TY - CHAP AU - Vajda, Dániel László AU - Do, Van Tien AU - Farkas, Károly TI - Data pre-processing to improve anomaly detection in the telemetry of a server farm T2 - 2nd Workshop on Intelligent Infocommunication Networks, Systems and Services PB - Budapest University of Technology and Economics CY - Budapest SN - 9789634219446 PY - 2024 SP - 67 EP - 72 PG - 6 DO - 10.3311/WINS2024-012 UR - https://m2.mtmt.hu/api/publication/34777302 ID - 34777302 AB - Server farm telemetry plays a crucial role in overseeingand ensuring the health, performance, and efficiency ofinterconnected servers, which deliver computing resources forapplications and services. An essential step in the telemetryprocess is the analysis of data collected from servers. Anomaly detectionis a significant task in this step: by automatically detectingsigns of abnormal behaviour, operators can prevent issues fromescalating into major operational setbacks. This paper presents anew pre-processing procedure to improve our previous anomalydetection algorithms and state-of-the-art detectors. Motivatedby the finding that periodic datasets often pose challenges toanomaly detection, our method transforms a dataset by removingmodes containing regular, periodic behaviour while preservingsigns of anomalies. Our proposed pre-processing procedureimproved the performance of all anomaly detectors we tested,while our latest detector achieved substantially better resultson periodic data than originally. We also present an extensivenumerical analysis of our pre-processing parameters and stateof-the-art anomaly detection algorithms regarding performancevia the F-score metric. LA - English DB - MTMT ER - TY - CHAP AU - Jwaifel, Arwa Mahmoud AU - Do, Van Tien ED - Kozierkiewicz, Adrianna ED - Vossen, Gottfried ED - Treur, Jan ED - Núñez, Manuel ED - Gulyás, László ED - Botzheim, János ED - Nguyen, Ngoc Thanh TI - Deep Reinforcement Learning for Jointly Resource Allocation and Trajectory Planning in UAV-Assisted Networks T2 - Computational Collective Intelligence VL - 14162 LNAI PB - Springer Switzerland CY - Cham SN - 9783031414565 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 14162. PY - 2023 SP - 71 EP - 83 PG - 13 DO - 10.1007/978-3-031-41456-5_6 UR - https://m2.mtmt.hu/api/publication/34177678 ID - 34177678 N1 - Export Date: 6 October 2023 Correspondence Address: Jwaifel, A.M.; Department of Networked Systems and Services, Hungary; email: jwaifel@hit.bme.hu LA - English DB - MTMT ER - TY - JOUR AU - Nguyen, Khanh-Van AU - Nguyen, Chi-Hieu AU - Do, Van Tien AU - Rotter, Csaba TI - Efficient Multi-UAV Assisted Data Gathering Schemes for Maximizing the Operation Time of Wireless Sensor Networks in Precision Farming JF - IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS J2 - IEEE T IND INFORM VL - 19 PY - 2023 IS - 12 SP - 11664 EP - 11674 PG - 11 SN - 1551-3203 DO - 10.1109/TII.2023.3248616 UR - https://m2.mtmt.hu/api/publication/33733394 ID - 33733394 N1 - Hanoi University of Science and Technology Ha Noi, Viet Nam Department of Networked Systems and Services, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary Nokia Bell Labs Hungary, Budapest, Hungary LA - English DB - MTMT ER - TY - JOUR AU - Jwaifel, Arwa Mahmoud AU - Ghareeb, Ibrahim AU - Do, Van Tien TI - Impact of Co-channel Interference on the Performance of Cooperative Diversity Systems over α–μ Fading Channels JF - INTERNATIONAL JOURNAL OF WIRELESS INFORMATION NETWORKS J2 - INT J WIREL INF NETW VL - 29 PY - 2022 IS - 3 SP - 232 EP - 239 PG - 8 SN - 1068-9605 DO - 10.1007/s10776-022-00563-w UR - https://m2.mtmt.hu/api/publication/32916674 ID - 32916674 N1 - Funding Agency and Grant Number: Budapest University of Technology and Economics Funding text: Open access funding provided by Budapest University of Technology and Economics. AB - This paper investigates the impact of the co-channel interference on the performance of cooperative diversity networks. Selection