Simultaneous Genetic Evolution of Neural Networks for Optimal SFC Embedding

2025-12-10

AI Summary

The service function chain (SFC) embedding problem is NP-hard, and existing genetic algorithms (GAs) fail to jointly optimize chain composition, virtual network function (VNF) mapping, and link embedding. To address this, we propose GENESIS—a novel framework enabling end-to-end co-optimization of all three subproblems. GENESIS innovatively integrates three sine-activated neural networks into the GA’s population evolution process, augments exploration via Gaussian sampling, and incorporates A* search to enhance path planning accuracy. Evaluated across 48 datacenter topologies, GENESIS achieves a 100% optimal embedding success rate—surpassing all state-of-the-art methods. It attains an average runtime of 15.84 minutes, outperforming the next-best GA by over 59% in speed. To the best of our knowledge, GENESIS is the first scalable, high-precision co-evolutionary solution for SFC embedding.

Technology Category

• Search and Optimization: Evolutionary Computation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The reliance of organisations on computer networks is enabled by network programmability, which is typically achieved through Service Function Chaining. These chains virtualise network functions, link them, and programmatically embed them on networking infrastructure. Optimal embedding of Service Function Chains is an NP-hard problem, with three sub-problems, chain composition, virtual network function embedding, and link embedding, that have to be optimised simultaneously, rather than sequentially, for optimal results. Genetic Algorithms have been employed for this, but existing approaches either do not optimise all three sub-problems or do not optimise all three sub-problems simultaneously. We propose a Genetic Algorithm-based approach called GENESIS, which evolves three sine-function-activated Neural Networks, and funnels their output to a Gaussian distribution and an A* algorithm to optimise all three sub-problems simultaneously. We evaluate GENESIS on an emulator across 48 different data centre scenarios and compare its performance to two state-of-the-art Genetic Algorithms and one greedy algorithm. GENESIS produces an optimal solution for 100% of the scenarios, whereas the second-best method optimises only 71% of the scenarios. Moreover, GENESIS is the fastest among all Genetic Algorithms, averaging 15.84 minutes, compared to an average of 38.62 minutes for the second-best Genetic Algorithm.

Problem

• Optimizes Service Function Chain embedding simultaneously
• Addresses NP-hard problem with three sub-problems jointly
• Uses Genetic Algorithm with Neural Networks for optimal solutions

Innovation

• Genetic Algorithm evolving three neural networks simultaneously
• Neural networks use sine activation and Gaussian distribution funneling
• Combines A* algorithm for optimal service chain embedding