Hybrid SDN Research Articles

FRRL: A reinforcement learning approach for link failure recovery in a hybrid SDN

FRRL: A reinforcement learning approach for link failure recovery in a hybrid SDN

Performance enhancement in hybrid SDN using advanced deep learning with multi‐objective optimization frameworks under heterogeneous environments

Performance enhancement in hybrid SDN using advanced deep learning with multi‐objective optimization frameworks under heterogeneous environments

TITE: A transformer-based deep reinforcement learning approach for traffic engineering in hybrid SDN with dynamic traffic

Hybrid Software Defined Networks (Hybrid SDNs), with a partial upgrade of legacy routers to SDN switches in traditional distributed networks, currently stand as a prevailing network architecture. Traffic Engineering (TE) in hybrid SDN requires the efficient and timely acquisition of a routing policy to adapt to dynamically changing traffic demands, which has recently become a hot topic. Ignoring the hidden relations of consecutive states and the compact representation of the network environment, previous Deep Reinforcement Learning (DRL)-based studies suffer from the convergence problem by only establishing the direct relationship between individual Traffic Matrix (TM) and routing policy. Therefore, to enhance TE performance in hybrid SDNs under dynamically changing traffic demands, we propose to integrate the Transformer model with DRL to establish the relationship between consecutive states and routing policies. The temporal characteristic among consecutive states can effectively assist DRL in solving the convergence problem. To obtain a compact and accurate description of the network environment, we propose to jointly consider TM, routing action, and reward in designing the state of the network environment. To better capture the temporal relations among consecutive states of the network environment, we design a multi-feature embedding module and achieve positional encodings in the Transformer model. The extensive experiments demonstrate that once the convergence problem is solved, the proposed Transformer-based DRL method can efficiently generate routing policies that adapt well to dynamic network traffic.

Modified smell detection algorithm for optimal paths engineering in hybrid SDN

Optimal path engineering in hybrid software defined networking environments involves leveraging traditional networking and software defined capabilities to determine the most efficient paths for network traffic. In hybrid software defined networks, some parts of the network may be controlled by controllers, while others rely on traditional routing protocols. Leveraging the OpenFlow protocol, widely used in such deployments, to program flow entries in software defined switches is one approach to achieving optimal path engineering in hybrid software defined networks. By specifying specific rules and policies in the switches, we can control traffic forwarding behaviour and steer traffic along desired paths based on application requirements. In this work, the smell detection algorithm, a new variant of bio-inspired method, is adopted to explore its capability in routing. The new paradigm of smell detection agent, its architecture, protocols used, and the concept of hybrid defined network is also explained. A comprehensive experimental examination of within the controller, an algorithm based on smell detecting agents computes the most efficient route from where it began to the intended destination. Simulation results readily demonstrate the smell detection agent based technique's effective functioning in getting the optimum direction. In this work, bio-inspired algorithms outperformed conventional algorithms in terms of performance.

Metaheuristic based segment routing for hybrid software-defined network under heterogeneous environment

Metaheuristic based segment routing for hybrid software-defined network under heterogeneous environment

SDN candidate and protection path selection for link failure protection in hybrid SDNs

Software-Defined Networks (SDNs) have emerged as significant frameworks for enhancing the network flexibility. Currently, the migration from legacy IP networks to pure SDNs promotes the development of hybrid SDNs. However, the inevitable link failures will damage the network reliability. Therefore, this paper focuses on upgrading the legacy routers to SDN switches with minimal deployment overhead for protecting against all link failures, and selecting appropriate protection paths with the routing flexibility of these switches, thus improving the network performance and resilience. Firstly, we propose the heuristic SCS_LN algorithm for SDN Candidate Selection (SCS) that narrows the selection range of SDN candidate nodes through the link protection difficulty and selects the upgraded nodes based on the node protection capability. Secondly, we develop PPS_PM algorithm with the weight-based selection rule for adaptive Protection Path Selection (PPS), which takes interactive path parameters into account, such as Protection Path Length (PPL) and Maximum Link Utilization (MLU). Finally, extensive simulation experiments on diverse network topologies with various parameters are conducted to demonstrate that our proposed algorithms save up to 12.58% of the SDN switch deployment, and gain up to 12.15% and 7.34% improvement of the average PPL and MLU over existing algorithms, respectively.

