Last updated: 2024-05-21 03:01 UTC
All documents
Number of pages: 114
Author(s) | Title | Year | Issue | Keywords | ||
---|---|---|---|---|---|---|
Miao Ye, Chenwei Zhao, Peng Wen, Yong Wang, Xiaoli Wang, Hongbing Qiu | DHRL-FNMR: An Intelligent Multicast Routing Approach Based on Deep Hierarchical Reinforcement Learning in SDN | 2024 | Early Access | Deep Hierarchical Reinforcement Learning Multicast Tree Deep Reinforcement Learning Software-Defined Networking | The multicast routing problem in software-defined networking (SDN) is an NP-hard problem. The existing solution methods based on deep strength learning suffer from the problems of branch redundancy, an excessively large action space and slow convergence of the intelligent models. In this paper, an intelligent multicast routing algorithm based on deep hierarchical reinforcement learning is proposed to circumvent the aforementioned problems. First, the optimal multicast tree problem is decomposed into two subproblems: fork node selection and the construction of an optimal path from a fork node to a destination node. Second, a multichannel matrix is designed as the state space for the internal and external controllers of hierarchical reinforcement learning based on the global network-aware information characteristics of SDN. Then, different action spaces are designed for the upper and lower subproblems, four action selection policies are designed for constructing multicast paths, and different reward policies are designed at different levels. Finally, a series of experiments and their results show that the designed algorithm not only searches the multicast tree efficiently but also converges faster and without redundant branches, with better performance in terms of bandwidth, delay and packet loss rate than the current mainstream solution algorithms. The codes for DHRL-FNMR are open and available at https://github.com/GuetYe/DHRL-FNMR. | 10.1109/TNSM.2024.3402275 |
Kaiyi Zhang, Nancy Samaan, Ahmed Karmouch | A Machine Learning-Based Toolbox for P4 Programmable Data-Planes | 2024 | Early Access | Computational modeling Training Quantization (signal) Analytical models Task analysis Pipelines Optical switches Intelligent data-planes P4 machine learning neural networks traffic classification | Intelligent data-planes (IDPs) can enhance network service performance and adaptation speed by executing one or more machine learning (ML) models directly on the served flows. The real-time ML inference enables line-speed decision-making for some traffic management functionalities. Due to the inherent scarcity of both the computational and memory resources and the strict high-speed per-packet processing demands, existing IDP deployments either realize only a limited set of ML models such as decision trees, or require substantial modifications in the switch hardware. In this paper, we propose INQ-MLT, a novel ML-based management toolbox to address the aforementioned limitations. INQ-MLT delegates the task of training various ML models to the control-plane. The latter adopts a tailored quantization-aware training process to compensate for the effect of precision loss resulting from quantization. The toolbox then employs a quantization mechanism to transform the trained ML model parameters (e.g., weights and activations) from floating-point representations to compact low-precision fixed integer values that can be easily processed and stored in the data-plane. Finally, the trained model is deployed into the IDP pipeline by restricting all its inference operations to basic arithmetic operations. To analyze the performance of INQ-MLT, we quantify the accuracy loss resulting from the quantization step through rigorous theoretical analysis. A proof-of-concept implementation of the proposed toolbox is developed using P4-based software switches. Experiments on two use-cases demonstrate that the deployed quantized models have almost no loss of accuracy when compared to their floating-point counterparts. | 10.1109/TNSM.2024.3402074 |
Francesco Betti Sorbelli, Federico Corò, Punyasha Chatterjee, Sajjad Ghobadi, Lorenzo Palazzetti, Cristina M. Pinotti | A Novel Graph-Based Multi-Layer Framework for Managing Drone BVLoS Operations | 2024 | Early Access | Drones Path planning Planning Risk management Autonomous aerial vehicles Visualization Vegetation Drones BVLoS Connectivity Ground risk | Drones have become increasingly popular in a variety of fields, including agriculture, emergency response, and package delivery. However, most drone operations are currently limited to within Visual Line of Sight () due to safety concerns. Flying drones Beyond Visual Line of Sight () broadens to new challenges and opportunities, but also requires new