Recently, with the rapid development of information and communication technologies, the infrastructures, resources, end devices, and applications in communications and networking systems are becoming much more complex and heterogeneous. In addition, the large volume of data and massive end devices may bring serious security, privacy, services provisioning, and network management challenges. In order to achieve decentralized, secure, intelligent, and efficient network operation and management, the joint consideration of blockchain and machine learning (ML) may bring significant benefits and have attracted great interests from both academia and industry. On one hand, blockchain can significantly facilitate training data and ML model sharing, decentralized intelligence, security, privacy, and trusted decision-making of ML. On the other hand, ML will have significant impacts on the development of blockchain in communications and networking systems, including energy and resource efficiency, scalability, security, privacy, and intelligent smart contracts. However, some essential open issues and challenges that remain to be addressed before the widespread deployment of the integration of blockchain and ML, including resource management, data processing, scalable operation, and security issues. In this paper, we present a survey on the existing works for blockchain and ML technologies. We identify several important aspects of integrating blockchain and ML, including overview, benefits, and applications. Then we discuss some open issues, challenges, and broader perspectives that need to be addressed to jointly consider blockchain and ML for communications and networking systems.

Blockchain and Machine Learning for Communications and Networking Systems

In recent years, Software Defined Networking (SDN) has emerged as a pivotal element not only in data-centers and wide-area networks, but also in next generation networking architectures such as Vehicular ad hoc network and 5G. SDN is characterized by decoupled data and control planes, and logically centralized control plane. The centralized control plane in SDN offers several opportunities as well as challenges. A key design choice of the SDN control plane is placement of the controller(s), which impacts a wide range of network issues ranging from latency to resiliency, from energy efficiency to load balancing, and so on. In this paper, we present a comprehensive survey on the controller placement problem (CPP) in SDN. We introduce the CPP in SDN and highlight its significance. We present the classical CPP formulation along with its supporting system model. We also discuss a wide range of the CPP modeling choices and associated metrics. We classify the CPP literature based on the objectives and methodologies. Apart from the primary use-cases of the CPP in data-center networks and wide area networks, we also examine the recent application of the CPP in several new domains such as mobile/cellular networks, 5G, named data networks, wireless mesh networks and VANETs. We conclude our survey with discussion on open issues and future scope of this topic.

A Survey on Controller Placement in SDN

Reinforcement learning (RL), which is a class of machine learning, provides a framework by which a system can learn from its previous interactions with its environment to efficiently select its actions in the future. RL has been used in a number of application fields, including game playing, robotics and control, networks, and telecommunications, for building autonomous systems that improve themselves with experience. It is commonly accepted that RL is suitable for solving optimization problems related to distributed systems in general and to routing in networks in particular. RL also has reasonable overhead—in terms of control packets, memory and computation—compared to other optimization techniques used to solve the same problems. Since the mid-1990s, over 60 protocols have been proposed, with major or minor contributions in the field of optimal route selection to convey packets in different types of communication networks under various user QoS requirements. This paper provides a comprehensive review of the literature on the topic. The review is structured in a way that shows how network characteristics and requirements were gradually considered over time. Classification criteria are proposed to present and qualitatively compare existing RL-based routing protocols.

/pdf/reinforcement-learning-based-routing-in-networks-review-and-4kebu4ymqq.pdf

Reinforcement Learning Based Routing in Networks: Review and Classification of Approaches

In order to simplify the management of the traditional network, software-defined networking (SDN) has been proposed as a promising paradigm shift that decouples control plane and data plane, providing programmability to configure the network. With the deployment and the applications of SDN, researchers have found that the controller placement directly affects network performance in SDN. In this paper, the state of the art of controller placement problem is surveyed from the perspective of optimization objective. First, we introduce the overview of SDN and controller placement problem. Then, we classify this paper of controller placement problem into four aspects (latency, reliability, and cost and multi-objective) depending on their objective and analyze specific algorithms in different application scenarios. Finally, we identify some relevant open issues and research challenge to deal with in the future and conclude the controller placement problem.

