MULTI-OBJECTIVE EVOLUTIONARY OPTIMIZATION OF SECURITY POLICIES IN SOFTWAREDEFINED NETWORKS (SDN) GIVEN TCAM AND LATENCY CONSTRAINTS

Deep Reinforcement Learning for energy-aware task offloading in join SDN-Blockchain 5G massive IoT edge network

Deep reinforcement learning (DRL) is one of the emerging areas of machine learning which focuses on maximized rewards. DRL is a type of machine learning that combines reinforcement learning and deep learning. It uses a series of algorithms to enable an agent to learn how to make decisions in a complex environment. DRL is a subset of artificial intelligence that focuses on making decisions based on the environment and the rewards associated with each action.The goal of DRL is to maximize the long-term reward of an agent. In order to do this, the agent must use a combination of deep learning, reinforcement learning and other AI techniques to learn which actions will lead to the highest reward. DRL is used to solve a variety of problems, from playing video games to controlling robots. It is also used in autonomous driving and robotics, as well as for financial trading. DRL is a powerful tool for solving complex problems and has been used in a variety of research projects. DRL has the potential to revolutionize the way we interact with machines and the environment.

Software Defined Networking (SDN) has a potential to address a number of networking challenges, but still presents other financial and business challenges such as budget constraints, acceptability and trust amongst network operators. A hybrid SDN deployment is a conceivable solution, because it offers the benefits of SDN and traditional network capabilities, including budget constraints adaptability, falling back on time-tested traditional tools, central network programmability and will offer an organization a smooth transition to SDN. As modern-day communication has become an imperative feature of day to day business functions, there is a need to balance the network load to achieve improved network performance, minimizing delay and reduce the time taken for network response. In this paper, we develop and study multi-path load balancing in a hybrid SDN data plane. The load balancer’s performance is tested using four different hybrid SDN topologies, namely, Fat Tree, Ring, Mesh and Torus topology with the OpenDayLight controller. The main contribution of this work is a data plane congestion and link overloading load balancing testing and analysis for deployment (before or after network failure) in hybrid SDN environments. The obtained results display an improved overall network performance and reduced network delay.

The increasing demand for fast, reliable, and robust network services has driven the telecommunications industry to design novel network architectures that employ Network Functions Virtualization and Software Defined Networking. Despite the advancements in cellular networks, there is a need for an automatic, self-adapting orchestrating mechanism that can manage the placement of resources. Deep Reinforcement Learning can perform such tasks dynamically, without any prior knowledge. In this work, we leverage a Deep Deterministic Policy Gradient Reinforcement Learning algorithm, to fully automate the Virtual Network Functions deployment process between edge and cloud network nodes. We evaluate the performance of our implementation and compare it with alternative solutions to prove its superiority while demonstrating results that pave the way for Experiential Network Intelligence and fully automated, Zero touch network Service Management.

Software defined networks, as an emerging network architecture, separate the control plane and data plane of the network, providing new ideas and methods for network management and optimization.In software defined networks, routing optimization is one of the key issues in improving network performance and flexibility.The current routing optimization algorithms often fail to fully consider the dynamics and complexity of the network, making it difficult to achieve intelligent management and optimization of the network.In order to accurately and timely perceive the dynamic changes of network traffic and improve network stability, this paper combines deep reinforcement learning to conduct in-depth research on routing optimization algorithms in software defined networks.This article first combines DQN (Deep Q Network) and Optimized Link State Routing (OLSR) protocols in deep reinforcement learning, capturing the relationships and traffic directions between different nodes in the network; Then, the link state information used for routing decisions is exchanged to solve the resource waste problem in Deep Deterministic Policy Gradient (DDPG), in order to achieve network optimization and intelligent management of network resources; Finally, based on real-time network status and service quality requirements, the optimal path is dynamically selected to respond to changes in the network environment and provide stable and reliable network services, thereby optimizing routing.The experimental results show that the average throughput of the DQN-OLSR route is 21.9% and 31.4% higher than that of the DQN and DDPG routes, respectively.The conclusion indicates that DQN-OLSR makes the network more flexible and helps to improve the service quality and management level of the entire network.

