Workshops

Session AidTSP-TS1: AidTSP Technical Session I Session AidTSP-TS2: AidTSP Technical Session II Session AidTSP-TS3: AidTSP Technical Session III Session AidTSP-TS4: AidTSP Technical Session IV
Session AoI-Open: Opening Session Session AoI-Key: Keynote Session AoI-SCH: Scheduling and Optimization for AoI Session AoI-CBrk: Virtual Coffee Break Session AoI-BEY: Beyond AoI Metrics
Session CNERT-O: Opening Session Session CNERT-K: Keynote Session CNERT-P: Panel Session CNERT-S1: Session 1, Experimentation Enabling Capabilities Session CNERT-S2: Session 2, Services and network design Session CNERT-S3: Session 3, Wireless Session CNERT-D: Demo Session
Session DeepWireless-OS: Opening Session Session DeepWireless-KS1: Keynote Session 1 Session DeepWireless-TS1: Technical Session 1 - Deep Learning for Wireless Security Session DeepWireless-TS2: Technical Session 2 - Deep Learning for Wireless Applications Session DeepWireless-KS2: Keynote Session 2 Session DeepWireless-TS3: Technical Session 3 - Deep Learning for 5G Communications Session DeepWireless-CS: Closing Session
Session DroneCom-TS1: Technical Session I Session DroneCom-KS1: Keynote Session I Session DroneCom-TS2: Technical Session II Session DroneCom-TS3: Technical Session III Session DroneCom-KS2: Keynote Session II Session DroneCom-TS4: Technical Session IV
Session FOGML-S1: Opening Remarks Session FOGML-S2: Federated Learning Session FOGML-S3: Distributed Learning and Edge Computing
Session GI-00: Session#0 - Opening Session with Invited Keynote Session GI-01: Session#1 - Applying Machine Learning to Next Generation Internet Session GI-02: Session#2 - Performance Optimization of Next Generation Internet
Session ICCN-KS1: Security in Wireless Body Area Networks Session ICCN-B1: Virtual Coffee Break Session ICCN-S1: Cloud and Edge Computing Session ICCN-S2: Cloud and Edge Security Session ICCN-B2: Virtual Lunch Break Session ICCN-S3: Cloud and Edge Computing Session ICCN-S4: Cloud and Edge Computing
Session MobiSec-S1: AI & Security (I) Session MobiSec-K: Keynote: AI for Cybersecurity and Security of AI Session MobiSec-S2: AI & Security (II) Session MobiSec-S3: Mobile & Edge Security Session MobiSec-S4: Communication Security
Session NG-OPERA-OS: Opening Session Session NG-OPERA-KS: Keynote Session Session NG-OPERA-PS: Panel Session Session NG-OPERA-Break-1: Break Session NG-OPERA-TS1: Technical Session 1: Machine Learning and Resource Optimization for 6G RANs Session NG-OPERA-Lunch: Lunch Session NG-OPERA-TS2: Technical Session 2: System-level Solutions for Open RANs Session NG-OPERA-Break-2: Break Session NG-OPERA-TS3: Technical Session 3: Non-terrestrial Integration and Posters Session NG-OPERA-ACS: Awards and Closing
Session NetSciQCom-S1: Keynote Talk Session NetSciQCom-S2: Contributed Talks
Session PerAI-6G-Opening: Opening Session Session PerAI-6G-Keynote-1: Keynote Session 1 Session PerAI-6G-Keynote-2: Keynote Session 2 Session PerAI-6G-Session-1: Session 1: AI applications in 6G Session PerAI-6G-Session-2: Session 2: Distributed Learning in 6G Session PerAI-6G-Session-3: Session 3: Digital Twin in 6G Session PerAI-6G-Session-4: Session 4: Resource Management in 6G Session PerAI-6G-Closing: Closing Session
Session WISARN-O: Opening Session WISARN-K1: Keynote Session WISARN-CB: Virtual Coffee Break Session WISARN-S1: Technical Session
Session Wireless-Sec-I: Wireless Security I Session Wireless-Sec-II: Wireless Security II

