Christian L. Vielhaus, Johannes V. S. Busch, Philipp Geuer, Alexandros Palaios, Justus Rischke, D. Külzer, Vincent Latzko, F. Fitzek
{"title":"Handover Predictions as an Enabler for Anticipatory Service Adaptations in Next-Generation Cellular Networks","authors":"Christian L. Vielhaus, Johannes V. S. Busch, Philipp Geuer, Alexandros Palaios, Justus Rischke, D. Külzer, Vincent Latzko, F. Fitzek","doi":"10.1145/3551660.3560913","DOIUrl":"https://doi.org/10.1145/3551660.3560913","url":null,"abstract":"Next-generation networks are envisioned to be empowered by artificial intelligence with predictive capabilities. Predicting handovers in high mobility scenarios enables networks and applications to adapt ahead of time to improve the Quality of Service (QoS). In this paper, we present a two-step machine learning (ML) method, consisting of a classifier and regressor, that can predict the remaining time until a handover occurs. Our approach is validated on a dataset that was captured in a real cellular network. The results show that upcoming handovers can be detected with a recall above 90% and the timing of handovers with an error smaller than one second. Furthermore, we compare the importance of input features derived from radio conditions and user locations for the ML models and discuss deployment scenarios of our approach. In particular, our results suggest that cell-based models perform better than models trained for larger areas.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116888365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards Cross-domain Mobility Management in the Edge: New Elements of Cloud-native Mobile IPv6 Full-scale Implementation","authors":"Ákos Leiter, Edina Lami, L. Bokor","doi":"10.1145/3551660.3560919","DOIUrl":"https://doi.org/10.1145/3551660.3560919","url":null,"abstract":"Control and User Plane Separation (CUPS) allows placing the control plane separately from the actual user plane executor. This allows deploying user plane instances closer to the end-user: traffic serving can be more effortless, and end-to-end latency can be decreased. Mobile IPv6 can also be divided into control and user plane parts. This article will show what this separation presumably will look like in connection with Mobile IPv6. In a dynamic cloud environment, standard Mobile IPv6 must be part of the overall orchestration flow. This is where Cloud-native Mobile IPv6 comes into the picture. This paper presents how ordinary and cloud-native Mobile IPv6 architectures should be refactored with corresponding signaling flows to fit into the CUPS concept. We also show by measurements the latency budget we can gain using localized user-plane instances to connect to a distributed application.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126182220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nafi Ahmad, Abdul Wahab, J. Schormans, A. A. Arnab
{"title":"Comparative QoE Study of VoD and Passive Gaming Videos using Cross-Correlated QoS Metrics","authors":"Nafi Ahmad, Abdul Wahab, J. Schormans, A. A. Arnab","doi":"10.1145/3551660.3560907","DOIUrl":"https://doi.org/10.1145/3551660.3560907","url":null,"abstract":"In this paper, we compare the end-user Quality of Experience (QoE) of two of the most popular streaming applications: Video on Demand (VoD) applications and Passive Video Game (PVG) streaming applications. Previous studies have shown that in real-life traffic, the Quality of Service (QoS) metrics such as packet delay and packet loss ratio (PLR) have cross-correlation between them. Very few studies have been done on how the correlated QoS metrics affect the end user QoE. In previous work, we have shown that correlated QoS metrics map objective QoE differently than non-correlated QoS metrics. Following the findings, we carried out a subjective QoE analysis to observe if it shows a similar outcome as objective QoE. We used a bespoke version of the NetEm emulator, which allowed us to implement cross-correlated QoS inputs and carried out a subjective QoE survey using 42 human subjects for both VoD and PVG streaming applications. The result showed for low PLR conditions, QoE in both correlated and non-correlated PLR showed similar ratings. But as PLR increased, the average QoE of correlated QoS was considerably higher (sometimes about 50%) than its non-correlated counterparts. It was observed for both VoD and PVG applications. This was more pronounced in the case of PVG when the experience of the subject was taken into consideration. We also found that age and gender do not show significant differences in the subjective QoE. Finally, we compared the existing state-of-the-art objective quality assessment with the subjective QoE of PVG application. We found that QoE with correlated PLR showed a higher correlation coefficient with the existing objective QoE metrics than the non-correlated counterparts. This finding solidifies the importance of studying QoE using correlated QoS metrics.