Traffic engineering (TE) can balance the traffic in the network to reduce network congestion and improve network resource utilization. The emergence of Software Defined Network (SDN) provides a more flexible and effective way to control traffic in the network. Existing TE solutions mainly focus on routing traffic via the shortest path or evenly distributing the traffic among multiple available paths, but these methods are not flexible since this static mapping of traffic to paths does not consider either the current network utilization or traffic load. Heuristics-based TE methods depends on operators' understanding of the workload and environment. Designing and implementing those methods thus take at least weeks. Furthermore, it usually takes minutes to output the solution. Inspired by recent successes in applying Deep Reinforcement Learning (DRL) techniques to solve complex control problems, we leverage DRL to control traffic in SDN. We start by building a framework which integrates the DRL algorithm into SDN. Based on this framework, we propose a modified DRL algorithm to control the traffic split ratio to multiple paths. Simulation results show that the proposed approach performs better than three baseline methods when the traffic load is dynamically changing.

The need for reliable and flexible wireless networks has significantly increased in recent years, according to the growing reliance of an enormous number of devices on these networks to establish communications and access service. Mobile Ad-hoc Networks (MANETs) allow the wireless network to establish communications without the need for infrastructure by allowing the nodes to deliver each other’s packets to their destination. Such networks increased flexibility but require more-complex routing methods. In this study, we proposed a new routing method, based on Deep Reinforcement Learning (DRL), that distributes the computations in a Software Defined Network (SDN) controller and the nodes, so that, no redundant computations are executed in the nodes to save the limited resources available on these nodes. The proposed method has been able to significantly increase the lifetime of the network, while maintaining a high Packet Delivery Rate (PDR) and throughput. The results also show that the End-to-End delay of the proposed method is slightly larger than existing routing methods, according to the need for longer alternative routes to balance the loading among the nodes of the MANET.

SDN (Software-Defined Networking) technology is in high demand in the networking industry due to its ability to add higher agility and scalability for networks. Currently, many developed open-source controllers have been integrated with SDN networks such as POX, NOX, Floodlight, and Open Daylight. However, each controller has its own processing capacity, number of ports, and flow-setup latency. This paper evaluates the performance of Open Flow switches and Open daylight controllers. This research aims to prove that performance can be improved for SDN networks by modifying the processing capacity of the open flow controllers. The experiment presents the analysis of virtual network of hosts and Open Flow switches in Mininet communicating with the Open Daylight remote controller from local host. Simulated traffic, in the form of different time frames for TCP and UDP traffic between each host in Mininet linear topology, has been generated by the Open Flow switches to the Open Daylight controller in order to capture the performance.

Software Defined Network (SDN) Technology made tremendous changes in networking field by controlling the hardware with remote software by decoupling data plane and control plane. The focus here is on the controller which is part of control plane. A controller is a central part of SDN; it is an intermediary between Data plane and Forwarding plane. It takes prime place in SDN architecture like Operating System in Computers. SDN Controller is a software which directs the packets using flow rules and also contains statistical information of network. The controller orchestrates the networking devices such as switches and routers by channelizing the packets. SDN controller has different flavor based on the commercial requirement achieved by including new pluggable module. This paper discusses some of the SDN Controller with their feature; the controllers are POX, NOX, Floodlight, ODL, Open Contrail. This paper also compares the characteristic of centralized and distributed controller by focusing on performance, bandwidth and round-trip time of Floodlight and Open Daylight (ODL) controller. The simulation is conducted using Mininet.

Computer network conditions that are dynamic and also complex make network operators often make mistakes in the configuration of a network device. However, these mistakes can be resolved by the emergence of a centralized programming approach which is now known as Software Defined Network (SDN). In addition, with the development of information technology, several services in computer networks also grabbed a lot of attention from the world, such as video streaming services. A video streaming service that is so massive is capable of having an impact on data traffic on computer networks. In SDN networks, controllers are a core component of this architecture. Currently, many different types of SDN controllers can be used, however, choosing a controller in an SDN network must be an important concern. This is related to the performance of the SDN controller which is a requirement for SDN network development. This research will analyze the performance of the video streaming service using the Real-time Transport Protocol (RTP) streaming protocol in testing two SDN controllers, namely Pox and Opendaylight. Based on the tests that have been carried out, it produces Quality of Service (QoS) values in the form of throughput, delay, and jitter. The Pox controller excels in the value of QoS delay and throughput. As for the jitter value, both Pox and Opendaylight controllers have good indexes.

