Slice as an Evolutionary Service: Genetic Optimization for Inter-Slice Resource Management in 5G Networks

Abstract

In the context of Fifth Generation (5G) mobile networks, the concept of "Slice as a Service" (SlaaS) promotes mobile network operators to flexibly share infrastructures with mobile service providers and stakeholders. However, it also challenges with an emerging demand for efficient online algorithms to optimize the request-and-decision-based inter-slice resource management strategy. Based on genetic algorithms, this paper presents a novel online optimizer that efficiently approaches towards the ideal slicing strategy with maximized long-term network utility. The proposed method encodes slicing strategies into binary sequences to cope with the request-and-decision mechanism. It requires no a priori knowledge about the traffic/utility models, and therefore supports heterogeneous slices, while providing solid effectiveness, good robustness against non-stationary service scenarios, and high scalability.

arXiv commentFirst version (v1) submitted to IEEE Access on 09-Feb-2018, resubmission (v2) on 09-May-2018, acceptance (v3) on 08-June-2018

References in corpus (2)

• Evolutionary Algorithms for Reinforcement Learning
• Modeling Profit of Sliced 5G Networks for Advanced Network Resource Management and Slice Implementation

Cited by in corpus (15)

• 5G network slicing using SDN and NFV- A survey of taxonomy, architectures and future challenges
• A Utility-Driven Multi-Queue Admission Control Solution for Network Slicing
• Latency-Sensitive 5G RAN Slicing for Industry 4.0
• Multiservice-based Network Slicing Orchestration with Impatient Tenants
• Admission and Congestion Control for 5G Network Slicing
• A Markov Model of Slice Admission Control
• Expanded Combinatorial Designs as Tool to Model Network Slicing in 5G
• Game theory and Evolutionary-optimization methods applied to resource allocation problems in emerging computing environments: A survey
• GAN-powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicing
• Deep Reinforcement Learning for Resource Management in Network Slicing
• 6G Vision: An Ultra-Flexible Perspective
• DPoS: Decentralized, Privacy-Preserving, and Low-Complexity Online Slicing for Multi-Tenant Networks
• Joint Resource and Admission Management for Slice-enabled Networks
• Optimal and Fast Real-time Resources Slicing with Deep Dueling Neural Networks
• The Slice Is Served: Enforcing Radio Access Network Slicing in Virtualized 5G Systems