TY - JOUR AU - Fayad, Abdulhalim AU - Cinkler, Tibor TI - Energy-Efficient Joint User and Power Allocation in 5G Millimeter Wave Networks: A Genetic Algorithm-based Approach JF - IEEE ACCESS J2 - IEEE ACCESS VL - 12 PY - 2024 SP - 20019 EP - 20030 PG - 12 SN - 2169-3536 DO - 10.1109/ACCESS.2024.3361660 UR - https://m2.mtmt.hu/api/publication/34559046 ID - 34559046 N1 - Export Date: 19 February 2024 LA - English DB - MTMT ER - TY - JOUR AU - Zentai, B. AU - Toka, László TI - Boat Speed Prediction in SailGP JF - COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE J2 - COMMUN COMPUT INFORM SCI VL - 2035 PY - 2024 SP - 155 EP - 164 PG - 10 SN - 1865-0929 DO - 10.1007/978-3-031-53833-9_13 UR - https://m2.mtmt.hu/api/publication/34751443 ID - 34751443 N1 - Conference code: 308699 Export Date: 22 March 2024 Correspondence Address: Zentai, B.; Budapest University of Technology and EconomicsHungary; email: benedek.zentai@edu.bme.hu AB - The significance of data analysis in high-performance sports has largely increased in recent years offering opportunities for further exploration using machine learning techniques. As a pioneer work in the academic community, our work showcases the power of data-driven approaches in enhancing performance and decision-making at high-performance sailing events. Specifically, we explore the application of data mining techniques on the dataset collected at a high-performance sailing event in Bermuda in 2021. By analyzing data from Race 4, the study aims to gain valuable insights into the relationship between variables such as wind speed, wind direction, foil usage, and daggerboard adjustments, and their impact on boat speed. Various prediction models, including Gradient Boosting, Random Forest, and a stacked model, were employed and evaluated using performance metrics like R2 score and mean squared error. The results demonstrate the models’ ability to accurately predict boat speed. These findings can be utilized to refine race strategies, optimize sail and rudder settings, and improve overall performance in SailGP races. Future plans include collaboration with SailGP to work with larger datasets and integrate the models into live racing scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. LA - English DB - MTMT ER - TY - JOUR AU - Rahimian, Pegah AU - Kim, H. AU - Schmid, M. AU - Toka, László TI - Pass Receiver and Outcome Prediction in Soccer Using Temporal Graph Networks JF - COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE J2 - COMMUN COMPUT INFORM SCI VL - 2035 PY - 2024 SP - 52 EP - 63 PG - 12 SN - 1865-0929 DO - 10.1007/978-3-031-53833-9_5 UR - https://m2.mtmt.hu/api/publication/34751450 ID - 34751450 N1 - Conference code: 308699 Export Date: 22 March 2024 Correspondence Address: Rahimian, P.; Budapest University of Technology and EconomicsHungary; email: pegah.rahimian@edu.bme.hu AB - This paper explores the application of the Temporal Graph Network (TGN) model to predict the receiver and outcome of a pass in soccer. We construct two TGN models that estimate receiver selection probabilities (RSP) and receiver prediction probabilities (RPP) to predict the intended and actual receivers of a given pass attempt, respectively. Then, based on these RSP and RPP, we compute the success probability (CPSP) of each passing option that the pass is successfully sent to the intended receiver as well as the overall pass success probability (OPSP) of a given situation. The proposed framework provides deeper insights into the context around passes in soccer by quantifying the tendency of passers’ choice of passing options, difficulties of the options, and the overall difficulty of a given passing situation at once. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. LA - English DB - MTMT ER - TY - JOUR AU - Mihályi, Balázs Márk AU - Biczók, Gergely AU - Toka, László TI - Momentum Matters: Investigating High-Pressure Situations in the NBA Through Scoring Probability JF - COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE J2 - COMMUN COMPUT INFORM SCI VL - 2035 PY - 2024 SP - 77 EP - 90 PG - 14 SN - 1865-0929 DO - 10.1007/978-3-031-53833-9_7 UR - https://m2.mtmt.hu/api/publication/34751452 ID - 34751452 N1 - Conference code: 308699 Export Date: 22 March 2024 Correspondence Address: Mihalyi, B.; Budapest University of Technology and EconomicsHungary; email: balazsmark.mihalyi@edu.bme.hu AB - One of the defining characteristics of real basketball stars, and even great role players, is how well they perform under immense mental pressure. In this paper, we present a method to identify high-pressure situations during a basketball game through shooting success. In order to calculate the amount of pressure a team is facing going into a game, we use a prediction model to determine the importance of the given game for that team to reach their end-of-season goal. The model relies on features referring to game context, recent form, and pre-season aspirations. We then investigate the impact of our pre-game pressure metric, along with other factors, on the shooting performance of NBA players on six seasons’ worth of data. We find that shotmaking in the NBA is mainly impacted by the so-called momentum, i.e., when a team outscores their opponent significantly over a short period of time. