Network Resource Optimization Research Articles

Flow Entry Timeouts Optimization over Software Defined Networks Supporting Elephant Flow Classification

<p>Elephant flow (elephant) classification is significant for network performance management and resource optimization. Classifying elephants over Software Defined Networks (SDNs) often relies on statistics counted by switches and transferred to controllers, leading to a huge control channel bandwidth occupation that degrades network latency and user experience. Classifying elephants using flow packets forwarded to controllers completely avoids moving statistics from switches to controllers, but couples flow entry timeouts to elephant classification accuracy, time efficiency, flow table size, control channel bandwidth usage, and network latency. This paper aims to find the best flow entry timeouts to optimize the objectives by modeling the objectives and formulating a multi-objective optimization problem. The number of objectives is further reduced to 3 and the problem is solved by Machine Learning (ML) approaches. Extensive evaluations are made over real packet traces. To the best of our knowledge, this work is the first effort that explores all the objectives related to flow entry timeouts when using flow packets forwarded to controllers to classify elephants over SDNs.</p> <p> </p>

Dynamic Radio Access Selection and Slice Allocation for Differentiated Traffic Management on Future Mobile Networks

The development of future wireless networks focuses on providing services with strict, dynamic, and diverse quality of service (QoS) requirements. In this sense, the network slicing paradigm arises as a critical piece on the efficient allocation and management of network resources, allowing for dividing the network into several logical networks with specific functionalities and performance. This paper aims at finding the best combination of access network and network slices over a heterogeneous environment to fulfill users’ requests and optimize network resources usage. We propose the Dynamic radio Access selection and Slice Allocation (DASA) algorithm, flexibly adapted to network conditions, user priorities, and mobility behavior. DASA is based on a multi-attribute decision making (MADM) and analytical hierarchy process (AHP) to face the complex problem of network selection. Moreover, it uses a cooperative game theory approach to handle load balancing during overload situations. This work presents an integral solution that combines software-defined network (SDN) and network function virtualization (NFV) technologies to improve network performance and user satisfaction. DASA algorithm is evaluated through network-level simulations, focusing on flexibility and the effective utilization of network resources during network selection and load balancing mechanisms.

Cooperative Multi-Agent Deep Reinforcement Learning for Dynamic Virtual Network Allocation With Traffic Fluctuations

Network traffic and computing demand have been changing dramatically due to the growth of various types of network services, e.g., high-quality video delivery and operating system (OS) updates. To maximize the utilization efficiency of limited network resources, network resource control technology is required for smooth and quick operation when network demands change. Therefore, we propose a dynamic virtual network (VN) allocation method based on cooperative multi-agent deep reinforcement learning (Coop-MADRL). This method can quickly optimize network resources even while network demands are drastically changing by learning the relationship between network demand patterns and optimal allocation by using deep reinforcement learning (DRL) in advance. The key idea is to use a multi-agent technique for a reinforcement learning (RL) based dynamic VN allocation method, which can reduce the number of candidate actions per agent and can improve the performance for VN allocation. Moreover, a cooperation technique improves the efficiency of VN allocation. From results of a simulation evaluation, Coop-MADRL can calculate effective allocation within 1 s, which reduces the maximum server and link utilization and drastically reduces the constraint violations compared with that of the static VN allocation method. Furthermore, we revealed that the learning with various mixed traffic models could achieve a high generalization performance for all traffic patterns.

A DDoS attack detection and countermeasure scheme based on DWT and auto-encoder neural network for SDN

