization (MAPPO) reinforcement learning algorithm to jointly optimize the semantic extraction factor, communication resources, and computing resources to maximize overall QoE. Experimental results show that the proposed method achieves a reduction in execution latency and energy consumption of 18.1% and 12.9%, respectively compared with the semantic-unaware approach. Moreover, the proposed approach can be easily extended to models with different user preferences.

Problem

• Optimizing task offloading in bandwidth-limited edge computing systems
• Balancing latency, energy, and performance via semantic extraction
• Maximizing QoE for multi-modal tasks using MAPPO algorithm

Innovation

• Semantic-aware multi-modal task offloading framework
• Unified QoE metric for multi-modal tasks
• MAPPO algorithm for joint resource optimization