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124020629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Environment-Aware Link Quality Prediction for Millimeter-Wave Wireless LANs","authors":"Yuchen Liu, D. Blough","doi":"10.1145/3551660.3560912","DOIUrl":"https://doi.org/10.1145/3551660.3560912","url":null,"abstract":"Millimeter-wave (mmWave) communications have been regarded as one of the most promising solutions to deliver ultra-high data rates in wireless local-area networks. A significant barrier to delivering consistently high rate performance is the rapid variation in quality of mmWave links due to blockages and small changes in user locations. If link quality can be predicted in advance, proactive resource allocation techniques such as link-quality-aware scheduling can be used to mitigate this problem. In this paper, we propose a link quality prediction scheme based on knowledge of the environment. We use geometric analysis to identify the shadowed regions that separate LoS and NLoS scenarios, and build LoS and NLoS link-quality predictors based on an analytical model and a regression-based approach, respectively. For the more challenging NLoS case, we use a synthetic dataset generator with accurate ray tracing analysis to train a deep neural network (DNN) to learn the mapping between environment features and link quality. We then use the DNN to efficiently construct a map of link quality predictions within given environments. Extensive evaluations with additional synthetically generated scenarios show a very high prediction accuracy for our solution. We also experimentally verify the scheme by applying it to predict link quality in an actual 802.11ad environment, and the results show a close agreement between predicted values and measurements of link quality.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129537682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Gonsioroski, Amanda Beatriz dos Santos, Luiz Raimundo Leão Junior, L. Mello
{"title":"Optimization of Path Loss Prediction in Urban and Suburban Environments in 2.3-2.4 GHz using OLS Nonlinear Regression and Artificial Neural Networks","authors":"L. Gonsioroski, Amanda Beatriz dos Santos, Luiz Raimundo Leão Junior, L. Mello","doi":"10.1145/3551660.3560917","DOIUrl":"https://doi.org/10.1145/3551660.3560917","url":null,"abstract":"The path loss models for urban and suburban scenarios play a key role since they provide RF power estimations that allow an optimized design and performance of the wireless network. Although different models of propagation can be found in the literature, it is always important to consider the particular characteristics of urbanization in each region where a 5G technology will be implemented. In this work, the empirical results of propagation loss in the 2.3-2.4 GHz band in an urban and suburban environment are compared with some widely used empirical models. Subsequently, the nonlinear regression of the propagation loss values obtained in the field is performed based on an Ordinary Least Squares (OLS) approach and an Artificial Neural Networks (ANN) approach. The empirical results, both in urban and suburban scenarios, were better represented by the SUI model. The nonlinear regression results generated by the ANN modeling were better than the OLS regression results.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"227 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132225647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deep Q-learning-enabled Deployment of Aerial Base Stations in the Presence of Mobile Users","authors":"Nahid Parvaresh, B. Kantarci","doi":"10.1145/3551660.3560909","DOIUrl":"https://doi.org/10.1145/3551660.3560909","url":null,"abstract":"Uncrewed aerial vehicle-mounted base stations (UAV-BS) have recently attracted significant attention in order to assist ground base stations (BSs) and provide Internet access to users. UAV-BSs benefit from their mobility nature in the air and are able to constantly move towards the locations where the demand is higher. However, finding the optimal location of UAV-BSs and maintaining it is an NP-hard problem that has no deterministic solution in polynomial time. In this paper, we exploit reinforcement learning (RL) in order to solve the optimization problem of UAV-BSs and find their optimal location in the presence of mobile User Equipment (UEs). We consider UAV-BS as the agent of RL and deploy two algorithms, i.e. Q-learning and deep Q-learning in order to solve the location optimization problem of UAV-BSs. Through simulations, we show that the proposed DQL model with a continuous state space including the mobility information of users can effectively adapt to the environmental changes and improve the user data rate by 46%, packet loss ratio by 70%, and transmission delay by 60%.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133928314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"When Is Multiple Access Beneficial? An Analysis of Multi-User Performance in IEEE 802.11ax","authors":"Harshal Dev, Utkrisht Sikka, Jagrati Kulshrestha, Mukulika Maity","doi":"10.1145/3551660.3560920","DOIUrl":"https://doi.org/10.1145/3551660.3560920","url":null,"abstract":"IEEE 802.11ax introduces OFDMA (Orthogonal Frequency Division Multiple Access), that allows multiple users to transmit or receive frames concurrently. The standard suggests that OFDMA will provide reduced latency and increased throughput in dense scenarios compared to single-user OFDM. This work uses the latest 802.11ax models supplied by the widely used open-source network simulator NS-3 (version 3.34) to investigate the OFDMA performance under various downlink traffic loads and various application settings for both UDP and TCP traffic. Our simulation results show that the actual benefits of OFDMA over OFDM can only be extracted under intermediate traffic loads for UDP and TCP. We observe that in comparison to OFDM, OFDMA provides more consistent performance in the case of video streaming and video conferencing. Further, it provides lesser latency for web-based applications.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122361467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Joe Saad, K. Khawam, Mohamad Yassin, Salvatore Costanzo, Karen Boulos