Secure Multi-Path Selection with Optimal Controller Placement Using Hybrid Software-Defined Networks with Optimization Algorithm

The Internet's growth in popularity requires computer networks for both agility and resilience. Recently, unable to satisfy the computer needs for traditional networking systems. Software Defined Networking (SDN) is known as a paradigm shift in the networking industry. Many organizations are used SDN due to their efficiency of transmission. Striking the right balance between SDN and legacy switching capabilities will enable successful network scenarios in architecture networks. Therefore, this object grand scenario for a hybrid network where the external perimeter transport device is replaced with an SDN device in the service provider network. With the moving away from older networks to SDN, hybrid SDN includes both legacy and SDN switches. Existing models of SDN have limitations such as overfitting, local optimal trapping, and poor path selection efficiency. This paper proposed a Deep Kronecker Neural Network (DKNN) to improve its efficiency with a moderate optimization method for multipath selection in SDN. Dynamic resource scheduling is used for the reward function the learning performance is improved by the deep reinforcement learning (DRL) technique. The controller for centralised SDN acts as a network brain in the control plane. Among the most important duties network is selected for the best SDN controller. It is vulnerable to invasions and the controller becomes a network bottleneck. This study presents an intrusion detection system (IDS) based on the SDN model that runs as an application module within the controller. Therefore, this study suggested the feature extraction and classification of contractive auto-encoder with a triple attention-based classifier. Additionally, this study leveraged the best performing SDN controllers on which many other SDN controllers are based on OpenDayLight (ODL) provides an open northbound API and supports multiple southbound protocols. Therefore, one of the main issues in the multi-controller placement problem (CPP) that addresses needed in the setting of SDN specifically when different aspects in interruption, ability, authenticity and load distribution are being considered. Introducing the scenario concept, CPP is formulated as a robust optimization problem that considers changes in network status due to power outages, controller’s capacity, load fluctuations and changes in switches demand. Therefore, to improve network performance, it is planned to improve the optimal amount of controller placements by simulated annealing using different topologies the modified Dragonfly optimization algorithm (MDOA).

Delegating Data Plane With Cloud-Assisted Routing

Data centers are embracing the software-defined networking (SDN) as it is evident that this technology of completely separating the data plane from the control plane gives more flexibility for their internal routing management and provides better Quality-of-Service (QoS) to the users. Implementing a similar solution to serve the purpose of software-defined wide-area networking using public Internet routing is also gaining popularity. Although, instead of having a complete separation, a hybrid approach to keep most of the control plane along with the least of the data plane in the remote and vice-versa for the local platform may be more fitting. To this end, we propose a new hybrid SDN approach, Cloud-Assisted Routing (CAR), that utilizes the high computational services that cloud offers at a lower price by splitting both control and data plane functions between a local router and a remote cloud computing platform. Such delegation of data plane to a third-party authority requires proper control plane management policies and handling or avoiding possible loops and failures. We detail the architectural view of CAR, address its associated challenges, and present prototype-based evaluations of it for reducing routing table sizes.

An End-Host-Importance-Aware Secure Service-Enabled Hybrid SDN Deployment

Security is critical to networks, but TCP/IP-based legacy networks are difficult to advance new security functions due to the use of costly inflexible hardware devices and error-prone network configurations. Recent literature explores the paradigm of consolidating security services with the forwarding functionality using Software-defined Networking (SDN). Existing full SDN deployment, replacing all legacy network devices with SDN devices, is cost-prohibitive. Whereas the hybrid SDN that only upgrades partial legacy devices to SDN switches is considered practical. However, the challenge is to minimize threats and deployment expenses simultaneously under heterogeneous end-host businesses that have various importance. In this paper, we study the challenge and propose the (EASON) problem. We mathematically formulate the EASON problem as an integer programming problem, prove its non-polynomial time complexity, and propose a heuristic algorithm called BonSéc. We conduct rigorous simulations on real-world topologies and traces. Experimental results show that BonSéc achieves comparable security and cost performances to the optimal solution on small topologies. Meanwhile, it is scalable on larger topologies.