Session ICCN-KS1

Security in Wireless Body Area Networks

Conference
9:00 AM — 10:00 AM EDT
Local
May 20 Sat, 6:00 AM — 7:00 AM PDT

Security in Wireless Body Area Networks

Honggang Wang (University of Massachusetts Dartmouth, USA)

0
Dr. Honggang Wang is a professor at UMass Dartmouth. He is an alumnus of NAE Frontiers of Engineering program. He has graduated 30 MS/Ph.D. students and produced high-quality publications in prestigious journals and conferences in his research areas, wining several prestigious best paper awards. His research interests include Internet of Things and their applications in health and transportation (e.g., autonomous vehicles) domains, Machine Learning and Big Data, Multimedia and Cyber Security, Smart and Connected Health, Wireless Networks and Multimedia Communications. He is an IEEE distinguished lecturer and an IEEE Fellow. He served as the Editor in Chief (EiC) of IEEE Internet of Things Journal (2020-2022). He also served as the Chair (2018-2020) of IEEE Multimedia Communications Technical Committee and was the IEEE eHealth Technical Committee Chair (2020-2021).
Speaker
Speaker biography is not available.
Session Chair

Ruidong Li (Kanazawa University)

Session ICCN-B1

Virtual Coffee Break

Conference
10:00 AM — 10:30 AM EDT
Local
May 20 Sat, 7:00 AM — 7:30 AM PDT

Session ICCN-S1

Cloud and Edge Computing

Conference
10:30 AM — 11:30 AM EDT
Local
May 20 Sat, 7:30 AM — 8:30 AM PDT

Live Migration of containerized microservices between remote Kubernetes Clusters

Kiranpreet Kaur (Orange & CNAM, France); Fabrice M. Guillemin (Orange Labs, France); Fran_oise Sailhan (IMT-Atlantique, France)

0
The recent adoption of cloud native technologies by telecommunication industry is accompanied by the incoming development of Network Functions that are containerized and packaged as light-weighted microservices. In order to efficiently orchestrate the Containerized Network Functions (CNFs), thorough migration strategies should be supported to place and migrate the CNFs. In this regards, we present the deployment and migration of a network function belonging to the 5G core network.
Speaker Kiranpreet Kaur (Orange and CNAM Paris, France)

Kiranpreet is pursuing an Industrial PhD on traffic management of network functions decomposed into microservices for distributed cloud infrastructure from CNAM Paris in collaboration with Orange Innovation, France. Her key activities are focused on Orchestration of 5G/6G CNFs, ILP Optimization models and algorithms for microservices placement and migration strategies.

Offloading Tasks to Unknown Edge Servers: A Contextual Multi-Armed Bandit Approach

Shu Zhang and Mingjun Xiao (University of Science and Technology of China, China); Guoju Gao (Soochow University, China); Yin Xu and He Sun (University of Science and Technology of China, China)

0
Mobile Edge Computing (MEC), envisioned as an innovative paradigm, pushes resources from the cloud to the network edge and prompts users to offload computation-intensive and data-intensive tasks to edge servers for meeting the stringent service requirements. Prior approaches often study efficiently offloading tasks with given system information, though rigorously time-sensitive tasks offloading problems receive less attention under system uncertainty. As motivated, we propose a multi-user collaborative offloading model where users jointly decide time-sensitive task placement while considering the unknown system information and contexts. We formulate the offloading problem as a Multi-user Contextual Combinatorial Multi-armed Bandit (MCC-MAB) problem and propose a learning algorithm Context-Aware Task Offloading Decision (CATOD) to explore the system uncertainty. Since the time-sensitive task offloading problem with learned system information is still NP-hard, we present an approximation algorithm Offline Generalized Task Assignment (OGTA) to obtain an efficient offloading solution. Additionally, meticulous theoretical analysis and extensive evaluations demonstrate the significant performance on a real-world dataset.
Speaker Shu Zhang (University of Science and Technology of China)

My name is Shu Zhang. I am from University of Science and Technology of China.

