5G cellular networks are expected to be the key infrastructure to deliver the emerging services. These services bring new requirements and challenges that obstruct the desired goal of forthcoming networks. Mobile operators are rethinking their network design to provide more flexible, dynamic, cost-effective and intelligent solutions. This paper starts with describing the background of the 5G wireless networks then we give a deep insight into a set of 5G challenges and research opportunities for machine learning (ML) techniques to manage these challenges. The first part of the paper is devoted to overview the fifth-generation of cellular networks, explaining its requirements as well as its key technologies, their challenges and its forthcoming architecture. The second part is devoted to present a basic overview of ML techniques that are nowadays applied to cellular networks. The last part discusses the most important related works which propose ML solutions in order to overcome 5G challenges.

No abstract

Summary-Energy consumption of large-scale networks has become a primary concern in a society increasingly dependent on information technology. Novel solutions that contribute to achieving energy savings in wired networks have been proposed to mitigate ongoing and alarming climate change and global warming. A detailed survey of relevant power-saving approaches in wired networks is presented here. We give a special focus on carrier-grade networks. At first we perform a comprehensive study of communication infrastructures regarding energy saving. Then, we highlight key issues to enable green networks, ranging from network design to network operation. After that, we present the major contributors to power consumption in wireline networks. Afterwards, we survey, classify, and compare the main energyaware methods and mechanisms that are the most appropriate for improving the energy efficiency of carrier-grade networks.

Soft-Defined Networking (SDN) is a new approach that enables operators to easily manage all the network elements.In this paper, we address the problem of energy-aware routing in SDN-based carrier-grade Ethernet networks. Our approach is based on turning off network nodes and links to reduce energy consumption, while respecting the rule space capacity for each Openflow switch, and maintaining an allowable maximum link utilization. The problem of identifying the optimal set of network elements to be turned off is NP-hard. We first present an exact model based on an Integer Linear Programming formulation for the problem. Then, we describe a set of firstfit heuristic algorithms suitable for large-sized networks. The exact and heuristic approaches are tested on SNDlib-based instances. Experimentations show the efficiency of both exact and heuristic methods for different network topologies. In particular, our heuristic algorithms are able to achieve a good balance between energy consumption, resource utilization, and network performance.

No abstract

Energy optimization has become a crucial issue in the realm of ICT. This paper addresses the problem of energy consumption in a Metro Ethernet network. Ethernet technology deployments have been increasing tremendously because of their simplicity and low cost. However, much research remains to be conducted to address energy efficiency in Ethernet networks. In this paper, we propose a novel Energy Aware Forwarding Strategy for Metro Ethernet networks based on a modification of the Internet Energy Aware Routing (EAR) algorithm. Our contribution identifies the set of links to turn off and maintain links with minimum energy impact on the active state. Our proposed algorithm could be a superior choice for use in networks with low saturation, as it involves a tradeoff between maintaining good network performance and minimizing the active links in the network. Performance evaluation shows that, at medium load traffic, energy savings of 60% can be achieved. At high loads, energy savings of 40% can be achieved without affecting the network performance.

No abstract

No abstract