AI-assisted traffic matrix prediction using GA-enabled deep ensemble learning for hybrid SDN

A hybrid software-defined network (SDN), which is a network where traditional routers and SDN protocols coexist during the incremental deployment of SDNs, requires real-time link traffic information for effective deployment. This has called for the need of accurate real-time data analytics and traffic prediction methods. To date, various traffic prediction frameworks have been studied to facilitate analysis and extraction of valuable information from huge sets of incomplete and noisy data. However, due to the linear nature of network design, mainly characterized by manual control plane forwarding configurations, existing traffic prediction frameworks cannot perform consistent traffic prediction over multiple datasets in modern dynamic networks. To address this issue, ensemble-driven approaches based on deep learning (DL) have recently been suggested as a promising solution. Nevertheless, determining the most appropriate combination of baseline DL architectures to be adopted for accurate traffic prediction remains a challenge. This paper proposes a novel DL framework for improved traffic prediction in hybrid SDNs. The framework combines a deep ensemble learning model utilizing multiple dimensionality reduction algorithms and a genetic algorithm (GA). The multi-objective GA is used to perform dynamic optimization of the connection weights and thresholds of the deep ensemble learning model while overcoming the local optima problem. Experimental results show that the proposed approach can achieve more accurate forecast of link traffic than the traditional baseline DL frameworks.

A Trusted Remote Data Trading Scheme in Hybrid SDN for Intelligent Internet of Things

Intelligent internet of things (IIoTs) have these features: heterogeneous network patterns, significant differences in devices, dynamic variability of network topologies, etc. In the complex security situation, it is necessary to reject data from untrusted devices to guarantee the security data trading of IIoTs. In this paper, we focus on the trustworthiness and authentication in a hybrid SDN scenario of IIoTs. For the process of the trusted judgment, we firstly implement the standardized model for the nodes with the device attributes, network states, and operation behaviors. Based on the standardized model, we propose feature evaluation functions in SDN and IP domains, respectively, to calculate the intradomain node trust values to achieve the trusted judgment. To consider the demand for secure data trading for cross-domain devices, we propose a remote data trading scheme in which the data transmitter signs the node identity and its trust value by a group signature and the data receiver verifies the signature. The group signature is not only to protect the privacy of the group members but also to support the dynamic accession and revocation of group members, so it is more suitable for IIoTs where the nodes frequently access/exit. The security is proved under the standard model. We conduct the simulation experiments to evaluate the correctness of the trusted judgment mechanism. The evaluation shows that the scheme has lower computational cost and the higher efficiency of the group signature scheme.

ETHoS: Energy-Aware Traffic Engineering for Sustainable Hybrid SDN

In this paper, we present a traffic engineering scheme for sustainable hybrid Software-Defined Networks (SDN) to reduce the overall energy consumption of the network and increase the amount of programmable traffic. Hybrid SDN involves both legacy and SDN switches because of the migration from a legacy network to an SDN. The primary reason for this migration is to increase the amount of programmable traffic and add flexibility to network management operations such as network monitoring, load distribution, and energy management. The energy management solutions in SDN include dynamic activation or deactivation of network elements and traffic rerouting. However, there exists a trade-off between energy-aware routing and programmable traffic, as unplanned traffic rerouting may transform programmable traffic into a non-programmable one. In this paper, we propose a scheme for dynamic activation of SDN links and optimal route selection of existing flows. In contrast to the previous works, we focus on reducing energy consumption, while maximizing the programmable traffic, as it serves the primary intent of transforming a legacy network into an SDN. The simulation results show that the proposed scheme, ETHoS, increases the energy savings by <inline-formula><tex-math notation="LaTeX">$28.91\%$</tex-math></inline-formula> compared to SENEtoR, an existing scheme.