Incentive-driven and SAC-based Resource Allocation and Offloading Strategy in Vehicular Edge Computing Networks

Jianmeng Guo, Huan Zhou and Liang Zhao (China Three Gorges University, China); Wei Chang (Saint Joseph's University, USA); Tingyao Jiang (China Three Gorges University, China)

0
Vehicular edge computing (VEC) networks can provide low-latency services for vehicles. However, it is a great challenge for edge nodes to satisfy the computing tasks of all vehicles during vehicle peak hours. This paper studies the joint optimization problem of offloading strategy and resource allocation in a VEC network composed of road side units (RSUs) with computing resources, vehicle users and vehicle workers. In order to alleviate the computing pressure of the RSU, we use contract theory to encourage vehicle workers to do computing tasks. At the same time, we propose a novel algorithm based on Soft Actor-Critic (SAC) to solve the system cost minimization problem considering vehicle users' satisfaction, RSUs' cost and vehicle workers' reward. Finally, we conduct extensive simulations in different scenarios, the simulation results show that our proposed algorithm has higher performance in reducing system cost compared with other benchmark methods.
Speaker Jianmeng Guo(China Three Gorges University)


Controller-Assisted Adaptive Video Streaming Experimented in Cloud-Native ICN Platform

Yusaku Hayamizu and Atsushi Ooka (National Institute of Information and Communications Technology, Japan); Kazuhisa Matsuzono (National Institute of Information and Communication Technology (NICT), Japan); Hitoshi Asaeda (National Institute of Information and Communications Technology (NICT), Japan)

0
In this paper, we propose a controller-assisted adaptive video streaming framework in Information-Centric Networking (ICN) for application-oriented service provisioning. In this framework, our cache pruning mechanism (CPM) provides stable QoS performance and achieve QoE performance for streaming users by eliminating ``harmful'' cached chunks. We developed a CCNx-1.0 compliant controller and CPM and experimented the framework in a cloud-native ICN platform to prove stable video streaming quality. Through the real-world performance evaluation, we show that our proposed framework can substantially improve throughput and achieve high QoS performance at the transport layer level. The QoE performance in the application layer was also significantly improved by QoS improvement in an indirect fashion.
Speaker Yusaku Hayamizu (NICT)

Yusaku Hayamizu received his B.E., M.E., and Ph.D. degrees in engineering from Kansai University in 2014, 2016, and 2019, respectively. He is currently a researcher of Network Architecture Laboratory at National Institute of Information and Communications Technology (NICT). His research interests include computer networks, information centric networks, traffic control, in-network computing, and network softwarelization. Dr. Hayamizu is the recipient of Best Paper Awards from the 2017 IEEE CQR Workshop and the 2018 IEEE LANMAN Symposium. He is a member of the ACM, the IEEE, and the IEICE.

Session Chair

Bo Fan (Beijing University of Technology)

Session ICCN-S2

Cloud and Edge Security

Conference
11:30 AM — 12:30 PM EDT
Local
May 20 Sat, 8:30 AM — 9:30 AM PDT

Securing Federated Learning through Blockchain and Explainable AI for Robust Intrusion Detection in IoT Networks

Zakaria Abou El Houda (University of Montreal, Canada); Hajar Moudoud (Universite de Sherbrooke, Canada); Bouziane Brik (University of Bourgogne, France); Lyes Khoukhi (ENSICAEN, Normandie University, France)