New network paradigms have emerged in recent years such as software-defined networking (SDN). These new technologies present innovations to traditional networks but security problems are still the subjects of analysis and study. The article presents an application in the software-defined networking technology with the OpenDaylight controller. This application detects and mitigates distributed denial-of-service attacks. The application monitors all network flows to determine possible attackers in various network nodes and ports. The application carries out a process of estimation of throughput and according to the information obtained installs rules to drop the packets belonging to attackers of the network. Results with various topologies and various numbers of attackers are obtained using the Mininet emulator. Quality of service results in the different scenarios are shown.

Software defined network (SDN) is a promising technology which can reduce network management complexity through the decoupling of the control plane and data plane. Due to large number of switches in the data plane, distributed and multiple controllers are necessary in the control plane for managing the switches. The switch controller mapping strategy for identifying the mapping relationships between the switch and controller is crucial in order to optimize the network performance. Considering the dynamics of the network behavior, it is quite important and challenging to develop models to reflect the network topology dynamics and to propose method for solving the long-term network performance optimization. Inspired by the recent advances in Artificial Intelligence (AI), in this paper, we propose a Deep Reinforcement Learning (DRL) based strategy for solving the switch controller mapping problem. A DRL based mapping strategy is proposed, in which Markov Decision Process (MDP) formulation is devised and Deep $Q$ -network (DQN) is proposed to achieve the maximization of long-term system performance by leveraging network latency, load balancing and system stability. Extensive simulations show that the DQN based algorithm can achieve the best system stability results while maintaining moderate switch controller latency and system equilibrium performance comparing with the optimization which only considers current system performance for switch controller mapping decision, and the optimization approaches which generate mapping decisions purely based on latency or load balancing separately.

One of the major concerns on today's Software-Defined Network (SDN) is to enhance its security. Files sharing in SDN can be made much more secured against fraudulent activities by the implementation of blockchain technology. When the privacy of network's users is increased, the reliability of system increases correspondingly. Blockchain Security over SDN (BSS) is proposed which protects privacy and availability of resources against non-trusting members. Mininet emulator is used for simulating custom SDN network topology. OpenDaylight controller is integrated with OpenStack controller. For cloud data storage, OpenStack platform is used. For testing purpose of Blockchain, Pyethereum tester tool under Ethereum platform is implemented. Serpent programming is used for creating contract in the blockchain. BSS facilitates files sharing among SDN users in distributed peer-to-peer basis using OpenStack as a cloud storage platform.

The SDN controller is a fundamental component of Software-Defined Networking. There is a variety of SDN controllers created by industry and academic research. Consequently, its selection is critical as it influences the success or failure of network connectivity. This study compared Open Network Operating System (ONOS) and Open Daylight (ODL) controllers. These open-source controllers have been installed in virtual machines to evaluate Performance using three types of network topologies that were emulated with the Mininet tool. The Performance was evaluated in terms of Throughput, Jitter, and Latency. The results showed that the ONOS controller achieved a high throughput of 79.200 Mbits, with a lower jitter of 0.022 ms and a minimum latency of 0.117 ms compared to the ODL controller.

This article presents a literature review of the past five years of studies using Deep Reinforcement Learning (DRL) and Inverse Reinforcement Learning (IRL) in robotic manipulation tasks. The reviewed articles are examined in various categories, including DRL and IRL for perception, assembly, manipulation with uncertain rewards, multitasking, transfer learning, multimodal, and Human-Robot Interaction (HRI). The articles are summarized in terms of the main contributions, methods, challenges, and highlights of the latest and relevant studies using DRL and IRL for robotic manipulation. Additionally, summary tables regarding the problem and solution are presented. The literature review then focuses on the concepts of trustworthy AI, interpretable AI, and explainable AI (XAI) in the context of robotic manipulation. Moreover, this review provides a resource for future research on DRL/IRL in trustworthy robotic manipulation.