technologies and regulatory frameworks to ensure that the drone is constantly under the control of a remote operator. In this work, we propose a novel graph-based multi-layer framework that closely resembles real-world scenarios and challenges in order to plan drone operations. Our framework includes layers of constraints such as ground risk, cellular network infrastructure, and obstacles, at different heights. From the multi-layer structure, a graph is constructed whose edges are weighted with a dependability score that takes into account the information of the layers, allowing efficient path planning of missions, using algorithms such as Dijkstra’s. Since the built graph can be really large, we also propose lighter graph-based corridors by considering only a limited portion of the original graph. Through extensive experimental evaluation on a real dataset, we demonstrate the effectiveness of our framework in solving the (), which can be efficiently solved by applying the Dijkstra’s algorithm. | 10.1109/TNSM.2024.3401175 |
Surabhi Sharma, Sateesh K. Peddoju | Efficient Multi-Broker Load Balancing in Event Driven Pub-Sub Networks | 2024 | Early Access | Load management Load modeling Temperature sensors Routing Data models Protocols Overlay networks Event driven networks publish/subscribe model application layer topic management load balancing | Publish-Subscribe (Pub-Sub) network is a communication paradigm where publishers produce data on specific topics and subscribers subscribe to these topics. Brokers are middleware facilitating data delivery and communication based on topics. However, brokers are geographically distributed in a multi-broker environment, offering different service times, and tend to become overloaded due to the popularity of the topics when an event occurs. This results in an intolerable average delivery delay. Therefore, we propose an efficient topic-aware low latency load balancing approach that reduces the delay by handling unequal traffic distribution due to data popularity, varied request rates, and hierarchical topic ordering. The proposed approach is manifold. First, it associates the topics to a broker using a Trie data structure, identifies Hot topics based on the outlier detection method, and balances the broker load based on sojourn time modeling and heuristic approach. We use a Pub-Sub MQTT testbed to experiment with a Mosquitto broker distributed network. It reduces the clients’ average waiting time by 11%. Our approach distributes the load 20% more evenly than other approaches, and the average server utilization rate is close to 22%, which is proximal to the optimal approach and better than other approaches under study. | 10.1109/TNSM.2024.3401484 |
Chong Liu, Ruixiang Li, Fuxiang yuan, Shichang Ding, Yan Liu, Xiangyang Luo | 6Subpattern: Target Generation Based on Subpattern Analysis for Internet-Wide IPv6 Scanning | 2024 | Early Access | 6G mobile communication Entropy Clustering algorithms IP networks Heuristic algorithms Internet Hamming distances IPv6 scanning Active address Pattern mining Subpattern analysis Target generation | IP scanning is crucial for network management and security. However, the brute-force scanning is infeasible in IPv6 networks due to the vast address space. Consequently, target generation algorithms (TGAs) have become necessary to address this issue. Nevertheless, existing algorithms often struggle with low hit rates due to coarse-grained pattern mining. To address this problem, we propose 6Subpattern, a target generation algorithm based on subpattern analysis for Internet-wide IPv6 scanning. 6Subpattern first clusters seeds into high-density regions according to the seed structure information. Subsequently, pattern mining and subpattern analysis are carried out in these regions. Different from previous works, 6Subpattern can obtain all fine-grained patterns while automatically avoiding the influence of outlier addresses and the quandary of setting heuristic thresholds through subpattern analysis. Moreover, pattern refining is conducted based on the distribution of nibbles in address regions to further narrow the scanning space. Finally, targets are effectively generated according to the density of the patterns. Experimental results on real-world networks demonstrate that the address patterns discovered by 6Subpattern provide a superior scanning space than existing algorithms. Further results of hit rates on nine candidate seed sets reveal that 6Subpattern can achieve a 53%-315% improvement over the static TGAs on all seed sets and achieve a 15%-25% improvement on all randomly sampled seed sets compared with dynamic TGAs in Internet-wide IPv6 scanning. | 10.1109/TNSM.2024.3400864 |