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. LA - English DB - MTMT ER - TY - JOUR AU - Erdei, Roland AU - Toka, László TI - Minimizing Resource Allocation for Cloud-Native Microservices JF - JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT J2 - J NETW SYST MANAG VL - 31 PY - 2023 IS - 2 PG - 18 SN - 1064-7570 DO - 10.1007/s10922-023-09726-3 UR - https://m2.mtmt.hu/api/publication/33638899 ID - 33638899 AB - With the continuous progress of cloud computing, many microservices and complex multi-component applications arise for which resource planning is a great challenge. For example, when it comes to data-intensive cloud-native applications, the tenant might be eager to provision cloud resources in an economical manner while ensuring that the application performance meets the requirements in terms of data throughput. However, due to the complexity of the interplay between the building blocks, adequately setting resource limits of the components separately for various data rates is nearly impossible. In this paper, we propose a comprehensive approach that consists of measuring the resource footprint and data throughput performance of such a microservices-based application, analyzing the measurement results by data mining techniques, and finally formulating an optimization problem that aims to minimize the allocated resources given the performance constraints. We illustrate the benefits of the proposed approach on Cortex, an extension to Prometheus for storing monitored metrics data. The data-intensive nature of this illustrative example stems from real-time monitoring of metrics exposed by a multitude of applications running in a data center and the continuous analysis performed on the collected data that can be fetched from Cortex. We present Cortex’s performance vs resource footprint trade-off, and then we build regression models to predict the microservices’ resource consumption and draw a mathematical programming formulation to optimize the most important configuration parameters. Our most important finding is the linear relationship between resource consumption and application performance, which allows for applying linear regression and linear programming models. After the optimization, we compare our results to Cortex’s recommendation, leading to a CPU reservation reduced by 50–80%. LA - English DB - MTMT ER - TY - CHAP AU - Kovács, Gergely Attila AU - Bokor, László ED - Imre, Sándor ED - Gyimóthy, Szabolcs ED - Varga, Pál TI - Towards realistic simulation of MEC-based Collective Perception: an initial edge service design for the Artery/Simu5G framework T2 - Proceedings of the 1st Workshop on Intelligent Infocommunication Networks, Systems and Services (WI2NS2) PB - BME Villamosmérnöki és Informatikai Kar CY - Budapest SN - 9789634219026 PY - 2023 SP - 1 EP - 6 PG - 6 DO - 10.3311/WINS2023-010 UR - https://m2.mtmt.hu/api/publication/33667720 ID - 33667720 AB - Day 2 V2X applications are the next step in vehicular communications, as they aim to extend the scope of shared information. In addition to status data, traffic participants are also aware of each other's sensory capabilities and the data deriving from those sensors. Collective Perception (CP), one of the flagship Day 2 services, enables vehicles and infrastructural elements, like roadside units or smart intersection controllers, to provide information about detected objects, significantly increasing the level of cooperative awareness V2X can grant for the communicating entities. However, with the escalation in the amount of data to be sent over the vehicular or mobile networks and the need for more processing power to enable real-time safety applications based on CP, some form of infrastructural aid is needed. The traditional central cloud-based approach might fall short of meeting the latency requirements. To keep latency within an acceptable range and solve the computational tasks locally, leveraging the capabilities of 5G Multi-access Edge Computing (MEC) could be a potential solution, thus ensuring a minimum impact on the core network. The architectural design and the modular approach of service implementation in the MEC specification by ETSI enable quick service deployment. This paper focuses on advanced Collective Perception-based V2X applications and the potential positive impact on their performance when operating with the support of edge computing. We also present the description – including the design considerations – of an initial, Artery/Simu5G-based edge service model working as a network-side intelligence extending the functionality of applications hosted on the vehicles. LA - English DB - MTMT ER - TY - JOUR AU - Leiter, Ákos AU - Lami, Edina AU - Hegyi, Attila AU - Varga, József AU - Bokor, László TI - Closed-loop Orchestration for Cloud-native Mobile IPv6 JF - INFOCOMMUNICATIONS JOURNAL J2 - INFOCOMMUNICATIONS J VL - 15 PY - 2023 IS - 1 SP - 44 EP - 54 PG - 11 SN - 2061-2079 DO - 10.36244/ICJ.2023.1.5 UR - https://m2.mtmt.hu/api/publication/33780195 ID - 33780195 N1 - Nokia Bell Labs, Budapest, Hungary Department of Networked Systems and Services, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary ELKH-BME Cloud Applications Research Group, BME Informatics Building, Budapest, Hungary Export Date: 1 June 2023 AB - With the advent of Network Function Virtualization (NFV) and Software-Defined Networking (SDN), every network service type faces significant challenges induced by novel requirements. Mobile IPv6, the well-known IETF standard for network-level mobility management, is not an exemption. Cloud-native Mobile IPv6 has acquired several new capabilities due to the technological advancements of NFV/SDN evolution. This paper presents how automatic failover and scaling can be envisioned in the context of cloud-native Mobile IPv6 with closed-loop orchestration on the top of the Open Network Automation Platform. Numerical results are also presented to indicate the usefulness of the new operational features (failover, scaling) driven by the cloud-native approach and highlight the advantages of network automation in virtualized and softwarized environments. LA - English DB - MTMT ER - TY - JOUR AU - Pelle, István AU - Paolucci, Francesco AU - Sonkoly, Balázs AU - Cugini, Filippo TI - P4-assisted seamless migration of serverless applications towards the edge continuum JF - FUTURE GENERATION COMPUTER SYSTEMS J2 - FUTUR GENER COMP SYST VL - 146 PY - 2023 SP - 122 EP - 138 PG - 17 SN - 0167-739X DO - 10.1016/j.future.2023.04.010 UR - https://m2.mtmt.hu/api/publication/33781827 ID - 33781827 N1 - High Speed Networks Laboratory, Department of Telecommunications and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3, Budapest, H-1111, Hungary MTA-BME Network Softwarization Research Group, Műegyetem rkp. 3., Budapest, H-1111, Hungary ELKH-BME Cloud Applications Research Group, Műegyetem rkp. 3., Budapest, H-1111, Hungary EIT Digital Doctoral School, Budapest, H-1111, Hungary CNIT, Pisa, Italy Export Date: 5 May 2023 CODEN: FGCSE Correspondence Address: Pelle, I.; High Speed Networks Laboratory, Műegyetem rkp. 3, Hungary; email: pelle.istvan@vik.bme.hu LA - English DB - MTMT ER - TY - CHAP AU - Sonkoly, Balázs AU - Nagy, Bálint György AU - Dóka, János AU - Kecskés-Solymosi, Zsófia AU - Czentye, János Emánuel AU - Formanek, Bence AU - Jocha, Dávid AU - Gerő, Balázs Péter TI - Towards an Edge Cloud Based Coordination Platform for Multi-User AR Applications Built on Open-Source SLAMs T2 - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 9798350348392 PY - 2023 SP - 923 EP - 924 PG - 2 DO - 10.1109/VRW58643.2023.00304 UR - https://m2.mtmt.hu/api/publication/33792422 ID - 33792422 N1 - Budapest University of Technology and Economics, HSN Lab, Faculty of Electrical Engineering and Informatics, Department of Telecommunications and Media Informatics, Hungary MTA-BME Network Softwarization Research Group, Hungary ELKH-BME Cloud Applications Research Group, Hungary Ericsson Research, Sweden Export Date: 1 June 2023 Correspondence Address: Sonkoly, B.; Budapest University of Technology and Economics, Hungary; email: sonkoly.balazs@vik.bme.hu AB - Multi-user and collaborative AR applications pose several challenges. The expected user experience requires accurate pose information for each device and precise synchronization of the respective coordinate systems in real-time. Unlike mobile phones or AR glasses running on battery with constrained resource capacity, cloud and edge platforms can provide the computing power for the core functions under the hood. In this paper, we propose a novel edge cloud based platform for multi-user AR applications realizing an essential coordination service among the users. The latency critical, computation intensive Simultaneous Localization And Mapping (SLAM) function is offloaded from the device to the edge cloud infrastructure. LA - English DB - MTMT ER - TY - CHAP AU - Pelle, István AU - Paolucci, Francesco AU - Sonkoly, Balázs AU - Cugini, Filippo ED - Anon, A TI - P4-based Hitless FaaS Load Balancer for Packet-Optical Network Edge Continuum T2 - Optical Fiber Communication Conference (OFC) 2023 PB - Optica Publishing Group CY - Washington DC SN - 9781957171180 PY - 2023 PG - 3 DO - 10.1364/OFC.2023.Th1D.5 UR - https://m2.mtmt.hu/api/publication/33845812 ID - 33845812 AB - P4 and novel node telemetry are leveraged to provide load balancing of ultra-low latency serverless application to multiple edges. Handling the overload of one edge without observable change in application delay is demonstrated. LA - English DB - MTMT ER -