Quality Of Service Guarantees Research Articles

Enhancing low‐priority traffic reconfiguration designs in mixed‐critical avionics networks

AbstractIn avionics system networking, mixed‐critical networks are commonly used to integrate system applications with different levels of guarantees for various traffic classes on a shared resource platform, effectively addressing issues such as cabling, cost, weight, volume, power consumption, etc. However, current fault recovery and reconfiguration techniques mainly focus on high‐priority time‐triggered (TT) traffic, often neglecting the impact of TT traffic reconfiguration on low‐priority traffic. This paper proposes an avionics mixed‐critical networking approach based on the IEEE 802.1CB protocol, which is shown to be more effective for the post‐failure recovery of Rate‐Constrained (RC) traffic (a typical type of low‐priority traffic in TT networks). Furthermore, an elastic reconfiguration algorithm is presented to ensure quality of service for RC traffic during and after reconfiguration, preventing arbitrary application and traffic shutdown triggered by TT traffic reconfiguration. Simulations demonstrate that the proposed approach and algorithm can significantly improve the post‐failure recovery ratio of RC traffic, as well as guarantee quality of service and network throughput of RC traffic during and after reconfiguration to a certain extent.

A Novel Multimodal Deep Learning Framework for Encrypted Traffic Classification

Traffic classification is essential for cybersecurity maintenance and network management, and has been widely used in QoS (Quality of Service) guarantees, intrusion detection, and other tasks. Recently, with the emergence of SSL/TLS encryption protocols in the modern Internet environment, the traditional payload-based classification methods are no longer effective. Some researchers have used machine learning methods to model the flow features of encrypted traffics (e.g. message type, length sequence, statistical features, etc.), and achieved good results in some cases. However, these high-level hand-designed features cannot be used for more fine-grained operations and may lead to the loss of important information, thus affecting the classification accuracy. To overcome this limitation, in this paper, we designed a novel multimodal deep learning framework for encrypted traffic classification called PEAN. PEAN uses the raw bytes and length sequence as the input, and uses the self-attention mechanism to learn the deep relationship among network packets in a biflow. Furthermore, unsupervised pre-training was introduced to enhance PEAN’s ability to characterize network packets. Experiments on a real trace set captured in a large data center demonstrate the effectiveness of PEAN, which achieves better results than the state-of-the-art methods.

WFO: Cloud-Edge Cooperative Data Offloading Strategy Akin to Water Flow

The exponential growth of video data in networks has led to video flow occupying a significant proportion of network traffic, causing congestion and poor service quality. To address this issue, it is crucial to quickly offload data and ensure high-quality service for users, especially in the context of cloud-edge collaboration. We propose a strategy for collaborative data offloading between cloud and edge computing, analogous to water flow (WFO). When users simultaneously access the same data from the same data source, WFO can serve more users within the limited bandwidth of the cloud while maintaining the quality of service. WFO creates a water flow-like data link between nodes to enable data offloading, using multiple nodes in collaboration to offload data for a single node. Experimental results show that compared with typical methods, such as fair-queue and first-come-first-served, WFO can significantly reduce the data offloading delay, guarantee service quality, and effectively reduce network congestion. Moreover, the number of service nodes can be as numerous as possible.

A Multiple QoS Metrics-Aware Virtual Network Embedding Algorithm

Abstract As a key issue of network virtualisation, virtual network embedding (VNE) aims to embed multiple virtual network requests (VNRs) from different applications onto the substrate network effectively. In real networks, about 90% of traffic is generated by different quality of service (QoS) sensitive applications. However, most existing VNE algorithms do not account for the difference. Although several VNE algorithms considered the delay metric of applications, they usually provide strict delay guarantees for all VNRs, leading to a low VNR acceptance ratio. In this paper, we focus on the VNE problem involving multiple QoS metrics and propose a multiple QoS metrics-aware VNE algorithm based on reinforcement learning (RLQ-VNE). We first classify VNRs according to their different requirements for multiple QoS metrics including delay, jitter and packet loss rate, and then introduce reinforcement learning to implement differentiated VNE. Specifically, RLQ-VNE provides strict QoS guarantees for the VNRs with high-level QoS requirements and provides lower QoS guarantees for the VNRs with low-level QoS requirements, thus balancing the QoS guarantee and request acceptance ratio. Simulation results from multiple experimental scenarios show that RLQ-VNE improves the request acceptance ratio and network resource utilisation by sacrificing less QoS.