Software Defined Networking provides new functionalities to easily manage, configure, and optimize network resources by introducing a clear separation between the control entity and the forwarding devices. Such functionalities also help network operators detect and mitigate the security attacks to the network and provide better security level when compared to the traditional networks. However, some security threats, particularly distributed denial of service (DDoS) attacks, keep their effectiveness in degrading the availability of the networks even if the networking paradigm have changed. Existing DDoS attack detection approaches for SDN are mainly based on statistical (threshold-based) and Machine Learning-based (ML) approaches. Considering the dynamic characteristics of the network traffic, finding a dynamic threshold is somehow problematic. On the other hand, finding an appropriate feature that can discriminate DDoS attack from normal traffic is challenging for ML-based approaches. Therefore, to address the aforementioned issues, in this work, we propose a DDoS attack detection and countermeasure scheme based on discrete wavelet transform (DWT) and auto-encoder neural network for SDN. The proposed scheme extracts statistical features from the wavelet transform to be processed by an auto-encoder neural network to detect samples of DDoS attack traffic. Later, to reduce the computational burden imposed by the neural network model, the average hit rate in the flow table of the switches is used to activate the DDoS detection of the scheme. We also provide a detailed performance analysis by considering the computational cost complexity of the algorithms proposed in scheme and the evaluation of the successful detection rate with simulations. Our experimental results show that the proposed scheme achieves high detection rate against DNS amplification, Network Time Protocol and TCP SYN flood attacks with a remarkably low false alarm rate.

RT-SDN: Adaptive Routing and Priority Ordering for Software-Defined Real-Time Networking

In this article, an adaptive real-time communication system is proposed that leverages the software-defined networking (SDN) paradigm to provide end-to-end deadline guarantees. SDN is an emerging networking paradigm that allows control of the network through directly programmable software controllers, offering the flexibility to manage and optimize network resources dynamically. By utilizing these SDN features, a novel networking system, called RT-SDN, is presented that can effectively support real-time communication through cooperative routing and scheduling. To this end, we present a highly efficient routing algorithm that can adaptively reconfigure the routes of existing flows to find bandwidth-guaranteed routes for all flows. We then introduce a new priority assignment scheme that can achieve better deadline guarantees (i.e., better schedulability). In addition, RT-SDN allows routing and scheduling to operate together by employing a feedback loop between them. We implemented a prototype of RT-SDN as an SDN controller and deployed it on a testbed network of 30 BeagleBone devices. Our experiment results show that RT-SDN can be deployed in real-world commodity networks to provide end-to-end deadline guarantees, and the proposed schemes collectively improve the schedulability to a significant degree.

Dynamic Network Slicing Orchestration for Remote Adaptation and Configuration in Industrial IoT

As an emerging and prospective paradigm, the industrial Internet of Things (IIoT) enable intelligent manufacturing through the interconnection and interaction of industrial production elements. The traditional approach that transmits data in a single physical network is undesirable because such a scheme cannot meet the network requirements of different industrial applications. To address this problem, in this article, we propose a network slicing orchestration system for remote adaptation and configuration in smart factories. We exploit software-defined networking and network functions virtualization to slice the physical network into multiple virtual networks. Different applications can use a dedicated network that meets its requirements with limited network resources with this scheme. To optimize network resource allocation and adapt to the dynamic network environments, we propose two heuristic algorithms with the assistance of artificial intelligence and the theoretical analysis of the network slicing system. We conduct numerical simulations to learn the performance of the proposed algorithms. Our experimental results show the effectiveness and efficiency of our proposed algorithms when multiple network services are concurrently running in the IIoT. Finally, we use a case study to verify the feasibility of the proposed network slicing orchestration system on a real smart manufacturing testbed.

Physical-layer impairment estimation for arbitrary spectral-shaped signals in optical networks.

In long-haul fiber-optic networks, precise modeling of physical-layer impairments (PLIs) is crucial to optimizing network resource usage while ensuring adequate transmission quality. In order to accurately estimate PLIs, many mathematical models have been proposed. Among them, the so-called Gaussian noise (GN) model is one of the most accurate and simple enough to use on complex continental-size networks. However, the closed-form GN model assumes that the signals can be represented as having rectangular spectra, leading to a significant estimation error in typical cases when this assumption is violated. We propose the component-wise Gaussian noise (CWGN) PLI model that can account for arbitrary spectral-shaped demands. The CWGN model is computationally simple and suitable for most network management approaches. Results indicate that the CWGN model can prevent as much as a 136% overestimation of the PLIs resulting from the closed-form GN model applied to network lightpaths containing cascaded filters.