Ruizhi Xiao, Weilong Li, Jintian Lu, Shuyuan Jin | ContexLog: Non-Parsing Log Anomaly Detection With All Information Preservation and Enhanced Contextual Representation | 2024 | Early Access | Anomaly detection Feature extraction Transformers Deep learning Software reliability Semantics Long short term memory Anomaly detection log analysis deep learning | Logs are widely used in software to trace the runtime states and critical events. Log-based anomaly detection is crucial for software maintenance and reliability assurance. Existing log-based anomaly detection methods are suffering from imperfections of log parsing, the neglect of the log individual context, and the discarding of non-character tokens. In this paper, we propose ContexLog, a non-parsing log-based anomaly detection method with all information preservation and enhanced log contextual representation, to detect diverse anomalies effectively. Log messages are first grouped as sequences with different windowing techniques. To capture all log features, ContexLog tokenizes each log sequence and preserves all information, including character and non-character tokens. It then represents the log sequential context and individual context simultaneously to construct input for a Transformer encoder-based classification model. Experimental evaluations on real-world datasets and synthetic datasets demonstrate ContexLog outperforms existing methods in achieving accurate anomaly detection results, handling unseen logs to avoid log parsing imperfections, and utilizing non-character tokens to detect diverse anomalies. | 10.1109/TNSM.2024.3400283 |
Tushar Bose, Nilesh Chatur, Sonil Baberwal, Aneek Adhya | Caching and Computing Resource Allocation in Cooperative Heterogeneous 5G Edge Networks Using Deep Reinforcement Learning | 2024 | Early Access | 5G mobile communication Resource management Servers Q-learning Quality of service Planning Heterogeneous networks Content caching Non-standalone architecture (NSA) Fifth Generation (5G) Heterogeneous network (HetNet) Deep Reinforcement Learning (DRL) Deep-Q network (DQN) | In this work, we explore a framework for a 5G non-standalone (NSA) heterogeneous network, to meet heterogeneous content requests for users moving in vehicles. We consider that an enhanced NodeB (eNB) acts as a macrocell and next-generation NodeBs (gNBs) act as the small cells. To reduce the downstream latency, entire (or part) of the popular contents are fetched from the core network and cached (stored) at the eNB and gNBs. The computing resources are required at the eNB and gNBs along with the caching resources, for content compression and decompression, leading to a reduced requirement for the caching resources. The eNB and gNBs cooperatively decide on the resources (caching and computing) to be allocated. In this network planning approach, first we compute the optimal coverage radius of the eNB and gNBs. Thereafter, we identify the optimal number of non-overlapping gNBs under the coverage area of the eNB. Finally, we propose a novel deep-Q network (DQN)-based algorithm to train the centralized controller agent so as to identify an optimal policy for caching and computing resource allocation. In case the content popularity and road traffic condition change, the agent can be trained again so as to identify a new optimal policy. We also explore the resource allocation policy using other optimization techniques, such as pattern search, genetic algorithm, and multi-start search. The proposed DQN-based algorithm is scalable and shows an average percentage gain of 66.52%, 76.31%, and 53.64% in terms of computation time to identify an optimal policy for caching and computing resource allocation, over pattern search, genetic algorithm, and multi-start search technique, respectively. | 10.1109/TNSM.2024.3400510 |
Yu Liu, Luhan Wang, Zhaoming Lu, Guochu Shou | A QoS Guaranteed Efficient Integration of UPF and LEO Satellite Networks | 2024 | Early Access | Satellites Quality of service Satellite broadcasting Low earth orbit satellites Servers Topology Network topology Low-Earth Orbit User Plane Function satellite networks dynamic topology 5G | Integrating the User Plane Function (UPF), which is responsible for forwarding user data in 5G, with the Low Earth Orbit (LEO) satellite networks can facilitate communication among users and take advantage of satellite edge computing. Satellite UPF (S-UPF) placement strategy is crucial to the integration performance. Static placement, in which the S-UPF drifts away with the satellite, is difficult to adapt to the dynamic satellite networks. The uneven distribution of terrestrial traffic and the resource limitations of satellites cause overload. The fast movement of S-UPF results in an augmented distance