HyPASS: Design of hybrid-SDN prevention of attacks of source spoofing with host discovery and address validation

SDN (Software-Defined Networking) is a new technology that separates data and control planes; the main components of SDN are OFSwitches and Controller. The traffic flow is monitored by the SDN controller. Initially, OFSwitches lack security rules for packet handling. OFSwitch sends the packet to the controller for examination, creating control messages that favor the packet and establishing necessary flow entry. Host packets are sent to their destination, seeing only the destination host address and not the source host address. The attacker takes advantage of this situation and generates packets with forged source addresses in order to conceal his identity and perform various source address spoofed attacks such as Denial of Service (DoS), man in the middle (MiM), Distributed DoS (DDoS), and so on. This paper proposes a design for discovering hosts proactively, preparing HostTable, configuring flow entry during handshaking, and detecting and preventing source-forged attacks in Hybrid SDN. We called it HyPASS: Design of Hybrid-SDN Prevention of Source Spoofing Attacks with Host Discovery and Address Validation. We used Python for Mininet implementation and tested it on RYU and POX controllers. During the experiment, it identifies and drops 99.99% of packets with the forged source address.

SCOPE: Cost-Efficient QoS-Aware Switch and Controller Placement in Hybrid SDN

This article addresses the joint switch and controller placement problem in a hybrid software-defined network (SDN), which is an intermediate step of transforming a traditional backbone network into a pure SDN. For a hybrid SDN, the quality of service (QoS) is a primary concern for ensuring service guarantee of a traditional network, while providing additional benefits of softwarization. In the SDN, the positions of SDN controllers determine the QoS parameters, such as network throughput and flow processing delays. Many existing solutions determine the controller locations to optimize the latency of network links and control plane load. However, there is a need to address the problem considering additional aspects of the hybrid SDN, such as SDN switch placement and incremental upgrades. In this article, we propose a priority-based SDN switch placement approach and an incremental controller placement approach for the hybrid SDN. Simulation results depict that the proposed scheme increases programmable traffic by 9.90% compared to the existing MapFirst scheme when the switch upgrade budget is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\$}$</tex-math></inline-formula> 400 K. The proposed scheme decreases QoS violation by 20.89% compared to the Greedy approach with 0.3 million flows.

Dynamic Routing Protocol Selection in Multi-Hop Device-to-Device Wireless Networks

Until now, multi-hop device-to-device (MD2D) routing in mobile wireless networks has been designed to operate over a single-protocol routing framework. Consequently, to the best of our knowledge, no framework has been developed to enable the dynamic deployment and switching of multiple MD2D routing protocols under one framework. This paper proposes a multi-protocol framework to introduce the idea of clustering a cell and deploying different MD2D routing protocols for each cluster based on the cluster requirements. To this end, four clusters are developed with varying network conditions (i.e., node density, mobility rate, and the number of flows). Then, the performance of our two previously designed multi-hop routing protocols, namely hybrid SDN architecture for wireless distributed networks (HSAW) and source-based virtual ad hoc routing protocol (VARP-S), are investigated in each cluster in terms of energy consumption, end-to-end (E2E) delay, packet loss, and cellular-band overhead. Based on the achieved simulation results, a multiple-criteria decision-making (MCDM) approach based on the analytic hierarchy process (AHP) is developed to choose the most suitable protocol for each cluster to provide the best performance. The simulation results indicate that our proposed multi-protocol framework provides better performance compared to traditional single-protocol architectures.

Path selection for link failure protection in hybrid SDNs

During the transition from traditional networks to pure Software-Defined Networks (SDNs), hybrid SDNs are derived to provide flexible services. Furthermore, developing effective failure protection algorithms is significantly urgent to improve the robustness and resilience of networks. In this paper, we propose several algorithms, including Straightforward Protection Path Selection with the Source and Destination-based Tunneling mechanism (S-PPSSDT), its simplification PPSSDT and Protection Path Selection with Load-Balancing (PPSLB) algorithms. Considering that the Protection Path Length (PPL) will affect the transmission delay of rerouted packets, S-PPSSDT leverages the source and destination-based tunneling mechanism to select optimum protection paths with the shortest length. Based on classification idea and optimization search, PPSSDT prunes unnecessary path searches in S-PPSSDT. Combining the tunneling mechanism with the priority-based Maximum Link Utilization (MLU) minimization approach, PPSLB also focuses on load balancing during failure protection to achieve potential congestion avoidance simultaneously. Besides, these algorithms redirect the traffic through various tunnels for affected paths by the non-shortest path routing capability of SDN switches. Extensive simulation results indicate that our proposed algorithms can effectively reduce the PPL and MLU of hybrid SDNs during failure protection, and have excellent performance under various network parameters compared with the state-of-the-art algorithms.