A resource-aware control approach to vehicle platoons under false data injection attacks

Wireless vehicle-to-vehicle communication brings inevitable imperfections. This work simultaneously addresses the resource utilization and security issues for a vehicle platoon. Inspired by the modeling of denial of service attacks, a novel queuing model is constructed to depict false data injection attacks. A switched event-triggered mechanism is proposed to optimize network resources. The transmission rate can be actively reduced when the system is under malicious attacks. Then, a unified error system is established, where string stability is interpreted as global exponential stability. By using a proper Lyapunov function, a co-design approach is developed for closed-loop controllers and event-triggering parameters, with which the vehicle platoon can maintain a small safety distance and resist the negative impacts of cyber attacks. Finally, the proposed methods are verified by a virtual vehicle platoon.

Approximation of Capacity in MIMO Systems

This paper introduces functional approximations to the MIMO capacity over flat Rayleigh fading channels, which allow for analytical solutions to network resource optimization problems. This approximation allows to solve the problem of resource allocation optimization in radio networks and in other systems used to transfer information. The precision of the suggested approximations is assessed and is shown to provide a very close match to the exact capacity expression.

Performance of Dense Wireless Networks in 5G and beyond Using Stochastic Geometry

Device density in cellular networks is expected to increase considerably in the near future. Accordingly, the access point (AP) will be equipped with massive multiple-input multiple-output (mMIMO) antennas, using collimated millimeter-wave (mmW) and sub-THz communications, and increasing the bandwidth to accommodate the growing data rate demands. In this scenario, interference plays a critical role and, if not characterized and mitigated properly, might limit the performances of the network. In this context, this paper derives the statistical properties of the aggregated interference power for a cellular network equipping a mMIMO cylindrical array. The proposed statistical model considers the link blockage and other network parameters such as antenna configuration and device density. The findings show that the characteristic function (CF) of the aggregated interference power can be regarded as a weighted mixture of two alpha-stable distributions. Furthermore, by analyzing the service probability, it is found that there is an optimal configuration of the array depending on the AP height and device density. The proposed statistical model can be part of the design of dense networks providing valuable insights for optimal network deployment and resource management and scheduling.

QoS‐aware IoT networks and protocols: A comprehensive survey

SummaryThe vast number of smart cloud applications that communicate with the “things” over a variety of physical networks and communication protocols contribute to the rise of complexity in Internet of Things (IoT) systems. The diversity of end‐user requirements related to the volume of generated data, its variety, and the velocity of its transmission makes quality of service (QoS) provisioning even more crucial and challenging in IoT. This paper provides a comprehensive and up‐to‐date survey of QoS support in IoT networks and communication protocols. An analysis of the QoS‐aware IoT architectures, layer‐dependent QoS metrics, and network resource optimization methods utilized in IoT systems are given. The limitations of the current state‐of‐the‐art studies for efficient delivery of QoS metrics are discussed. The paper concludes with future research directions on end‐to‐end QoS provisioning in IoT.

Towards delay-optimized and resource-efficient network function dynamic deployment for VNF service chaining

By decoupling virtualized network functions from the dedicated network equipment on which they run, Network Function Virtualization (NFV) has brought a flexible and economical way to support the complex communication demands of different applications. Virtualized Network Functions (VNFs) can be dispatched and deployed as instances of plain software on or near the communication paths of applications to establish Service Function Chains (SFCs), so as to provide special packet processing operations beyond simple packet forwarding. However, it is still a great challenge to dynamically place appropriate network functions at suitable locations so as to improve the efficiency of establishing SFCs and optimize network resource utilization. In this paper, the mechanism of dynamically deploying customized network functions via NFV is proposed. By predicting the future popularities of applications to switches, it adaptively places most of the appropriate network functions in corresponding forwarding equipment before they are massively requested. The serious latency and extra resource consumption caused by real-timely dispatching and deploying most of the requested network functions will be avoided. Then, the approach of Ant Colony Optimization (ACO) inspired multi-switch cooperative network function providing is devised. By cooperating multiple forwarding equipment on the packet transmission path, it makes full use of the already placed network functions to support packet processing operations in time with the cost and delay factors jointly considered. Simulation results show that the proposed mechanism has significant improvements in time overhead and resource utilization compared with the current state of the art. Specifically, our mechanism is capable of improving the service delay, the function utilization ratio, and the SFC adjustment efficiency by about 14%, 10% and 12% respectively, compared with corresponding work.