between S-UPF and users. This overload and extended distance degrade the Quality of Service (QoS). Dynamic S-UPF placement on satellites is a potential solution, but little attention is paid to it. To fill the gap, we propose a novel approach called Static Assignment Dynamic Placement (SADP), which comprises two key components: static user assignment and dynamic S-UPF placement. Static user assignment is designed to prevent overload, and dynamic S-UPF placement is applied to overcome the QoS degradation due to the extended distance between S-UPF and user. We evaluate the performance of SADP using real satellite constellations, and experimental results demonstrate its effectiveness in reducing latency and energy consumption. Compared to the static deployment, SADP achieves a significant 69.1% latency reduction and lower energy consumption. In contrast to deploying S-UPF on all satellites, SADP significantly reduces energy consumption by 85.2% while maintaining comparable latency performance. | 10.1109/TNSM.2024.3400255 |
Rana Muhammad Sohaib, Oluwakayode Onireti, Yusuf Sambo, Rafiq Swash, Muhammad Imran | Energy Efficient Resource Allocation Framework Based on Dynamic Meta-Transfer Learning for V2X Communications | 2024 | Early Access | Resource management Vehicle-to-everything Vehicle dynamics Ultra reliable low latency communication Energy efficiency Dynamic scheduling Energy consumption V2X DRL EE resource allocation meta-learning | Most existing studies consider the deep reinforcement learning (DRL) based Q-learning approach due to its ability to quickly converge to a near-optimal solution, resulting in effective allocation of resources and power. DRL-based Q-network discretizes the continuous power values which results in poor performance. It is challenging to allocate resources effectively in fast varying channel conditions in dynamic vehicular environments. In this work, we propose two approaches to overcome these challenges. First, we present a DRL-based energy-efficient resource allocation approach where we use a twin delayed deep deterministic policy gradient (TD3) scheme based on Thompson sampling to solve the power and resource allocation problem. Second, we present a dynamic meta-transfer learning framework to enhance the policy’s ability to adjust to new channel conditions. Simulation results shows that the proposed TD3 approach based on Thompson sampling enhances the system performance. Moreover, the proposed DRL-based dynamic meta-transfer learning framework takes 80% less samples to adapt to a new environment. | 10.1109/TNSM.2024.3400605 |
Felipe Arnhold, Sivasankari S. Anbazhagan, Lúcio R. Prade, José Marcos Nogueira, Aldebaro Klautau, Cristiano B. Both | Network Slicing Support by Fronthaul Interface in Disaggregated Radio Access Networks: A Survey | 2024 | Early Access | Network slicing Surveys 3GPP 6G mobile communication Next generation networking Ultra reliable low latency communication Resource management Network Slicing Disaggregated RAN Frounthaul Open RAN NG-RAN architecture | Beyond 5G (B5G) and 6G networks must offer network slicing as a service to support disruptive applications using mobile network infrastructures. Moreover, network slicing as a service should enable the orchestration and management of disaggregated radio access networks (RAN), i.e., it allows the automation and abstraction of network configurations composed of physical and virtualized components such as defined by the 3rd Generation Partnership Project (3GPP) and Open RAN (O-RAN) Alliance. Network slicing must reach the part of the network between the radio units and the distribution units, i.e., the fronthaul network. Fronthaul is essential and diverse in 5G and B5G networks and can be composed of point-to-point or multipoint connections. In this context, the literature presents several works investigating the problems of network slicing and disaggregated networks. However, no survey explores current works integrating network slicing in disaggregated networks, specifically in the fronthaul network. This article surveys network slicing on disaggregated networks and its potential use in point-to-point and multipoint fronthaul infrastructures. We cover the state-of-the-art by analyzing four fundamental research questions and discuss existing solutions, open challenges, and research opportunities in B5G and 6G networks. | 10.1109/TNSM.2024.3400019 |
