An SDN-Based Flow Table Encoding Approach for Resource and Efficiency Optimization in Topic-Based Pub/Sub Systems

With the rapid development of software-defined networking (SDN), SDN-Based multi-level flow table architectures are always employed to address issues such as QoS, security policies, and matching efficiency. The rise of semantic communication has also sparked researchers’ interest in semantic information and its utilization. Many studies on semantic representation and semantic summarization have emerged. This study takes a new perspective to reduce the number of table entries by utilizing the semantic relationships implied in the topic tree in the topic-based pub/sub systems and introduces the concept of semantic aggregation. Semantic aggregation of table entries can work with multi-level flow table architecture to reduce the number of table entries while ensuring the correct delivery of streams. We propose a semantic-based table entry encoding algorithm to implement our idea and conduct several experiments to examine its performance. The experiment results demonstrate that our algorithm can achieve high space and efficiency optimization rate in a short encoding time.