A study on resource reallocation in regional energy networks based on the adjustment of supply and demand nodes

In this paper, we propose and analyse a regional energy network resource allocation scheme and optimization model for regions where the number of energy supply nodes grows seasonally, including the optimal division of the energy supply range of each energy supply node based on distance, the optimal path planning scheme of the energy pipeline network connecting energy supply and consumption nodes, and the optimal allocation/reallocation model of regional energy network resources with the objective of optimal operational economy. The proposed scheme for the optimal redistribution of regional energy network resources is used to analyse and study the case area, and a scheme for the division of energy supply nodes in the case area, a scheme for the construction path of energy pipeline network and a planning strategy for the optimal redistribution of energy network resources are developed to verify the feasibility of the method in this paper.

Multicast traffic grooming in elastic optical network under Dynamic scenario

Elastic optical networks allow elastic allocation and de-allocation of optical resources to optimize network resources and reduce traffic demand blocking probability for dynamic traffic demands. The routing of dynamic traffic demands is a challenging task since the traffic demands are not predefined, they arrive and leave randomly. The approach presented here is a grooming, routing and spectrum allocation technique for multicast traffic demands in elastic optical networks for dynamic type of traffic demands. The simulation results show reduced blocking probability compared to existing approach.

Location-Aware Node Management Solution for Multi-Radio Dual Connectivity Scenarios.

The location of user equipments (UEs) allows application developers to customize the services for users to perceive an enhanced experience. In addition, this UE location enables network operators to develop location-aware solutions to optimize network resource management. Moreover, the combination of location-aware approaches and new network features introduced by 5G enables to further improve the network performance. In this sense, dual connectivity (DC) allows users to simultaneously communicate with two nodes. The basic strategy proposed by 3GPP to select these nodes is based only on the power received by the users. However, the network performance could be enhanced if an alternative methodology is proposed to make this decision. This paper proposes, instead of power-based selection, to choose the nodes that provide the highest quality of experience (QoE) to the user. With this purpose, the proposed system uses the UE location as well as multiple network metrics as inputs. A dense urban scenario is assumed to test the solution in a system-level simulation tool. The results show that the optimal selection varies depending on the UE location, as well as the increase in the QoE perceived by users of different services.

A Novel Approach for distributed denial of service defense using continuous wavelet transform and convolutional neural network for software-Defined network

Software-Defined Networks (SDNs) have emerged particularly for medium and large scale networks since they introduce agility and flexibility with the help of centralized network management by abstracting control plane from data forwarding plane. Although this centralized architecture provides various advantages in terms of effortlessly managing and optimizing network resources, this makes SDN vulnerable to conventional distributed denial of service (DDoS) attacks by making the network inoperable due to the overloaded network traffic. To address the vulnerability, in this work, we propose a detection and countermeasure scheme based on continuous wavelet transform (CWT) and convolutional neural network (CNN). The scheme uses features obtained from CWT as the input for the CNN classifier to differentiate attack samples from the normal ones. Our experimental results show that the proposed scheme achieves high detection rate against DNS amplification, NTP and TCP-SYN flood attacks with a remarkably low false alarm rate.