/pdf/a-survey-of-controller-placement-problem-in-software-defined-3yzdz77a6x.pdf

A Survey of Controller Placement Problem in Software-Defined Networking

Software-defined networking (SDN) is an emerging network architecture that promises to simplify network management, improve network resource utilization, and boost evolution and innovation in traditional networks. The SDN allows the abstraction and centralized management of the lower-level network functionalities by decoupling the network logic from the data forwarding devices into the logically centralized distributed controllers. However, this separation introduces new scalability and performance challenges in large-scale networks of dynamic traffic and topology conditions. Many research studies have represented that centralization and maintaining the global network visibility over the distributed SDN controller introduce scalability concern. This paper surveys the state-of-the-art proposed techniques toward minimizing the control to data planes communication overhead and controllers' consistency traffic to enhance the OpenFlow-SDN scalability in the context of logically centralized distributed SDN control plane architecture. The survey mainly focuses on four issues, including logically centralized visibility, link-state discovery, flow rules placement, and controllers' load balancing. In addition, this paper discusses each issue and presents an updated and detailed study of existing solutions and limitations in enhancing the OpenFlow-SDN scalability and performance. Moreover, it outlines the potential challenges that need to be addressed further in obtaining adaptive and scalable OpenFlow-SDN flow control.

Toward adaptive and scalable openflow-SDN flow control: A survey

Software-defined networking (SDN) is a novel network paradigm that enables flexible management for networks. As the network size increases, the single centralized controller cannot meet the increasing demand for flow processing. Thus, the promising solution for SDN with large-scale networks is the multi-controller. In this paper, we present a compressive survey for multi-controller research in SDN. First, we introduce the overview of multi-controller, including the origin of multi-controller and its challenges. Then, we classify multi-controller research into four aspects (scalability, consistency, reliability, and load balancing) depending on the process of implementing the multi-controller. Finally, we propose some relevant research issues to deal with in the future and conclude the multi-controller research.

Multi-controller Based Software-Defined Networking: A Survey

This paper proposes DROM, a deep reinforcement learning mechanism for Software-Defined Networks (SDN) to achieve a universal and customizable routing optimization. DROM simplifies the network operation and maintenance by improving the network performance, such as delay and throughput, with a black-box optimization in continuous time. We evaluate the DROM with experiments. The experimental results show that DROM has the good convergence and effectiveness and provides better routing configurations than existing solutions to improve the network performance, such as reducing the delay and improving the throughput.

DROM: Optimizing the Routing in Software-Defined Networks With Deep Reinforcement Learning

TIDE: Time-relevant deep reinforcement learning for routing optimization

Network Function Virtualization (NFV) technology utilizes software to implement network function as virtual instances, which reduces the cost on various middlebox hardware. A Virtual Network Function (VNF) instance requires multiple resource types in the network (e.g., CPU, memory). Therefore, an efficient VNF placement policy should consider both the resource utilization problem and the Quality of Service (QoS) of flows, which is proved NP-hard. Recent studies employ Deep Reinforcement Learning (DRL) to solve the VNF placement problem, but existing DRL-based solutions cannot generalize well to different topologies. In this letter, we propose to combine the advantage of DRL and Graph Neural Network (GNN) to design our VNF placement scheme DeepOpt. Simulation results show that DeepOpt outperforms the state-of-the-art VNF placement schemes and shows a much better generalization ability in different network topologies.

Julong Lan

Papers

Multi-controller Based Software-Defined Networking: A Survey

DROM: Optimizing the Routing in Software-Defined Networks With Deep Reinforcement Learning

A Survey of Controller Placement Problem in Software-Defined Networking

TIDE: Time-relevant deep reinforcement learning for routing optimization

Combining Deep Reinforcement Learning With Graph Neural Networks for Optimal VNF Placement