Peng Liu, Youquan Xian, Chuanjian Yao, Peng Wang, Li-e Wang, Xianxian Li | A Trustworthy and Consistent Blockchain Oracle Scheme for Industrial Internet of Things | 2024 | Early Access | Blockchains Security Industrial Internet of Things Contracts Quality of service Task analysis Soft sensors IIoT Blockchain Oracle | A blockchain provides decentralization and trustlessness features for the Industrial Internet of Things (IIoT), which expands the application scenarios of IIoT. To address the problem that blockchains cannot actively obtain off-chain data, the blockchain oracle is proposed as a bridge between the blockchain and external data. However, the existing oracle schemes make it difficult to solve the problem of low quality of service caused by frequent data changes and heterogeneous devices in IIoT, and the current oracle node selection schemes are difficult to balance security and quality of service. To tackle these problems, this paper proposes a secure and reliable oracle scheme that can obtain high-quality off-chain data. Specifically, we first design an oracle node selection algorithm based on a Verifiable Random Function (VRF) and reputation mechanism to securely select high-quality nodes. Second, we propose a data filtering algorithm based on a sliding window to further improve the consistency of the collected data. We verify the security of the proposed scheme through security analysis. The experimental results show that the proposed scheme can effectively select high-quality nodes, reduce data differences, and improve the quality of service of the oracle. In the oracle network with malicious nodes accounting for 10%, the data accuracy rate is increased by about 4%, and the data variance is reduced by about 45% on average. | 10.1109/TNSM.2024.3399837 |
Liangyu Zhong, Lulu Wang, Lei Zhang, Josep Domingo-Ferrer, Lin Xu, Changti Wu, Rui Zhang | Dual-Server Based Lightweight Privacy-Preserving Federated Learning | 2024 | Early Access | Servers Task analysis Training Data models Cryptography Privacy Costs Privacy preservation lightweight cryptography secure aggregation federated learning | Federated learning (FL) allows multiple users to collaboratively train global machine learning models by keeping their data sets local. However, the existing privacy-preserving FL schemes suffer from several limitations, e.g., loss of accuracy, high communication/computation cost, failure to support dynamic users, and insecurity against collusion attacks. To solve these limitations, we propose a lightweight privacy-preserving FL scheme based on a dual-server architecture. Our scheme involves only lightweight cryptographic operations, i.e., hash and symmetric encryption operations, and it has low communication overhead. Thus, it is computationally lightweight and round-efficient. Further, it allows users to join/quit an FL task and it is accuracy-lossless. We formally prove that our scheme remains secure even in case of collusion attacks. In particular, if an attacker colludes with one of the servers and all the users who participate in an FL task except two, the privacy of user gradients stays unviolated. The reported experimental results demonstrate that our scheme incurs only a marginal increase in total communication overhead compared to the FL scheme without any privacy protection. In terms of computation overhead, the cost per user remains stable as the number of users grows, while the cost for the server is comparable to that of the FL scheme without any privacy protection. | 10.1109/TNSM.2024.3399534 |
Rui Zhuang, Jiangping Han, Kaiping Xue, Jian Li, Qibin Sun, Jun Lu | ProactMP: A Proactive Multipath Transport Protocol for Low-Latency Datacenters | 2024 | Early Access | Transport protocols Bandwidth Delays Downlink Receivers Topology Switches Datacenter network proactive transport multipath transmission transport protocol multipath TCP | With the development of datacenter networks (DCNs) towards high bandwidth and low latency, the demands of high-level datacenter applications are heading towards high performance and high reliability, which makes traffic congestion one of the most notable problems in DCNs and brings new challenges to transport protocols. Proactive transport protocols are gaining prevalence due to their ability to provide accurate feedback and precise end-to-end control, while multipath transmission is having a broader application space in the multi-path topology of large-scale DCNs. However, these advanced transport protocols aim to improve their performance by addressing some specific congestion problems, but fail to handle multiple congestion problems caused by incast, high workload and load imbalance. Their performance in terms of flow completion time (FCT), delay, robustness, and balance still has room for further improvement. In this paper, we propose ProactMP, a novel proactive multipath transport protocol for further improvement of datacenter communications. ProactMP utilizes the rich resources of parallel paths in modern DCN and spreads the load across available network paths to improve network efficiency. ProactMP deploys a credit-based bandwidth allocation strategy to achieve low delay and zero packet loss, and overcommits receiver downlinks to ensure high link utilization. We have implemented ProactMP in the Linux system. Our testbed experiments show that ProactMP outperforms the TCP variants, MPTCP variants and a leading proactive transport protocol in FCT, link utilization, fairness and latency. | 10.1109/TNSM.2024.3399028 |