Uniform distribution elephant herding optimization (UDEHO) based virtual machine consolidation for energy-efficient cloud data centres

Information technology (IT) providers should use cloud-based services due to their flexibility, reliability, and scalability to handle the rising requirement for processing capacity. The maintenance of dependable services between cloud providers and their customers in a cloud environment, on the other hand, depends on Quality of Service (QoS) assurance. Virtual machine (VM) consolidation is nondeterministic polynomial time (NP) hard issue, and numerous heuristic techniques have been suggested to solve it. In this work, the suggested VM consolidation technique takes into account both current and future uniform distribution elephant herding optimization (UDEHO) based VM consolidation approaches for resource utilization via host overload detection (utilization prediction based potential overload detection (UP-POD)) and host underload detection (UP-PUD). A UDEHO method efficiently predicts resource use in the future. Depending on the power utilization and the number of migrations, a power-saving value is advised for identifying under-loaded hosts. Furthermore, the CloudSim toolkit is used to construct and test these techniques using the same experimental parameters. Lastly, the findings demonstrate that the suggested methodologies considerably decrease the number of VM migrations by about 0.073%, the energy usage of about 11%, and SLA violations by 6.15% while retaining QoS guarantees when compared to conventional techniques.

Cloud computing: google firebase firestore optimization analysis

Cloud computing is a new paradigm that provides end users with a secure, personalized, dynamic computing environment with guaranteed service quality. One popular solution is Google cloud firestore, a global-scale not only structured query language (NoSQL) document database for mobile and web apps. Recent research on cloud-based NoSQL databases often discusses the difference between them and SQL databases and their performance. However, using cloud-based NoSQL databases such as firestore is tricky without any scientific comparison methodology, and it needs analysis of how its particular systems work. This study aims to discover what is the best design that could be implemented to optimize data read cost, response size, and time regarding the cloud firestore database. In this study, we develop a grade point average (GPA)-report mocking application to assess data read based on our institution’s needs. This application consists of three functions. Add the graduated GPA and students’ names, and view the ten highest GPAs, GPA average, and total graduated students. The finding indicates that aggregating data on the client side or utilizing the Google cloud function trigger, then updating aggregation data in one transaction significantly reduces document read count (cost), response size, and time.

QoS Guaranteed Power Minimization and Beamforming for IRS-Assisted NOMA Systems

In this letter, to solve the problem of large interference among users and reduce the transmit power consumption of base station while guaranteeing target quality of service (QoS) in downlink intelligent reflecting surface (IRS) assisted non-orthogonal multiple access (NOMA) systems, we present a joint optimization algorithm to design active beamforming for base station and passive beamforming (phase shift matrix) for IRS based on semidefinite relaxation (SDR). The non-convex constraint of signal-to-interference-plus-noise ratio (SINR) is transformed into affine constraint by increasing the dimension of optimization variables. The two subproblems of transmit power minimization and phase shift feasibility are solved iteratively using alternating optimization. To solve the computing performance degradation of SDR in largescale problems, we further propose a low-complexity algorithm based on successive convex approximation (SCA) and the original problem is then determined iteratively by relaxing the constant modulus constraint of IRS. Simulation results show that both algorithms have lower power consumption than the existing algorithms with different number of IRS reflecting elements or transmit antennas, and the SCA algorithm can approach the performance of SDR with lower complexity.

Hierarchical Multiresource Fair Queueing for Packet Processing

Various middleboxes are ubiquitously deployed in networks to perform packet processing functions, such as firewalling, proxy, scheduling, etc., for the flows passing through them. With the explosion of network traffic and the demand for multiple types of network resources, it has never been more challenging for a middlebox to provide Quality-of-Service (QoS) guarantees to grouped flows. Unfortunately, all currently existing fair queueing algorithms fail in supporting hierarchical scheduling, which is necessary to provide QoS guarantee to the grouped flows of multiple service classes. In this paper, we present two new multi-resource fair queueing algorithms to support hierarchical scheduling, collapsed Hierarchical Dominant Resource Fair Queueing (collapsed H-DRFQ) and dove-tailing H-DRFQ. Particularly, collapsed H-DRFQ transforms the hierarchy of grouped flows into a flat structure for flat scheduling while dove-tailing H-DRFQ iteratively performs flat scheduling to sibling nodes on the original hierarchy. Through rigorous theoretical analysis, we find that both algorithms can provide hierarchical share guarantees to individual flows, while the upper bound of packet delay in dove-tailing H-DRFQ is smaller than that of collapsed H-DRFQ. We implement the proposed algorithms on Click modular router and the experimental results verify our analytical results.

