Traditional Communication models rooted in Shanon’s theory, prioritize transmission of raw bits of data over semantic meaning and relevance, and are not able meet the demands of exponential growth in data and communication traffic, thus resulting in inefficiencies like high latency and poor resource utilization. Semantic communication addresses these issues by prioritizing meaningful data, but existing resource allocation methods cannot optimize Semantic Spectral Efficiency (S-SE) in multi-user environments. To address this, we propose a resource allocation framework integrating the Hungarian algorithm for optimal task assignment and Shapley value-based prioritization for fair distribution. This approach enhances S-SE, ensures fairness (validated by Jain’s fairness index), and maintains computational efficiency, making it ideal for real-time applications. Our framework advances semantic communication by balancing efficiency and fairness, benefiting wireless networks, IoT, and intelligent transportation.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Cooperative Game Theory-Based Resource Allocation in Text-Based Semantic Communication

  • Moirangthem Tiken Singh,
  • Adnan Arif

摘要

Traditional Communication models rooted in Shanon’s theory, prioritize transmission of raw bits of data over semantic meaning and relevance, and are not able meet the demands of exponential growth in data and communication traffic, thus resulting in inefficiencies like high latency and poor resource utilization. Semantic communication addresses these issues by prioritizing meaningful data, but existing resource allocation methods cannot optimize Semantic Spectral Efficiency (S-SE) in multi-user environments. To address this, we propose a resource allocation framework integrating the Hungarian algorithm for optimal task assignment and Shapley value-based prioritization for fair distribution. This approach enhances S-SE, ensures fairness (validated by Jain’s fairness index), and maintains computational efficiency, making it ideal for real-time applications. Our framework advances semantic communication by balancing efficiency and fairness, benefiting wireless networks, IoT, and intelligent transportation.