0
Federated learning (FL) is a distributed machine learning technique that allows multiple devices or nodes in a network to collaboratively train a machine learning model while keeping their data local to the device. This is particularly useful in the context of the Internet of Things (IoT) systems, where devices may have limited computational resources and may not be able to transmit their data to a central server due to privacy or bandwidth constraints. FL offers privacy protection but remains vulnerable to security and privacy attacks ($e.g.,$ Data Poisoning Attacks). To address this issue, in addition to the usual components of an FL system, an explainable FL framework for intrusion detection systems should also include mechanisms for explaining the model's predictions. This can be achieved through the use of techniques such as feature importance, which allows the model to identify the most important input features for a particular prediction. In this context, we propose a novel framework, called FedIoT, that leverages Explainable Artificial Intelligence (XAI) techniques and Blockchain to secure FL-based IDS in the IoT networks. FedIoT uses advanced XAI techniques to identify local model manipulations and mitigate FL-based attacks. Moreover, we propose a blockchain-based approach that uses an efficient reputation scheme that ensures the trustworthiness and reliability of the FL training process. We conducted experiments to validate FedIoT, an FL-based Intrusion Detection system in IoT networks. Using the UNSW-NB15 dataset, we confirmed that FedIoT can effectively detect malicious activity and facilitate efficient FL collaboration among multiple users.
Speaker Zakaria Abou El Houda (University of Montreal, Canada)

Zakaria Abou El Houda (Member, IEEE) received the M.Sc. degree in computer networks from Paul Sabatier University, Toulouse, France, in 2017, the Ph.D. degree in computer science from the University of Montreal, Montreal, QC, Canada, and the Ph.D. degree in computer engineering from the University of Technology of Troyes, Troyes, France, both in 2021. His current research interests include applied machine/deep learning for intrusion detection systems, security of distributed machine learning, and blockchain for network security.

Hyperledger based Verifiable and Secure Cloud Data Deletion

Debasish Bera (IIIT Kalyani, Nadia & IIIT Kalyani, India); Srijita Basu (Indian Institute of Information Technology Kalyani, India); Sandip Karmakar (NIT Durgapur, India); Shubhasri Roy (IIIT Kalyani Nadia West Bengal, India)

0
In today's era of diversified computational advancements, cloud computing and its application has become an inevitable part of the industry and academia. Chunks of data are stored and removed everyday from the cloud instances. Any remaining trace of this deleted data may lead to illicit data leakage. Cloud Service Consumers (CSC)/users mostly depend on third party auditors (TPA)/verification systems for guaranteeing that their data has been completely deleted from the cloud premises once their mutual service tenure ends. In this paper, the concept of blockchain technology is used to provide an authentication and verification platform for executing a secured and complete removal of user data from CSP premises and providing a proof for the same. The Elliptic Curve Digital Signature Algorithm (ECDSA) signature scheme has been integrated in the existing hyperledger fabric framework for achieving the required results. A performance analysis based on hyperledger caliper is presented. It manifests a negligible performance overhead of 13% due to the additional ECDSA layer. Additionally, the comparative study shows the benefits of TPA independence, deletion request authentication and user identity management which makes the proposed scheme more secure and efficient as compared to contemporary solutions.
Speaker Miss Shubhasri Roy, PhD student at IIIT Kalyani, W.B., India

Miss Shubhasri Roy, PhD student at IIIT Kalyani, W.B., India and Assistant Professor at the Institute of Engineering and Management, Kolkata, India. She has a work experience of 7 years. Currently, her area of interest includes Blockchain technology, cryptography and Cloud Computing. 

Accurate Anomaly Interval Recognition and Fault Classification by Pattern Mining and Clustering

Ningyuan Sun, Hongyun Zheng and Yishuai Chen (Beijing Jiaotong University, China); Yajun Liu and Jinuo Fang (Beijing Baolande Software Corporation, China)

0
To maintain the stability and reliability of a largescale information system, monitoring its Key Performance Indicators (KPIs) time series and detecting their anomalies are very important. In practice, however, multivariate time series anomaly detection is challenging due to the large dimension of time series, diverse anomalous patterns, and their complex relationships. In addition, KPIs may exhibit different patterns when different types of faults occur, which aggravates the difficulty of anomaly detection. In this paper, we propose an accurate KPI anomaly detection and fault classification method, which can adapt to multiple metrics and diverse fault types. It can automatically extract common anomalous patterns from different KPI responses when faults occur and accurately determine the fault intervals. In this method, we do not need to deploy a lot of different anomaly detectors, and can conduct both anomaly detection and fault classification simultaneously. Experimental results on the real-world Exathlon benchmark dataset show that our algorithm can accurately recognize the anomaly intervals and classify the faults, with F1-score 0.94.
Speaker Ningyuan Sun(Beijing Jiaotong University)