T. R. Bezerra, J. A. B. Moura, A. S. Lima, J. Neuman de Souza | Decision-Making Support in IT Services Sourcing Management Through a System Dynamics Model | 2024 | Early Access | Outsourcing Business Contracts Indium tin oxide Costs Monitoring System dynamics IT service management Capability System dynamics Decision-making Sourcing management Contract monitoring Business-driven IT Management | Aligning corporate support functions, such as Information Technology (IT), with business objectives is a good strategic practice. To spread risks and reduce costs, a company may contract some services to outside providers – in what is known as outsourcing, while insourcing some other services, by leveraging its own capabilities. Deciding on sourcing options to add business value is not trivial. It requires knowing and leveraging the company’s own capabilities and effectively managing sourcing customer-provider complex dynamics. Said dynamics are often subject to varying degrees of feedback and delays that evolve from outsourcing contracts. Such complexity causes managers’ decision making to be usually ill-informed about implications to the business. The specialized literature offers little insight on how and with what to assess such implications. This paper contributes to the literature by presenting a System Dynamics (SD) simulation model for the interactions among the customer’s capabilities and those of the provider. The model breaks down complexity by offering complementary SD views, allowing for what-if analyses to inform decisions on sourcing options that favor intended business results. The model aligns sourcing strategies with the business through (dynamic) Balanced Scorecard concepts. The paper assesses how capabilities of Contract Monitoring and Service Delivery affect the earned business value of IT service outsourcing orders. Validation of the model was carried out in a multi-year case study at a taxation agency in Brazil. | 10.1109/TNSM.2024.3398621 |
Shunrong Jiang, Xiao Zhang, Jingwei Chen, Jinpeng Li, Haiqin Wu, Yiliang Liu, Yong Zhou | Privacy-Preserving and Fair Crowdsourcing Framework With Fine-Grained Reuse Based on Blockchain | 2024 | Early Access | Crowdsourcing Blockchains Security Task analysis Privacy Smart contracts Data privacy Crowdsourcing privacy preservation fine-grained reuse blockchain | Crowdsourcing has gained many developments and wide applications in our daily life. Traditional centralized crowdsourcing systems suffer from high management costs and low efficiency. The recent advance in the blockchain technology has enabled the construction of decentralized crowdsourcing systems, which can overcome the limitations of centralized systems and make crowdsourcing solution reuse possible. However, such systems also bring new security and privacy challenges. For instance, transactions on blockchain are publicly visible which can lead to privacy leakage of crowdsourcing users. Moreover, unfair exchange is a critical issue on these platforms. In this paper, we propose a privacy-preserving and fair crowdsourcing framework with fine-grained reuse based on blockchain to meet the security requirements for decentralized crowdsourcing. Specifically, we construct one-address-only (OAO) authentication to ensure the uniqueness of the participant’s address in the crowdsourcing process. Additionally, We design a submit-then-open method with commitments to resist the “free-riding" and “false-reporting" attacks. Thus, fair exchange between entities can be guaranteed. To ensure data confidentiality and fine-grained solution item reuse, we employ pairing-based cryptography to generate an encryption key and ensure flexible authorization reuse. We also adopt stealth authorization techniques to ensure privacy-preserving access authorization during the reuse phase. Finally, security analysis and implementation results have shown that the proposed framework can effectively achieve privacy-preserving and fair crowdsourcing as well as fine-grained crowdsourcing reuse. Specifically, the gas consumption in the reuse phase is reduced by approximately 49% to 81% compared to the normal operation, which significantly improves the efficiency of blockchain applications. | 10.1109/TNSM.2024.3398143 |