Power and Element Allocation Design for RIS–NOMA IoV Networks

In this paper, a cooperative, non-orthogonal multiple access (NOMA)-based internet of vehicles (IoV) network is proposed, which is assisted by a reconfigurable intelligent surface (RIS) to enhance signal transmission. Due to the intelligent control of RISs, the channel condition of our proposed IoV system is more diversified compared to conventional NOMA–RIS schemes, and thus two power allocation schemes are considered to tackle this issue, providing better channel gain to transmit signals. In this proposed scheme, power allocation schemes are discussed for a diverse number of reflecting elements, and a number of elements are obtained serving users near or far. To further improve system capacity and guarantee quality of service (QoS), we derive the number of elements to guarantee the same transmission data sum-rate under different channel qualities. Numerical and simulation results verify the correctness as well as superiority of our proposed scheme.

“A highly demanding measure”: practitioner contributions to improving practice and policy for foster families

Foster families provide at-risk children with a family environment. In Portugal, however, there appears to be a major lack of political investment in foster care programmes, with only around 191 children currently placed with a foster family. To increase these numbers, we need to listen and give a voice to the social workers who provide support to foster carers. This empirical study uses a qualitative methodology based on interviews with practitioners working in the only two organisations offering a foster care programme. The qualitative analysis is inspired by categorical analysis. The findings suggest an urgent need for policy action to train workers throughout the child protection system so as to guarantee service quality standards. Moreover, this should be combined with a mass information campaign aimed at the general public. This would provide a real social image of foster families, as well as improving their recruitment and retention.

Hybrid Optimization Assisted Green Power Allocation Model for QoS-Driven Energy-Efficiency in 5G Networks

5G networks are progressing to offer services with high Quality of Service (QoS) features like high user mobility skills, higher data rates, high reliable communiqué, and lower latency. For this, numerous novel settings like integration of Software-Defined Networking (SDN) and Network Function Virtualization (NFV) should be implemented in the network system. Here, this paper plans to design an optimization-based power allocation model to increase the Effective Power Efficiency (EPE) that offers guaranteed QoS over “Single-Input Single-Output (SISO) and Multiple-Input Multiple-Output (MIMO)-channel oriented 5 G networks”. Moreover, the statistical QoS-based green power allotment system was also analyzed to increase the EPE over other MIMO networks. Particularly, this paper makes an attempt to make the power allocation optimal, which directly ensures the 5 G network energy efficiency when guaranteeing QoS. This is considered to be the optimization issue, which is solved by MS-DA. Our suggested approach can be applied to hybrid energy supply networks with various network topologies, such as 5 G networks, which are now the most extensively used, and is capable of achieving a good resolution through iterative convergence.

Data Center Traffic Scheduling Strategy for Minimization Congestion and Quality of Service Guaranteeing

According to Cisco’s Internet Report 2020 white paper, there will be 29.3 billion connected devices worldwide by 2023, up from 18.4 billion in 2018. 5G connections will generate nearly three times more traffic than 4G connections. While bringing a boom to the network, it also presents unprecedented challenges in terms of flow forwarding decisions. The path assignment mechanism used in traditional traffic scheduling methods tends to cause local network congestion caused by the concentration of elephant flows, resulting in unbalanced network load and degraded quality of service. Using the centralized control of software-defined networks, this study proposes a data center traffic scheduling strategy for minimization congestion and quality of service guaranteeing (MCQG). The ideal transmission path is selected for data flows while considering the network congestion rate and quality of service. Different traffic scheduling strategies are used according to the characteristics of different service types in data centers. Reroute scheduling for elephant flows that tend to cause local congestion. The path evaluation function is formed by the maximum link utilization on the path, the number of elephant flows and the time delay, and the fast merit-seeking capability of the sparrow search algorithm is used to find the path with the lowest actual link overhead as the rerouting path for the elephant flows. It is used to reduce the possibility of local network congestion occurrence. Equal cost multi-path (ECMP) protocols with faster response time are used to schedule mouse flows with shorter duration. Used to guarantee the quality of service of the network. To achieve isolated transmission of various types of data streams. The experimental results show that the proposed strategy has higher throughput, better network load balancing, and better robustness compared to ECMP under different traffic models. In addition, because it can fully utilize the resources in the network, MCQG also outperforms another traffic scheduling strategy that does rerouting for elephant flows (namely Hedera). Compared with ECMP and Hedera, MCQG improves average throughput by 11.73% and 4.29%, and normalized total throughput by 6.74% and 2.64%, respectively; MCQG improves link utilization by 23.25% and 15.07%; in addition, the average round-trip delay and packet loss rate fluctuate significantly less than the two compared strategies.