Ningyuan Sun received the B.E. degree from Beijing Jiaotong University, Beijing, China, in 2020, where she is currently pursuing the M.E. degree with the School of Electronics and Information Engineering. Her research interests include SDN upgrade optimization and anomaly detection of AIOps.

Blockchain-Based Privacy-Preserving Authentication Scheme Using PUF for Vehicular Ad Hoc Networks

Shuangrong Peng (Southwest Jiaotong University, China)

0
With the rapid development of wireless networks, vehicular ad hoc networks (VANET) have been the key indispensable module of the future intelligent transportation system. Security and privacy are two essential attributes to protect the safe driving of vehicles. Over the last two decades, a large number of conditional privacy-preserving authentication (CPPA) schemes for the VANET environment have been proposed. To the best of our knowledge, cross-domain authentication schemes need to be further improved to better communication. Blockchain technology with several inherent advantages like decentralization and unforgeability offers a feasible solution to this issue. However, the problems of un-linkability and physical attack in current blockchain-based CPPA schemes are still urgent challenges. In order to accomplish this, we combine physically unclonable function (PUF) and blockchain technology to construct a CPPA scheme for the VANET environment. The proposed scheme is able to provide message authentication, identity privacy preservation, un-linkability, traceability, etc.
Speaker
Speaker biography is not available.
Session Chair

Zhiqing Tang (Beijing Normal University)

Session ICCN-B2

Virtual Lunch Break

Conference
12:30 PM — 2:00 PM EDT
Local
May 20 Sat, 9:30 AM — 11:00 AM PDT

Session ICCN-S3

Cloud and Edge Computing

Conference
2:00 PM — 3:30 PM EDT
Local
May 20 Sat, 11:00 AM — 12:30 PM PDT

Bs-SpMM: Accelerate sparse matrix-matrix multiplication by balanced split strategy on the GPU

Guo Mingfeng, Yaobin Wang, Gu Yajun, Chen Yufang, Liu Huan, Chen Huarong and Han Dongxuan (Southwest University of Science and Technology, China); Xu Hengyang and Deng Chunhua (Tencent, China); Tang Pingping and Huang Qi (Southwest University of Science and Technology, China)

0
Sparse Matrix-Matrix Multiplication(SpMM) is a commonly utilized operation in various domains, particularly in the increasingly popular Graph Neural Networks(GNN) framework. The current GPU-based SpMM kernel mainly adopts the row-splitting strategy, in which a warp in the GPU processes one row of a sparse matrix. However, due to the uneven distribution of non-zero elements in sparse matrices, this row-splitting method often suffers from two problems. 1) Load imbalance among warps 2) When dealing with long rows, a warp's parallel efficiency is low. We propose a balanced split strategy SpMM algorithm named Bs-SpMM. When storing sparse matrices, we use "part" instead of "row" as the granularity just as int8 is more efficient than int16. Its advantage is to ensure that the basic work task size is within a certain range and that there are enough threads in the warp to parallelize all non-zero tasks. When computing tasks on the GPU, the parallel parts are processed by balance, thus avoiding the problem of large differences in the number of nonzero elements from row to row. This approach naturally alleviates the load imbalance problem among warps. When doing memory transactions on the GPU, the temporary space required by the part is small enough that it can always be stored in on-chip shared memory, which will ensure better data locality. Non-zero elements in part are from the same row, which continues to keep coalesced memory access to dense matrix. On Nvidia Rtx 3070 GPU, our experimental results based on SNAP Matrix Collection show that Bs-SpMM achieves an average speedup of 1.40x and 1.49x compared to Nvidia cuSPARSE and state-of-the-art GESpMM, respectively.
Speaker Mingfeng Guo

