Hybrid Model-Data Driven Network Slice Reconfiguration by Exploiting Prediction Interval and Robust Optimization

Abstract

Proactive reconfiguration of network slices according to uncertain traffic demands is essential to improve network resource utilization while ensuring service quality in 5G-andbeyond systems. Existing researches on network slice reconfiguration are either model-driven or data-driven methods. However, model-driven methods may cause resource over-provisioning due to a lack of prediction mechanism, while data-driven methods are unrealistic in inter-slice reconfiguration that involves costly and time-consuming operations such as VNF migration. To address these issues, in this paper, we propose a Hybrid Model-Data driven (HMD) framework that intelligently performs inter-slice reconfiguration by leveraging prediction interval and robust optimization. We design a Prediction Interval-oriented Predictor (PIP) to produce a prediction interval that can bracket the future traffic demand with a prespecified probability. Based on the prediction interval, we design an inter-slice reconfiguration scheme (named box optimizer) to perform fast inter-slice reconfigurations. To tackle the over-conservativeness of the box optimizer, we further design the ellipsoid optimizer with better optimality at a cost of increased complexity. Numerical results demonstrate that the proposed framework can provide high robustness with low power consumption. Meanwhile, the tradeoff between the power consumption and the realized robustness can be flexibly adjusted according to the type of slice and the level of traffic demand fluctuations.

Comprehensive Tutorial on the Organization of a Standards-Aligned Network Slice/Subnet Design Process and Opportunities for Its Automation

“…3. Consequently, the 3GPP Network Slicing management layer is reusing the NFV-MANO systems and comprises three conceptual architectural blocks 10 [12], [13] presented in the upper part of col. C of Fig. 3: Communication Service (CSMF), Network Slice (NSMF) and Network Slice Subnet (NSSMF) 11 Management Functions.…”

“…[108] explains the corresponding terms and concepts thoroughly. 10 Such a split was proposed in an early 3GPP report [12]. But, due to the adoption of Service-Based Management Architecture (SBMA) [113], this CSMF level, both design-time and runtime, are not specified within 3GPP (see upper part of Fig.…”

“…In the mature orchestration solutions, the post-design activities (see Fig. 14, yellow badges) typically include, but are not limited to: (10) onboarding and preprovisioning of the created Instance Descriptors followed by (11) triggering the lifecycle of an NSI/NSSI based on them. In the less mature solutions, the credibility of the produced design outcomes shall be practically confirmed before operational deployment, by performing their (9) operational validation.…”

“…Although deployed on a shared cloud infrastructure, all NSIs and NSSIs shall be isolated from each other in terms of performance, security and management [6]. Moreover, they are expected to be flexibly [7] created on demand within seconds and be operated largely hands-free, leveraging their closed-loop adaptation to the experienced conditions [8]- [10].…”

Migration and Energy Aware Network Traffic Prediction Method Based on LSTM in NFV Environment

“…The usual solution is to divide each day into multiple time slices. It obtains the resource demand according to the peak network traffic in each time slice, and actively performs migration before each time slice starts [6] [7][8] [9]. One fundamental problem is to predict the peak network traffic for the next time slice [10].…”