Hybrid Integrated Aquila Optimizer for Efficient Service Composition with Quality of Service Guarantees in Cloud Computing

Hybrid Integrated Aquila Optimizer for Efficient Service Composition with Quality of Service Guarantees in Cloud Computing

Cloud Host Selection using Iterative Particle-Swarm Optimization for Dynamic Container Consolidation

A significant portion of the energy consumption in cloud data centres can be attributed to the inefficient utilization of available resources due to the lack of dynamic resource allocation techniques such as virtual machine migration and workload consolidation strategies to better optimize the utilization of resources. We present a new method for optimizing cloud data centre management by combining virtual machine migration with workload consolidation. Our proposed Energy Efficient Particle Swarm Optimization (EE-PSO) algorithm to improve resource utilization and reduce energy consumption. We carried out experimental evaluations with the Container CloudSim toolkit to demonstrate the effectiveness of the proposed EE-PSO algorithm in terms of energy consumption, quality of service guarantees, the number of newly created VMs, and container migrations.

Wild Networks: Exposure of 5G Network Infrastructures to Adversarial Examples

Fifth Generation (5G) networks must support billions of heterogeneous devices while guaranteeing optimal Quality of Service (QoS). Such requirements are impossible to meet with human effort alone, and Machine Learning (ML) represents a core asset in 5G. ML, however, is known to be vulnerable to adversarial examples; moreover, as our paper will show, the 5G context is exposed to a yet another type of adversarial ML attacks that cannot be formalized with existing threat models. Proactive assessment of such risks is also challenging due to the lack of ML-powered 5G equipment available for adversarial ML research. To tackle these problems, we propose a novel adversarial ML threat model that is particularly suited to 5G scenarios, and is agnostic to the precise function solved by ML. In contrast to existing ML threat models, our attacks do not require any compromise of the target 5G system while still being viable due to the QoS guarantees and the open nature of 5G networks. Furthermore, we propose an original framework for realistic ML security assessments based on public data. We proactively evaluate our threat model on 6 applications of ML envisioned in 5G. Our attacks affect both the training and the inference stages, can degrade the performance of state-of-the-art ML systems, and have a lower entry barrier than previous attacks.

Risk-Averse Investment Strategy for MEC Service Provisioning: A Data-Driven Distributionally Robust Solution

The emerging Internet of Things (IoT) era has stimulated many new computation-intensive applications. To support them, mobile edge computing (MEC) is a promising solution that allows users to offload their heavy computing tasks to nearby edge servers. Taking such computation offloading as the service, application service providers (ASPs) can rent resources from mobile network operators for MEC service provisioning. However, it is challenging for ASPs to determine how many resources to rent at different regions and times due to the uncertain user demand. When making an investment strategy, it is crucial to maximize the profit with the consideration on the Quality of Service (QoS), where a joint scheduling on both communication and computing resource under the uncertain demand is needed. To deal with the uncertainty, the probability distribution information is usually employed, which, unfortunately, might be hardly obtainable in practice. Therefore, in this article, we propose a data-driven risk-averse MEC resource investment (DRAI) strategy, where the demand uncertainty issue is particularly addressed. Specifically, we formulate the DRAI strategy into a stochastic optimization problem, which can achieve the expected optimal profit under the QoS guarantee statistically from a risk-averse perspective. To solve it, instead of relying on specific distribution models, we construct an ambiguity set based on the statistical characteristics derived from the historical data that contains all possible distributions, and develop a data-driven distributionally robust solution, aiming at achieving the best strategy under the worst case to make it trustworthy. Simulation results illustrate the effectiveness of the proposed DRAI strategy.