{"title":"Crowding Game and Deep Q-Networks for Dynamic RAN Slicing in 5G Networks","authors":"Joe Saad, K. Khawam, Mohamad Yassin, Salvatore Costanzo, Karen Boulos","doi":"10.1145/3551660.3560908","DOIUrl":"https://doi.org/10.1145/3551660.3560908","url":null,"abstract":"Fifth generation (5G) mobile networks do not solely support services with very high throughput, but also answer the requirements of other heterogeneous services, characterized by different Quality of Service (QoS) criteria such as maximum tolerated delay, minimum guaranteed throughput, or capacity constraints. This heterogeneity necessitates the partitioning of the available radio resources into multiple slices, where each slice is characterized by specific QoS and isolation constraints. Nonetheless, a static resource allocation scheme among slices might not be an effective solution to face the dynamic and sporadic nature of traffic and users' service types. Therefore, a dynamic slicing scheme that leverages on the ease of slice selection per user in the fully virtualized open Radio Access Networks (RAN), is paramount to accommodate the various demands and load conditions. The main contribution of this paper is to apply traffic engineering in the scope of RAN slicing. In fact, instead of solely re-dimensioning the slices by injecting more resources when congestion hits, we also allot users to slices that may differ from their service type if their performance target is met. This is a novel definition of dynamic slicing, the dynamicity not being in re-dimensioning on the fly but in accommodating active users to existing resources for higher resource utilization efficiency without hindering users' performances. Additionally, the available bandwidth is dynamically adjusted among slices based on their load and affected users' performances. To reach that goal, two Dynamic RAN Slicing schemes are proposed: a centralized scheme based on Deep Reinforcement Learning (DRL) and a distributed scheme based on non-cooperative game theory. Exhaustive numerical simulations demonstrate the high efficiency of our proposed approach in comparison with the state-of-the-art where users are allocated to slices according to their service type and required Key Performance Indicators (KPIs).","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125835115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Model Driven Approach to Design an Automotive CPS with SysReo Language","authors":"Perla Tannoury, Samir Chouali, A. Hammad","doi":"10.1145/3551660.3560916","DOIUrl":"https://doi.org/10.1145/3551660.3560916","url":null,"abstract":"Modeling Cyber-Physical Systems (CPS) remains a challenge due to the complex behaviors of their interconnected components that operate in a physical environment. In this paper, we introduce a new modeling approach based on \"SysReo\" models, that relies on SysML/MARTE, Reo, and OCL to capture the different aspects of CPS with time constraints, including requirements, behavior, architecture, and interaction protocols. The novelty of our approach relies in the combination of SysML and Reo to handle the complexity of CPS architecture and protocols, in the design step by proceeding incrementally. Then we used SysML/MARTE to model the behavior of CPS with timed constraints. Furthermore, we define OCL constraints to specify rules to be respected to model consistently CPS.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121510020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Spectrum Sensing and SINR Estimation in an IEEE 802.11s Dynamic Spectrum Access Wireless Mesh Network","authors":"Natasha Zlobinsky, A. Mishra, F. Takawira","doi":"10.1145/3551660.3560918","DOIUrl":"https://doi.org/10.1145/3551660.3560918","url":null,"abstract":"Wireless Mesh Networks (WMNs) that make opportunistic use of licensed spectrum (also called Cognitive Radio Ad Hoc Networks or CRAHNs) need to perform spectrum sensing (SS) to find an advantageous channel assignment. However, current SS methods for cognitive radios typically rely on binary decisions on the presence or absence of interference, or the presence or absence of a licensed user. Interference estimation in WMNs also relies on binary measures such as the presence or absence of conflicts. Yet, performance can be significantly improved if measures have smaller resolutions, i.e., are more fine-grained than binary decisions. On the matter of when SS is performed, existing work tends to require a trade-off between SS time and data transmission. This work presents Signal-to-Interference-and-Noise-Ratio estimation for Dynamic Spectrum Access WMNs that is granular and accurate. We also propose to use the idle time inherent in the backoff mechanism of Enhanced Distributed Channel Access (EDCA) for performing SS, which has the benefit of causing no disruption to data transmissions. The estimation method we suggest that uses the SS results employs the maximum a posteriori estimate, which is the same as the maximum likelihood estimator. We show that this is the best possible estimator as it is the minimum variance unbiased estimator and it is efficient since the Cramer-Rao bound is satisfied by equality. The performance is evaluated in terms of confidence intervals. We show that the time available during EDCA backoff for performing sensing is sufficient. We also show the margin of error that can be achieved based on the number of sensing windows employed.","PeriodicalId":306986,"journal":{"name":"Proceedings of the 20th ACM International Symposium on Mobility Management and Wireless Access","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123656934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}