Learning from Images: Proactive Caching with Parallel Convolutional Neural Networks

With the continuous trend of data explosion, delivering packets from data servers to end users causes increased stress on both the fronthaul and backhaul traffic of mobile networks. To mitigate this problem, caching popular content closer to the end-users has emerged as an effective method for reducing network congestion and improving user experience. To find the optimal locations for content caching, many conventional approaches construct various mixed integer linear programming (MILP) models. However, such methods may fail to support online decision making due to the inherent curse of dimensionality. In this paper, a novel framework for proactive caching is proposed. This framework merges model-based optimization with data-driven techniques by transforming an optimization problem into a grayscale image. For parallel training and simple design purposes, the proposed MILP model is first decomposed into a number of sub-problems and, then, convolutional neural networks (CNNs) are trained to predict content caching locations of these sub-problems. Furthermore, since the MILP model decomposition neglects the internal effects among sub-problems, the CNNs outputs have the risk to be infeasible solutions. Therefore, two algorithms are provided: the first uses predictions from CNNs as an extra constraint to reduce the number of decision variables; the second employs CNNs outputs to accelerate local search. Numerical results show that the proposed scheme can reduce 71.6% computation time with only 0.8% additional performance cost compared to the MILP solution, which provides high quality decision making in real-time.

Energy-Efficient Proactive Caching with Multipath Routing

The ever-continuing explosive growth of on-demand content requests has imposed great pressure on mobile/wireless network infrastructures. To ease congestion in the network and increase perceived user experience, caching popular content closer to the end-users can play a significant role and as such this issue received significant attention over the last few years. Additionally, energy efficiency is treated as a fundamental requirement in the design of next-generation mobile networks. However, there has been little attention to the overlapping area between energy efficiency and network caching especially when considering multipath routing. To this end, this paper proposes an energy-efficient caching with multipath routing support. The proposed scheme provides a joint anchoring of popular content into a set of potential caching nodes with optimized multi-path support whilst ensuring a balance between transmission and caching energy cost. The proposed model also considers different content delivery modes, such as multicast and unicast. Two separated Integer-Linear Programming (ILP) models are formulated for each delivery mode. To tackle the curse of dimensionality we then provide a greedy simulated annealing algorithm, which not only reduces the time complexity but also provides a competitive performance as ILP models. A wide set of numerical investigations has shown that the proposed scheme is more energy-efficient compared with other widely used approaches in caching under the premise of network resource limitation.

A Survey of Deep Learning for Data Caching in Edge Network

The concept of edge caching provision in emerging 5G and beyond mobile networks is a promising method to deal both with the traffic congestion problem in the core network as well as reducing latency to access popular content. In that respect end user demand for popular content can be satisfied by proactively caching it at the network edge, i.e, at close proximity to the users. In addition to model based caching schemes learning-based edge caching optimizations has recently attracted significant attention and the aim hereafter is to capture these recent advances for both model based and data driven techniques in the area of proactive caching. This paper summarizes the utilization of deep learning for data caching in edge network. We first outline the typical research topics in content caching and formulate a taxonomy based on network hierarchical structure. Then, a number of key types of deep learning algorithms are presented, ranging from supervised learning to unsupervised learning as well as reinforcement learning. Furthermore, a comparison of state-of-the-art literature is provided from the aspects of caching topics and deep learning methods. Finally, we discuss research challenges and future directions of applying deep learning for caching

Network Orchestration in Mobile Networks via a Synergy of Model-driven and AI-based Techniques

As data traffic volume continues to increase, caching of popular content at strategic network locations closer to the end user can enhance not only user experience but ease the utilization of highly congested links in the network. A key challenge in the area of proactive caching is finding the optimal locations to host the popular content items under various optimization criteria. These problems are combinatorial in nature and therefore finding optimal and/or near optimal decisions is computationally expensive. In this paper a framework is proposed to reduce the computational complexity of the underlying integer mathematical program by first predicting decision variables related to optimal locations using a deep convolutional neural network (CNN). The CNN is trained in an offline manner with optimal solutions and is then used to feed a much smaller optimization problems which is amenable for real-time decision making. Numerical investigations reveal that the proposed approach can provide in an online manner high quality decision making; a feature which is crucially important for real-world implementations.

Caching as an Image Characterization Problem using Deep Convolutional Neural Networks

Caching of popular content closer to the mobile user can significantly increase overall user experience as well as network efficiency by decongesting backbone network segments in the case of congestion episodes. In order to find the optimal caching locations, many conventional approaches rely on solving a complex optimization problem that suffers from the curse of dimensionality, which may fail to support online decision making. In this paper we propose a framework to amalgamate model based optimization with data driven techniques by transforming an optimization problem to a grayscale image and train a convolutional neural network (CNN) to predict optimal caching location policies. The rationale for the proposed modelling comes from CNNs superiority to capture features in grayscale images reaching human level performance in image recognition problems. The CNN is trained with optimal solutions and numerical investigations reveal that the performance can increase by more than 400% compared to powerful randomized greedy algorithms. To this end, the proposed technique seems as a promising way forward to the holy grail aspect in resource orchestration which is providing high quality decision making in real time.