Crowdsourcing Framework for QoE-Aware SD-WAN

Quality of experience (QoE) is an important measure of users’ satisfaction regarding their network-based services, and it is widely employed today to provide a real assessment of the service quality as perceived by the end users. QoE measures can be used to improve application performance, as well as to optimize network resources and reallocate them as needed when the service quality degrades. While quantitative QoE assessments based on network parameters may provide insights into users’ experience, subjective assessments through direct feedback from the users have also gathered interest recently due to their accuracy and interactive nature. In this paper, we propose a framework that can be used to collect real-time QoE feedback through crowdsourcing and forward it to network controllers to enhance streaming routes. We analyze how QoE can be affected by different network conditions, and how different streaming protocols compare against each other when the network parameters change dynamically. We also compare the real-time user feedback to predefined network changes to measure if participants will be able to identify all degradation events, as well as to examine which combination of degradation events are noticeable to the participants. Our aim is to demonstrate that real-time QoE feedback can enhance cloud-based services and can adjust service quality on the basis of real-time, active participants’ interactions.

AI-assisted intent-based traffic grooming in a dynamically shared 5g optical fronthaul network.

The extremely high number of services with large bandwidth requirements and the increasingly dynamic traffic patterns of cell sites pose major challenges to optical fronthaul networks, rendering them incapable of coping with the extensive, uneven, and real-time traffic that will be generated in the future. In this paper, we first present the design of an adaptive graph convolutional network with gated recurrent unit (AGCN-GRU) network to learn the temporal and spatial dependencies of traffic patterns of cell sites to provide accurate traffic predictions, in which the AGCN model can capture potential spatial relations according to the similarity of network traffic patterns in different areas. Then, we innovatively consider how to deal with the unpredicted burst traffic and propose an AI-assisted intent-based traffic grooming scheme to realise automatic and intelligent cell sites clustering and traffic grooming. Finally, a software-defined testbed for 5G optical fronthaul network was established, on which the proposed schemes were deployed and evaluated by considering traffic datasets of existing optical networks. The experimental results showed that the proposed scheme can optimize network resource allocation, increase the average efficient resource utilization and reduce the average delay and the rejection ratio.

Towards Encrypted In-Network Storage Services with Secure Near-Duplicate Detection

In-network storage is recognized as a vital component of many emerging network architectures, which facilitates high-quality and efficient content-centric services. In this trend, providing content-based near-duplicate detection (NDD) services among in-network storage becomes naturally necessary for network traffic alleviation and resource optimization. However, due to the increasing attacking surfaces, storing data in the networked environment inevitably raises new concerns about user privacy exposure and unauthorized data access. Therefore, we aim to design a secure NDD service in the context of encrypted in-network storage. For efficiency, we first leverage the fingerprint techniques and locality-sensitive hashing to convert the problem of NDD into the keyword search. We then adopt an efficient multi-key searchable encryption scheme, which requires only one encrypted query from the user even the data are from multiple content providers encrypted with different keys. As simply combining the above methods does not appear to directly locate accurate results, we then devise a secure result refining scheme via Yao's garbled circuits to avoid user-side post-processing. Furthermore, we enhance our design to address the potential malicious behavior of in-network servers. Extensive evaluations of real-world image dataset demonstrate that our design can achieve comparable accuracy to the plaintext with modest security overhead.

QoE-Aware Video Streaming over Integrated Space and Terrestrial 5G Networks

The integration of the space information network (SIN) with terrestrial infrastructures has been attracting significant attention in the context of 5G, where satellite communications can be leveraged as additional capabilities such as backhauling between the core network and remote mobile edge sites. However, simple addition of SIN capabilities to terrestrial 5G does not automatically lead to enhanced service performance without systematic scheduling of coexisting resources. In this article, we focus on the scenario of multi-link video streaming over both parallel geostationary Earth orbit (GEO) satellite and terrestrial 5G backhaul links for enhancing user quality of experience and network efficiency. The distinct challenge is the complex optimization of scheduling video segment delivery via two parallel channels with very different characteristics while striving to enhance the video quality and resource optimality. We carried out systematic experiments based on a real-life 5G testing framework with integrated GEO satellite and terrestrial backhaul links. The experimental results demonstrate the effectiveness of our proposed 5G edge-computing-based solution for holistically achieving assured user experiences and optimized network resource efficiency in terms of video traffic offloading.