Muhammad Asad, Safa Otoum, Saima Shaukat | Clients Eligibility-Based Lightweight Protocol in Federated Learning: An IDS Use-Case | 2024 | Early Access | Training Data models Internet of Things Servers Convergence Protocols Optimization Federated Learning Client Eligibility Heterogeneous Network Resource-Constrained Intrusion Detection | Federated learning (FL) enables clients to train models locally, enhancing privacy by avoiding data centralization. Traditional FL assumes all clients have adequate resources, an often unrealistic expectation in heterogeneous networks with resource constraints like limited battery, memory, and bandwidth. These limitations can hinder performance, prolong convergence times, and lead to inaccurate models. To address these challenges, we introduce the Client Eligibility-based Lightweight Protocol (CELP), optimized for resource-constrained environments. CELP employs a sample-based pruning mechanism and a re-parameterized FedAvg algorithm, enhancing its management of resource variability. It also integrates an intrusion detection system to safeguard against malicious activities. Our results show that CELP significantly reduces communication overhead by up to 81.01% compared to FedAvg and up to 72.54% compared to FedProx and enhances system stability, achieving 93% accuracy on the MNIST dataset and 83% accuracy on CIFAR-10. These improvements demonstrate CELP’s ability to deliver robust performance and efficiency in diverse FL scenarios. | 10.1109/TNSM.2024.3398213 |
Fujun He, Mitsuki Ito, Takehiro Sato, Eiji Oki | Probabilistic Protection for Both Computing and Transmission Capacities of Virtual Networks Under Multiple Facility Node Failures | 2024 | Early Access | Computational modeling Resource management Protection Capacity planning Substrates Probabilistic logic Optimization Backup capacity allocation virtual network probabilistic protection robust optimization | This paper proposes a backup computing and transmission capacity allocation model for virtual networks that minimizes the required backup computing capacity under multiple facility node failures. The proposed model adopts the probabilistic protection, where the probability that the protection fails due to insufficient capacity is restricted not to be greater than a given survivability parameter, by using robust optimization. The conventional model allocates the backup computing capacity by considering the probabilistic protection but allocates the transmission capacity for all backup paths dedicatedly. The proposed model allocates the backup transmission capacity only for the failure patterns that are considered under the probabilistic protection guarantee; the probabilistic protection is considered for both computing and transmission capacity allocation. Reducing the required backup transmission capacity can also reduce the required backup computing capacity, since more feasible solutions for backup computing capacity allocation can exist. We introduce a heuristic algorithm to solve the backup computing and transmission capacity allocation problem. Numerical results show that the proposed model reduces the required backup transmission capacity and enhances the feasibility of allocating virtual networks compared with the conventional model. We also observe that reducing the required backup transmission capacity can lead to reducing the required backup computing capacity. | 10.1109/TNSM.2024.3397855 |
Wenqian Li, Long Qu, Juan Liu, Lingfu Xie | Reliability-Aware Resource Allocation for SFC: A Column Generation-Based Link Protection Approach | 2024 | Early Access | Reliability Protection Surgery Delays 5G mobile communication Virtual links Resource management Network function virtualization Service function chain Least square Network reliability Column generation | Network Function Virtualization (NFV) is considered one of the key technologies of 5G/B5G because of its advantages of flexibility, scalability, and manageability. In NFV networks, the flow of network service needs to go through a certain number of Virtual Network Functions (VNFs) which form Service Function Chain (SFC). Compared to link protection in traditional networks, the backup transmission links for different types of VNFs need to be considered to improve the SFCs’ reliability, since any failure of transmission link may interrupt the network service. Due to the uncertainty of VNF placement and routing, the flexible selection of link backup for each VNF to satisfy the reliability requirement of SFC becomes a remarkably challenging problem. In this paper, a Flexible virtual Link Protection (Fle_LP) mechanism is proposed to calculate backup resources accurately, enhancing the reliability of NFV-enabled network service. We mathematically formulate the problem as a Mixed Integer Nonlinear Program (MINLP). An Extended Least Square (ELS) method is introduced to deal with the nonlinear constraints, which transforms MINLP to Mixed Integer Linear Programming (MILP). Owing to the MILP’s remarkable complexity, a Column Generation-based Link Protection (CG_LP) algorithm is proposed, which generates an acceptable sub-optimal solution. Numerical results show that CG_LP reduces the computing time (8-node network: 92.3 %, 16-node network: 99.6 %) while achieving the same bandwidth consumption as MILP. | 10.1109/TNSM.2024.3397658 |