End-to-End Service Auction: A General Double Auction Mechanism for Edge Computing Services

Ubiquitous powerful personal computing facilities, such as desktop computers and parked autonomous cars, can function as micro edge computing servers by leveraging their spare resources. However, to harvest their resources for service provisioning, two significant challenges will arise: how to incentivize the server owners to contribute their computing resources, and how to guarantee the end-to-end (E2E) Quality-of-Service (QoS) for service buyers? In this paper, we address these two problems in a holistic way by advocating COMSA. Unlike the existing double auction schemes for edge computing which mostly focus on computing resource trading, COMSA addresses the joint problem of double auction mechanism design and network resource allocation by explicitly taking spectrum allocation and data routing into account, thereby providing E2E QoS guarantees for edge computing services. To handle the design complexity, COMSA employs a two-step procedure to decouple network optimization and mechanism design, which hence can be applied to general network optimization problems for edge computing. COMSA holds some critical economic properties, i.e., truthfulness, budget balance, and individual rationality. Our extensive simulation studies demonstrate the effectiveness of COMSA.

A Decision Tree-Based Online Traffic Classification Method for QoS Routing in Data Center Networks

In data center networks, how to ensure the quality of service (QoS) of traffic effectively has become an important optimization goal. Traffic classification has been widely studied to guarantee network flow QoS since it provides a basis for the network performance level requirement of different flow types. However, traditional network traffic classification methods, which can only identify traffic type offline, have no ability for online classification and the in-time QoS guarantee. To solve this problem, we propose an online traffic classification for QoS routing (OCQR) framework based on programmable data plane in this paper. Firstly, in order to improve the accuracy of flow classification and reduce the impact on line-rate packet forwarding, the way of machine learning model offline training and online deployment is used to classify the network flow in real time. Based on the hardware foundation of programmable switch and the complexity of machine learning algorithm, a CART decision tree model is used to classify network flows. Secondly, in order to actually deploy and run the decision tree model in the programmable switch with limited computing and storage resources, we prune the decision tree model and optimize the leaf nodes to reduce the size of the decision tree and improve the classification recall rate. Finally, by building a P4 simulation environment, the recall rate of OCQR’s classified scheduling of some application flows reaches more than 98%, which is consistent with the evaluation results of the offline dataset. At the same time, compared with the classification method based on SDN, OCQR does not require additional bandwidth occupation, so it has less impact on network performance.

Double QoS Guarantee for NOMA-Enabled Massive MTC Networks

Massive connections and diverse Quality of Service (QoS) requirements pose a major challenge for machine-type communication (MTC) networks. In this article, to satisfy the various QoS requirements of a massive number of MTC devices (MTCDs), the devices are divided into multiple clusters based on the QoS characteristics. The cluster access control and intracluster resource allocation problems are studied to satisfy the double delay requirements in the access and data transmission phases in a cross-layer approach. Specifically, we formulate an access control problem to maximize the access efficiency with constraints on access and transmission delays. An efficient algorithm is proposed to adaptively adjust the access time intervals and backoff factors of the clusters for different numbers of active MTCDs and transmission rates. Given the access parameters, nonorthogonal multiple access is adopted in resource allocation to maximize the system utility function while guaranteeing the delay requirements for each accessed MTCD. An efficient sequential convex programming iterative algorithm is proposed to solve the NP-hard nonconvex problem with two typical utility objectives: 1) total throughput and 2) consumed power. Simulation results show that the proposed scheme can achieve better performance in terms of access efficiency, delay, throughput, and consumed power than other schemes. The impacts of various parameters, including delay and traffic rate, on the performance, are disclosed.

Integrated optimization of train stop planning and ticket pricing with equity concerns of passengers for high-speed railways

Ticket pricing, which is critical to increasing the revenue for high-speed railways, is typically optimized with a given train stop plan. However, the passenger distributions are restricted by fixed train stop plans, and the optimal ticket price scheme may not be achieved. Therefore, a mixed-integer linear programming model is proposed to optimize collaboratively train stop planning and ticket pricing in this study. The objective is to maximize the total ticket revenue, while the total number of train stops is limited to guarantee service quality. Furthermore, equity concerns of passengers are addressed by ensuring that passengers have equitable travel costs and opportunities to access high-speed railways. Finally, numerical experiments are conducted on a hypothetical railway line and the Zhengzhou-Xi’an high-speed railway corridor to demonstrate the application of the proposed approach. The computational results indicate that the proposed method can increase the total ticket revenue by 27% through adding 14 train stops and formulating a new ticket price scheme compared to the traditional method. In addition, the equity performance can be kept at a level of 1.5.