On Efficient Service Function Chaining in Hybrid Software Defined Networks

To minimize operating expenses (OPEX) and enhance flexibility for network service provisioning, network function virtualization (NFV) is used to chain an ordered sequence of virtualized network functions (VNFs), also known as service function chain (SFC), which can be placed on commodity servers. As a highly complementary to NFV, software-defined networking (SDN) can offer an agile way of VNF orchestration with the capability of fine-granularity network control over flows. However, one-step migration to SDN is impossible in ISP networks. Thus, in this paper we resort to hybrid SDN to implement SFC provisioning. By jointly optimizing SDN deployment that largely determines capital expenditures (CAPEX) and VNF placement that decides OPEX, we manage to make a tradeoff between CAPEX and OPEX, and to find out an appropriate SDN deployment rate for network operator. We first formulate the problem as an integer linear programming (ILP) model <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol {P}$ </tex-math></inline-formula> , then, reformulate it with column generation technique and decomposition theory to develop a distributed approximation algorithm CGPD which obtains a tight upper bound of optimal solution to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol {P}$ </tex-math></inline-formula> . In order to better decrease CAPEX, a dynamic programming-based heuristic EOES giving importance to effective resource sharing is further designed based on a hidden Markov model. The simulation results indicate that, the difference between <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol {P}$ </tex-math></inline-formula> and CGPD is marginal. CGPD outperforms EOES in terms of total cost, average delay and bandwidth utilization, and EOES on the other hand demands 20% SDN deployment rate which is half of that of CGPD.

A Routing Strategy with Optimizing Linear Programming in Hybrid SDN

A Routing Strategy with Optimizing Linear Programming in Hybrid SDN

IeHDDP: An Integrated Solution for Topology Discovery and Automatic In-Band Control Channel Establishment for Hybrid SDN Environments

In-Band enhanced Hybrid Domain Discovery Protocol (ieHDDP) is a novel integral approach for hybrid Software-Defined Networking (SDN) environments that simultaneously provides a topology discovery service and an autonomous control channel configuration in the band. This contribution is particularly relevant since, to the best of our knowledge, it is the first all-in-one proposal for SDN capable of collecting the entire topology information (type of devices, links, etc.) and establishing in-band control channels at once in hybrid SDN environments (composed by SDN/no-SDN, wired/wireless devices), even with isolated SDN devices. ieHDDP facilitates the integration of heterogeneous networks, for example, in 5G/6G scenarios, and the deployment of SDN devices by using a simple exploration mechanism to gather all the required topological information and learn the necessary routes between the control and data planes at the same time. ieHDDP has been implemented in a well-known SDN software switch and evaluated in a comprehensive set of randomized topologies, acknowledging that ieHDDP is scalable in representative scenarios.

Extended indirect controller-legacy switch forwarding for link discovery in hybrid multi-controller SDN

Though widely perceived as a promising network architecture, Software Defined Networks (SDN) have inherent deployment issues, particularly in terms of a full SDN deployment paving the path for Hybrid Software Defined Networks (hSDN) and subsequently Multi-Controller h-SDN (MC-hSDN) to address limited scalability of the former. Networks allocate resources to applications based on their requirements which are taken care of by the controller. Existing link discovery protocols such as Link Layer Discovery Protocol (LLDP) and Broadcast Domain Discovery Protocol (BDDP) are able to detect links only for OpenFlow switch (OFS) in direct and indirect manners while Indirect Controller Legacy Forwarding (ICLF) scheme detects all links in h-SDN only for a single-controller environment, thus rendering link detection in MC-hSDN incomplete. This paper proposes a novel Extended ICLF (E-ICLF) scheme to fetch the topology in a multi-controller environment. A solitary PACKET_OUT (Pout) is emanated from every domain controller which circulates across the domain’s as nodes appending information which gets dispatched to the initiating controller. Experiments performed with Mininet indicate ports detection improvement and PACKET_ IN (Pin) message exchange reduction by an average of about (0.8%–44.8%) and (56.8%–93.2%) respectively with a fewer overhead of forwarded messages and convergence time to build the topology.