A master student at Southwest University of Science and Technology

An Appointed Access Control Scheme for Distributed-Cloud Environment

Z Zhou (XiHua University, China); Ling Xiong and Peng Chen (Xihua University, China); Niu XianHua and Feng Xu (XiHua, China)

0
With the development of cloud computing technology, single clouding services have not been able to cope adequately with the online services boom, cloud federation is satisfied with the demand.The access control technology among the cloud federation environment has become an indispensable threshold to ensure the security of cloud services. However, the current access control schemes are not appointed, i.e., once a user gets the credential, he/she has the capacity to access all services in the cloud federation environment.This is conflict with the practical application usually restricted by the role of the user.To overcome this weakness, this work designs an appointed access control scheme using signcryption for cloud federation environment, which provides mutual authentication, hierarchical access control, appointed access, etc. Finally, we compare with the existing scheme, and the results show that our scheme has the best computational efficiency and communication efficiency. Therefore, our scheme is more suitable for complex and diverse cloud federation environments.
Speaker Zheng Zhou(Xihua University)

Zheng Zhou is currently pursuing a master's degree in Computer and Software Engineering at Xihua University, with a research focus on security and privacy in Cloud Computing

Ensemble Learning for Predicting Task Connectivity Over Time in Cloud Data Centers

Mustafa Daraghmeh and Anjali Agarwal (Concordia University, Canada); Yaser Jararweh (Jordan University of Science and Technology, USA)

0
The rapid growth and interdependencies of cloud-hosted services and applications have made it imperative to optimize data center resource management while maintaining low operating costs. Inefficient resource use, rising energy consumption, and operating costs impact cloud provider's ability to provide high-quality services on an elastic basis. However, changing the selection and decision-making processes based on how the tasks are set up can improve scheduling and resource management in cloud data centers. In this paper, we develop a multivariate time series prediction model for task connectivity based on windowing characterization and ensemble learning methods. The high cardinality features are handled using a counter encoder, and the task trace data is transformed using a sliding window, from which features are extracted and used in conjunction with the task profile data to train and tune the candidate estimators. The best model outcomes are then used to construct an ensembled estimator. As part of the evaluation, a baseline comparison is performed in order to determine how well ensemble learning predicts task connectivity over time. The model outcomes are assisted using standard classification metrics such as accuracy, precision, and recall, including the F1 score, Kappa, and Matthews correlation coefficient. The results show that the proposed model outperformed the traditional models in most performance metrics, indicating the successful implementation of an ensemble learning approach for task connectivity predictions in large-scale cloud data centers.
Speaker Mustafa Daraghmeh (Concordia University)

He received a bachelor's degree in Computer Science from Al-Balqa' Applied University, Al-Huson University College, Irbid, Jordan, in 2009. He received a master's degree in Computer Science from Jordan University of Science and Technology, Irbid, Jordan, in 2014. He is pursuing a Ph.D. in Electrical and Computer Engineering at Concordia University, Montreal, QC, Canada. His research interests include cloud computing, resource management, multi-agent systems, time series analysis, and various aspects of machine learning.

Empirical Mode Decomposition and Stationary Wavelet Transformation in Internet Traffic Prediction

Sajal Saha (University of Western Onatrio, Canada); Moinul Islam Sayed (University of Western Ontario, Canada); Anwar Haque (Western Ontario, Canada)