combination technique is applied to the paths from multiple relay branches with no link directly connects the source and destination nodes. In addition, we derive the statistical characteristics of the upper bound of the SINR under the alpha-mu fading channel model, which then were used to derived the outage (P-out) and error (P-b(e)) probabilities for the cooperative network. LA - English DB - MTMT ER - TY - JOUR AU - Nguyen, Tuan Hai AU - Do, Van Tien AU - Rotter, Csaba TI - Scaling UPF Instances in 5G/6G Core with Deep Reinforcement Learning JF - IEEE ACCESS J2 - IEEE ACCESS VL - 9 PY - 2021 SP - 165892 EP - 165906 PG - 15 SN - 2169-3536 DO - 10.1109/ACCESS.2021.3135315 UR - https://m2.mtmt.hu/api/publication/32532803 ID - 32532803 N1 - Export Date: 1 March 2022 Correspondence Address: Van Do, T.; Department of Networked Systems and Services, Hungary; email: do@hit.bme.hu AB - In the 5G core and the upcoming 6G core, the User Plane Function (UPF) is responsible for the transportation of data from and to subscribers in Protocol Data Unit (PDU) sessions. The UPF is generally implemented in software and packed into either a virtual machine or container that can be launched as a UPF instance with a specific resource requirement in a cluster. To save resource consumption needed for UPF instances, the number of initiated UPF instances should depend on the number of PDU sessions required by customers, which is often controlled by a scaling algorithm. In this paper, we investigate the application of Deep Reinforcement Learning (DRL) for scaling UPF instances that are packed in the containers of the Kubernetes container-orchestration framework. We propose an approach with the formulation of a threshold-based reward function and adapt the proximal policy optimization (PPO) algorithm. Also, we apply a support vector machine (SVM) classifier to cope with a problem when the agent suggests an unwanted action due to the stochastic policy. Extensive numerical results show that our approach outperforms Kubernetes’s built-in Horizontal Pod Autoscaler (HPA). DRL could save 2.7–3.8% of the average number of Pods, while SVM could achieve 0.7–4.5% saving compared to HPA. LA - English DB - MTMT ER - TY - JOUR AU - Nguyen, Khanh-Van AU - Nguyen, Chi-Hieu AU - Phi, Le Nguyen AU - Do, Van Tien AU - Chlamtac, Imrich TI - Correction to: Energy-efficient routing in the proximity of a complicated hole in wireless sensor networks. (Wireless Networks, (2021), 27, 4, (3073-3089), 10.1007/s11276-021-02569-3) TS - (Wireless Networks, (2021), 27, 4, (3073-3089), 10.1007/s11276-021-02569-3) JF - WIRELESS NETWORKS J2 - WIREL NETW VL - 27 PY - 2021 IS - 4 SP - 3091 EP - 3091 PG - 1 SN - 1022-0038 DO - 10.1007/s11276-021-02607-0 UR - https://m2.mtmt.hu/api/publication/32409790 ID - 32409790 AB - An incorrect version of Figure 7 appeared in our paper entitled "Energy-efficient routing in the proximity of a complicated hole in wireless sensor networks" published in Wireless Networks. LA - English DB - MTMT ER - TY - JOUR AU - Xu, Q. AU - Li, S. AU - Do, Van Tien AU - Jia, K. AU - Yang, N. TI - Performance Analysis of Cognitive Radio Networks With Burst Dynamics JF - IEEE ACCESS J2 - IEEE ACCESS VL - 9 PY - 2021 SP - 110627 EP - 110638 PG - 12 SN - 2169-3536 DO - 10.1109/ACCESS.2021.3103321 UR - https://m2.mtmt.hu/api/publication/32150027 ID - 32150027 N1 - School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou, 730000, China School of Science, Lanzhou University of Technology, Lanzhou, 730000, China Department of Networked Systems and Services, Budapest University of Technology and Economics, Budapest, 1111, Hungary School of Computer and Communications, Lanzhou University of Technology, Lanzhou, 730000, China Cited By :1 Export Date: 1 March 2022 Correspondence Address: Li, S.; School of Electrical and Information Engineering, China; email: lsuop@163.com LA - English DB - MTMT ER - TY - JOUR AU - Nguyen, Tuan Hai AU - Do, Van Tien AU - Rotter, Csaba TI - Optimizing the resource usage of actor-based systems JF - JOURNAL OF NETWORK AND COMPUTER APPLICATIONS J2 - J NETW COMPUT APPL VL - 190 PY - 2021 PG - 12 SN - 1084-8045 DO - 10.1016/j.jnca.2021.103143 UR - https://m2.mtmt.hu/api/publication/32073418 ID - 32073418 N1 - Analysis, Design and Development of ICT systems (AddICT) Laboratory, Department of Networked Systems and Services, Budapest University of Technology and Economics, H-1117, Magyar tudósok körútja 2., Budapest, Hungary Nokia Bell Labs, H-1083 Budapest, Bókay János utca 36-42, Budapest, Hungary Cited By :2 Export Date: 9 June 2022 Correspondence Address: Do, T.V.; Analysis, H-1117, Magyar tudósok körútja 2., Hungary; email: do@hit.bme.hu Funding details: Hungarian Scientific Research Fund, OTKA, K-123914 Funding details: Nemzeti Kutatási Fejlesztési és Innovációs Hivatal, NKFIH Funding details: Innovációs és Technológiai Minisztérium Funding text 1: The work of H. Nguyen is partially supported by the National Research Development and Innovation Office of Hungary through the OTKA K-123914 project. The research reported in this paper and carried out at the Budapest University of Technology and Economics has been partially supported by the National Research Development and Innovation Fund based on the charter of bolster issued by the National Research Development and Innovation Office under the auspices of the Ministry for Innovation and Technology. AB - Runtime environments for IoT data processing systems based on the actor model often apply a thread pool to serve data streams. In this paper, we propose an approach based on Reinforcement Learning (RL) to find a trade-off between the the resource (thread pool in server machines) usage and the quality of service for data streams. We compare our approach and the Thread Pool Executor of Akka, an open-source software toolkit. Simulation results show that our approach outperforms ThreadPoolExecutor with the timeout rule when the thread start times are not negligible. Furthermore, the tuning of our approach is not tedious as the application of the timeout rule requires. LA - English DB - MTMT ER - TY - JOUR AU - Rotter, Csaba AU - Do, Van Tien TI - A Queueing Model for Threshold-based Scaling of UPF Instances in 5G Core JF - IEEE ACCESS J2 - IEEE ACCESS VL - 9 PY - 2021 SP - 81443 EP - 81453 PG - 11 SN - 2169-3536 DO - 10.1109/ACCESS.2021.3085955 UR - https://m2.mtmt.hu/api/publication/32055132 ID - 32055132 N1 - Cited By :1 Export Date: 28 February 2022 Correspondence Address: Van Do, T.; Department of Networked Systems and Services, Hungary; email: do@hit.bme.hu LA - English DB - MTMT ER - TY - JOUR AU - Nguyen, Khanh-Van AU - Nguyen, Chi-Hieu AU - Le, Nguyen Phi AU - Do, Van Tien AU - Chlamtac, Imrich TI - Energy-efficient routing in the proximity of a complicated hole in wireless sensor networks JF - WIRELESS NETWORKS J2 - WIREL NETW VL - 27 PY - 2021 IS - 4 SP - 3073 EP - 3089 PG - 17 SN - 1022-0038 DO - 10.1007/s11276-021-02569-3 UR - https://m2.mtmt.hu/api/publication/32048751 ID - 32048751 N1 - ISSN:1572-8196 AB - A quest for geographic routing schemes of wireless sensor networks when sensor nodes are deployed in areas with obstacles has resulted in numerous ingenious proposals and techniques. However, there is a lack of solutions for complicated cases wherein the source or the sink nodes are located close to a specific hole, especially in cavern-like regions of large complex-shaped holes. In this paper, we propose a geographic routing scheme to deal with the existence of complicated-shape holes in an effective manner. Our proposed routing scheme achieves routes around holes with the (1+$$\\epsilon$$)-stretch. Experimental results show that our routing scheme yields the highest load balancing and the most extended network lifetime compared to other well-known routing algorithms as well. LA - English DB - MTMT ER -