Sifan Li, Yue Cao, Hassan Jalil Hadi, Feng Hao, Faisal Bashir Hussain, Luan Chen | ECF-IDS: An Enhanced Cuckoo Filter-Based Intrusion Detection System for In-Vehicle Network | 2024 | Early Access | Security Long short term memory Intrusion detection Computational modeling Wiring Testing Performance evaluation CAN IDS BERT Cuckoo Filter | With the rapid advancement of vehicle connectivity and intelligent technologies, an increasing number of vehicles are now connected to the Internet. However, these connected vehicles are vulnerable to malicious attacks, posing serious security events. In particular, the in-vehicle controller area network (CAN) bus has witnessed a rise in incidents involving various network attacks, such as denial of service (DoS), fuzzy attacks, and gear attacks. In response, this paper proposes an enhanced cuckoo filter-based intrusion detection system (ECF-IDS) for in-vehicle network. The ECF-IDS builds on an enhanced version of the cuckoo filter. It first utilizes the cuckoo filter to establish two lists (a normal list and an intrusion list) based on the labeled dataset using Car Hacking Dataset (CHD) and can-train-and-test dataset. Then, the input CAN traffic is sequentially compared with these two lists, where the conflicting traffic is further identified using a BERT-based model. The ECF-IDS is experimentally validated using the CHD and can-train-and-test dataset, demonstrating higher detection efficiency, lower resource consumption, and detection success exceeding 99% compared to other algorithms presented in previous studies. Furthermore, we conducted real in-vehicle environment testing on the ECF-IDS model, and its detection performance proved to be excellent. | 10.1109/TNSM.2024.3394842 |
Suraj Kumar, Soumi Chattopadhyay, Chandranath Adak | TPMCF: Temporal QoS Prediction Using Multi-Source Collaborative Features | 2024 | Early Access | Quality of service Feature extraction Transformers Collaboration Data models Convolution Tensors Temporal QoS Prediction Graph Convolutional Matrix Factorization Predictive Transformer Encoder | The e-commerce industry has seen significant growth in recent years due to the introduction of new web service APIs. Quality-of-Service (QoS) parameters, which are fundamental for assessing service performance, have become crucial in evaluating services in the competitive market. Since QoS parameters can vary among users and change over time, accurate QoS predictions have become essential for users when selecting the most suitable services. Existing methods for predicting temporal QoS have hardly achieved the desired accuracy, beset by challenges like data sparsity, the presence of anomalies, and the inability to capture intricate temporal user-service interactions. Although some recent approaches, particularly those founded on recurrent neural network-based sequential architectures, endeavor to model temporal relationships in QoS data, they grapple with performance degradation due to the omission of other pivotal features, such as collaborative relationships and spatial characteristics of users and services. Furthermore, the uniform attention among features across all time-steps can thwart progress in predictive accuracy. This paper addresses these challenges and proffers a scalable strategy for temporal QoS prediction using multi-source collaborative features that not only furnishes heightened responsiveness but also engenders enhanced prediction accuracy. The method amalgamates collaborative features stemming from both users and services, capitalizing on the user-service relationship. Additionally, it integrates spatio-temporal auto-extracted features through the orchestration of graph convolution and a specialized variant of the transformer encoder equipped with multi-head self-attention. The proposed approach has been validated on the WSDREAM-2 benchmark datasets, and the results of these extensive experiments demonstrate that our framework surpasses major state-of-the-art methods in terms of predictive accuracy, all the while upholding robust scalability and reasonable responsiveness. | 10.1109/TNSM.2024.3395428 |