0
Internet traffic forecasting is critical for optimized usage of network resources. The existing traffic forecasting methodology applied Empirical Mode Decomposition (EMD) for traffic decomposition into multiple hierarchical components and predicted each component separately using different algorithms. But that approach seems inefficient as the total number of components depends on the input signal, and it is challenging to propose and optimize the prediction model separately for each component. In our proposed method, a multi-output single prediction model forecasts each EMD component of target traffic volume individually and aggregates the individual prediction for the final forecast. In addition, we compared the performance of EMD based approach with the Stationary Wavelet Transformation (SWT) integrated deep learning model. We used SWT to decompose our real-world internet traffic into high and low-frequency components while they respectively indicate the white noise and long-term trend in the traffic data. Only the low-frequency component has been considered to extract the trend feature and to train our deep-learning models. Our experimental results showed that EMD integrated model outperformed traditional deep learning models by approximately 1% to 3%. We further improved the traffic prediction accuracy by smoothing original traffic based on the SWT denoising process, and it outperforms the baseline deep learning model by 3%-5% more accuracy.
Speaker Sajal Saha

Sajal Saha is a Computer Science professional with extensive experience in academia and industry. Currently a Ph.D. candidate at Western University, Sajal holds an MSc in Computer Science from Brock University, a Master's in Information Technology from Jahangirnagar University, and a BSc in Computer Science and Engineering (Gold Medalist) from Patuakhali Science & Technology University. Sajal's work spans roles at Western University, Juniper Network, Brock University, Patuakhali Science & Technology University, and Samsung Electronics, specializing in formal methods, data mining, time-series prediction, network security, machine learning, and deep learning. As a researcher, Sajal has numerous publications in prestigious journals and conferences such as IEEE TNSM, IEEE Access, IEEE INFOCOM, IEEE NOMS, IEEE ICC, IEEE CCNC, IEEE ICNC, IEEE IWCMC, IEEE ISNCC, and MDPI Sensors. Skilled in Python, Java, C, SQL, and machine learning frameworks, Sajal's excellence is demonstrated through various awards, speaking engagements, student supervision, and research collaborations.

Session Chair

Peng Chen (Xihua University)

Session ICCN-S4

Cloud and Edge Computing

Conference
3:30 PM — 4:30 PM EDT
Local
May 20 Sat, 12:30 PM — 1:30 PM PDT

An Edge-Assisted Fair Transmission Scheme for Synchronized Interactive Virtual Reality

Huitong Liu, Peng Yang, Xi Wang and Wei Liu (Huazhong University of Science and Technology, China)

0
It is challenging to achieve satisfying experience in multi-user interactive virtual reality, as this application requires high frame rate, low response delay, and synchronized refresh across different users. Mobile edge computing can help to meet the requirement of low end-to-end delay, yet most of the existing works focus on minimizing end-to-end delay and ignore synchronization among users. We found that this is because synchronization and latency minimization are oftentimes conflicting objectives, which are difficult to achieve simultaneously. In this paper, we focus on quality of experience (QoE)-fair synchronous transmission for virtual reality conferencing in multi-user interactive scenario. A QoE-fair optimization problem is formulated, aiming at maximizing QoE fairness while meeting the aforementioned requirements. Then, we propose an edge-assisted fair transmission mechanism based on end-edge-cloud collaboration. This mechanism consists of an edge compression control algorithm and a synchronous decision algorithm in the cloud. Simulation results show that the proposed scheme achieves better performance for three requirements and QoE fairness compared with other benchmarks.
Speaker Huitong Liu (Huazhong University of Science and Technology)


i-Profiler: Towards Multi-Objective Autonomous VNF Profiling with Reinforcement Learning

Pratchaya Jaisudthi, Shadi Moazzeni, Xenofon Vasilakos, Reza Nejabati and Dimitra Simeonidou (University of Bristol, United Kingdom (Great Britain))

0
The intelligent orchestration of Virtual Network Functions (VNFs) requires understanding and profiling the impact of VNF resource consumption on its performance. Recent efforts focus on ML model-based profiling methods to discover and manage optimal trade-offs between cost-efficient resource combinations for VNFs and the latter's performance. To this end, the current paper poses a novel effort towards an intelligent VNF profiling by targeting multiple resource and performance optimisation objectives, thus suiting real-world applications. Our approach is based on adapted Reinforcement Learning (RL) considering three types of resources: CPU, memory, and network link capacity, as well as the output load and performance of VNFs. Our current results show how we can improve the VNF performance while at the same time optimising the consumption of multiple resources in contrast to single-objective solutions in the literature. We investigate a VNF type via exhaustive resource and performance profiling against our intelligent adapted RL approach. In addition, as a benchmark model to RL, we compare our model with a Supervised Learning (SL) model. Our results denote successful profiling decisions with greater resource prediction accuracy, paving the way for future research.
Speaker Shadi Moazzeni (University of Bristol)

