Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A New Realistic Platform for Benchmarking and Performance Evaluation of DRL-Driven and Reconfigurable SFC Provisioning Solutions

Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Emil Janulewicz, Sergio Slobodrian

TL;DR

The paper addresses efficient SFC provisioning in URLLC-driven NFV networks by introducing a realistic DRL-enabled simulation platform that models multiple DCs, VNFs, and SFCs with BW and latency constraints. A DRL-based provisioning algorithm, augmented with priority points, orchestrates VNF placement while remaining decoupled from the underlying simulator, enabling robust benchmarking and data collection. The key contributions include a comprehensive runtime data architecture (SFC_List, SFC_Attr, SFC_TX_Delay, SFC_TX_Packet), a multi-input DRL model using DQN and MDP, and a priority-driven action selection mechanism that improves SFC acceptance and reduces End-to-End latency compared to a heuristic baseline. The platform’s reconfigurability and detailed metrics support scalable evaluation of DRL-driven SFC provisioning, with practical implications for 5G and beyond networks.

Abstract

Service Function Chain (SFC) provisioning stands as a pivotal technology in the realm of 5G and future networks. Its essence lies in orchestrating VNFs (Virtual Network Functions) in a specified sequence for different types of SFC requests. Efficient SFC provisioning requires fast, reliable, and automatic VNFs' placements, especially in a network where massive amounts of SFC requests are generated having ultra-reliable and low latency communication (URLLC) requirements. Although much research has been done in this area, including Artificial Intelligence (AI) and Machine Learning (ML)-based solutions, this work presents an advanced Deep Reinforcement Learning (DRL)-based simulation model for SFC provisioning that illustrates a realistic environment. The proposed simulation platform can handle massive heterogeneous SFC requests having different characteristics in terms of VNFs chain, bandwidth, and latency constraints. Also, the model is flexible to apply to networks having different configurations in terms of the number of data centers (DCs), logical connections among DCs, and service demands. The simulation model components and the workflow of processing VNFs in the SFC requests are described in detail. Numerical results demonstrate that using this simulation setup and proposed algorithm, a realistic SFC provisioning can be achieved with an optimal SFC acceptance ratio while minimizing the E2E latency and resource consumption.

A New Realistic Platform for Benchmarking and Performance Evaluation of DRL-Driven and Reconfigurable SFC Provisioning Solutions

TL;DR

The paper addresses efficient SFC provisioning in URLLC-driven NFV networks by introducing a realistic DRL-enabled simulation platform that models multiple DCs, VNFs, and SFCs with BW and latency constraints. A DRL-based provisioning algorithm, augmented with priority points, orchestrates VNF placement while remaining decoupled from the underlying simulator, enabling robust benchmarking and data collection. The key contributions include a comprehensive runtime data architecture (SFC_List, SFC_Attr, SFC_TX_Delay, SFC_TX_Packet), a multi-input DRL model using DQN and MDP, and a priority-driven action selection mechanism that improves SFC acceptance and reduces End-to-End latency compared to a heuristic baseline. The platform’s reconfigurability and detailed metrics support scalable evaluation of DRL-driven SFC provisioning, with practical implications for 5G and beyond networks.

Abstract

Service Function Chain (SFC) provisioning stands as a pivotal technology in the realm of 5G and future networks. Its essence lies in orchestrating VNFs (Virtual Network Functions) in a specified sequence for different types of SFC requests. Efficient SFC provisioning requires fast, reliable, and automatic VNFs' placements, especially in a network where massive amounts of SFC requests are generated having ultra-reliable and low latency communication (URLLC) requirements. Although much research has been done in this area, including Artificial Intelligence (AI) and Machine Learning (ML)-based solutions, this work presents an advanced Deep Reinforcement Learning (DRL)-based simulation model for SFC provisioning that illustrates a realistic environment. The proposed simulation platform can handle massive heterogeneous SFC requests having different characteristics in terms of VNFs chain, bandwidth, and latency constraints. Also, the model is flexible to apply to networks having different configurations in terms of the number of data centers (DCs), logical connections among DCs, and service demands. The simulation model components and the workflow of processing VNFs in the SFC requests are described in detail. Numerical results demonstrate that using this simulation setup and proposed algorithm, a realistic SFC provisioning can be achieved with an optimal SFC acceptance ratio while minimizing the E2E latency and resource consumption.
Paper Structure (14 sections, 1 equation, 4 figures, 1 table, 1 algorithm)

This paper contains 14 sections, 1 equation, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. System Model and Problem Formulation
  4. Simulation Platform and Structures
  5. SFC and VNF Structures
  6. Connection Structures and Shortest Path Discovery
  7. Data Center Structures
  8. SFC Request Generation
  9. Simulation Run and VNF Processing
  10. SFC Provisioning Algorithm
  11. Deep Reinforcement Learning Module
  12. Priority Points
  13. Numerical Results
  14. Conclusions

Figures (4)

  • Figure 1: Platform Illustration, Data Structures, SFC Demand Creation, and AI Model for SFC Provisioning Task
  • Figure 2: SFC acceptance ratio and E2E delay for each type of requests with 5 DCs
  • Figure 3: SFC acceptance ratio and E2E delay for each type of requests with 3 DCs
  • Figure 4: Resource consumption: average and during simulation at 15ms time scale