Dynamic Resource Management in Service-Oriented Core Networks

1.1 Service-Oriented Core Networks

1.1.1 Software-Defined Networking (SDN)

1.1.2 Network Function Virtualization (NFV)

1.1.3 Service Function Chaining

1.2 Network Slicing Framework

1.2.1 Infrastructure Domain

1.2.3 SDN-NFV Integration

1.3 Multi-Timescale Dynamic Resource Management

1.3.1 Multi-Timescale Core Network Traffic Dynamics

1.3.2 Dynamic Resource Provisioning in Large Timescale

1.3.3 Dynamic Resource Scheduling in Small Timescale

1.4 Research Contributions

1.5 Outline

References

Chapter 2 System Model

2.1 Services

2.3 Placement and Scheduling of Virtual Network Function (VNF)

2.3 Migration Cost and Reconfiguration Overhead

References

Chapter 3 Dynamic Flow Migration: A Model-Based Optimization Approach

3.1 Model Assumptions

3.1.1 M/M/1 VNF Packet Processing Queueing Model

3.1.2 Generalized Processor Sharing (GPS)

3.2 Optimization Model for Dynamic Flow Migration

3.3 Mixed Integer Quadratically Constrained Programming (MIQCP) Problem Transformation

3.3.1 Optimality Gap

3.3.2 Optimal Solution Mapping

3.4 Low-Complexity Heuristic Flow Migration Algorithm

3.4.1 Algorithm Overview

3.4.2 Redistribution of Hop Delay Bounds

3.4.4 Iterative Resource Loading Threshold Update

3.4.5 Complexity Analysis

3.5 Simulation Results

3.6 Summary

References

Chapter 4 Dynamic VNF Resource Scaling and Migration: A Machine Learning Approach

4.1 Nonstationary Traffic Model

4.2 Machine Learning Tools for Analysis and Decision

4.2.1 Bayesian Conjugate Analysis

4.2.2 Gaussian Process Regression

4.2.3 Reinforcement Learning

4.3 Resource Demand Prediction for Dynamic VNF Resource Scaling

4.3.1 Bayesian Online Change Point Detection

4.3.2 Traffic Parameter Learning

4.3.3 Resource Demand Prediction

4.4 Deep Reinforcement Learning for Dynamic VNF Migration

4.4.1 Markov Decision Process

4.4.2 Penalty-Aware Deep Q-Learning Algorithm

4.5 Simulation Results

4.6 Summary

References

Chapter 5 Dynamic VNF Scheduling for Network Utility Maximization

5.1 Discrete-Time VNF Packet Processing Queueing Model

5.1.1 Physical Packet Processing Queue

5.1.2 Delay-Aware Virtual Packet Processing Queue

5.2 Stochastic VNF Scheduling: Problem and Solution

5.2.1 Stochastic Problem Formulation

5.2.2 Lyapunov Optimization and Problem Transformation

5.2.3 Online Distributed Algorithm

5.3 VNF Scheduling with Packet Rushing

5.3.1 Packet Rushing Analysis

5.3.2 Modified VNF Scheduling Algorithm

5.4 Simulation Results

5.5 Summary

References

Chapter 6 Conclusions and Future Research Directions

6.1 Conclusions

6.2 Future Research Directions

References