Dr. Shadi Moazzeni received the M.Sc. degree in computer architecture engineering from the Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran, in 2010, and the Ph.D. degree in computer architecture engineering from the University of Isfahan, Iran, in 2018. She was also a Ph.D. Visiting Researcher with the University of Bologna, Italy, from July 2016 to February 2017. She is a Research Fellow with the University of Bristol, Bristol, U.K., where she is a member of the Smart Internet Lab and the High Performance Networks Research Group and the Cluster Lead Researcher of the EU Horizon 2020 5G-VICTORI project. Her current research focuses on the performance and reliability of distributed software-defined networks, network function virtualization, multiedge orchestration, monitoring and measuring performance, and 6G network profiling and intelligent next generation orchestration.

Boids Swarm-based UAV Networking and Adaptive Routing Schemes for Emergency Communication

Xutong Yang, Li Wang, Lianming Xu, Yuming Zhang and Aiguo Fei (Beijing University of Posts and Telecommunications, China)

0
Communications in disaster scenarios face critical challenges because of damage to ground communication facilities. A promising solution for emergency response is establishing self-organizing networks with flexible unmanned aerial vehicles (UAVs) swarms to provide communication guarantees for rescue mission execution. However, the server environment of the disaster area and the highly dynamic characteristic of UAV networks place strict requirements on swarm mobility control and data transmission. To this end, this work proposes a Boids mobility model-based adaptive routing scheme to achieve efficient UAV swarm networking. Specifically, we develop a biological-inspired Boids-based Social Force Model (BSFM) to implement swarm mobility control with location information and link states to improve the communication performance of UAV networks. Then, we design an adaptive routing scheme to adjust the Hello message sending interval based on the relative velocity and distance between the UAVs for neighbor discovery and topology maintenance. We conduct experiments with Network Simulator 3 (NS-3) for performance evaluation, and simulation results show that our method outperforms conventional approaches regarding the average delay, packet loss, and network throughput.
Speaker Xutong Yang (Beijing University of Posts and Telecommunications, China)


Task Offloading using Multi-armed bandit Optimization in Autonomous Mobile Robots

Anis Ur Rahman (National University of Sciences and Technology (NUST), Pakistan); Assad Waqar (NUST, Pakistan); Hasan Ali Khattak (National University of Sciences and Technology, Pakistan); Moayad Aloqaily (Mohamed Bin Zayed University of Artificial Intelligence, Canada)

0
Evolution in ubiquitous and wireless services has enabled the massive adoption of autonomous cyber-physical systems for improving workflows in dynamic environments. Among other applications, it has been witnessed that these modern technologies with the help of machine learning and highspeed communications can enable optimum and safe utilization of resources to complete various repetitive yet hazardous tasks. The industry 5.0 vision requires a multitude of devices to work with such orchestration that compute-intensive tasks may be offloaded to nearby nodes to enable collaboration for such time-critical yet compute-intensive tasks. In this work, we present a multiarmed bandit-based approach for task offloading in unmanned autonomous robots. Through experimental validation, a proof of concept is given. It has been demonstrated that using the proposed technique we have achieved a higher task delivery rate with reduced average delay.
Speaker Anis Ur Rahman


Session Chair

Huitong Liu (Huazhong University of Science and Technology)


Gold Sponsor


Gold Sponsor


Bronze Sponsor


Student Travel Grants


Student Travel Grants


Local Organizer

Made with in Toronto · Privacy Policy · INFOCOM 2020 · INFOCOM 2021 · INFOCOM 2022 · © 2023 Duetone Corp.