Elastic Slice-Aware Radio Resource Management with AI-Traffic Prediction

Abstract

Network virtualisation and network slicing are the two essential innovations in the next generation of mobile networks also known as the 5G networks. Based on these innovations, multiple network slices with different requirements and objectives can share the same physical infrastructure. The techniques to efficiently allocate the available radio resources to different slices based on their requirements and their priority, also known as inter-slice radio resource management, has been the subject of many studies. The formerly proposed algorithms either assume the slices request maximum contracted data rates or they react passively as the demands arrive. This paper proposes to use Artificial Intelligence (AI) approaches to learn the pattern of the traffic demand of each network slices and predict the demands in the next decision interval. Based on the prediction of the slices' demands, a novel model for elastic inter-slice radio resource management is proposed to increase the multiplexing gain while not compromising the quality of offered connectivity services to the slices. The proposed model is evaluated using a practical scenario. The numeric results show that while the performance of the model under full demand is similar to former models, its elastic resource management enables more efficient resource allocation when the traffic demands vary over time.

Deep Learning at the Mobile Edge: Opportunities for 5G Networks

“…To reduce operational costs, deep learning techniques, borrowed from image processing, are used to anticipate network capacity based on metrics gathered in the mobile edge computing, such as signal quality, occupied resource blocks, and local computation loads [32]. Inter-slice resource allocation can be achieved by jointly optimizing according to slice priority (a slice providing remote healthcare could have priority over one for video streaming), under-stocking, fairness concerns [58], and QoE per slice [59].…”

Machine learning-assisted cross-slice radio resource optimization: Implementation framework and algorithmic solution

“…Recently, deep Q learning has become a quite popular tool for allocating radio resources to slices, as reflected by works [27]- [33] that include different variants of this technique and address the problem from different perspectives, such as the joint allocation of computational resources and radio resources to users in [27], the allocation of aggregate capacity per slice to multiple cells in [28], [29], the allocation of resources to slices on a single cell basis in [30], [31], [32], or the allocation of per-cell resources to the different slices jointly considering multiple cells in [33]. Finally, other works have proposed the use of traffic forecasting for cross-slice resource allocation, applying techniques such as LSTM neural networks [34], deep convolutional neural networks [35], Generative Adversarial Networks (GANs) [36], or deep neural networks [37].…”