{"title":"Performance of a Neural Network Receiver under Mismatch of Channel Training Samples","authors":"Pedro H. C. de Souza, L. Mendes, R. Souza","doi":"10.1109/FNWF55208.2022.00099","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00099","url":null,"abstract":"Data-driven frameworks for wireless communications systems are currently attracting a lot of attention from researchers and practitioners alike. These frameworks based on machine learning (ML) algorithms and neural networks (NN s) architectures, are capable of solving a broad variety of tasks in the wireless communications domain as, for exam-ple, signal detection, channel estimation, channel coding and modulation classification. Moreover, these tasks are solved at a reduced computational cost in comparison to classic model-driven frameworks such as the maximum likelihood for signal detection, for instance. However, data-driven frameworks depend heavily on the dataset available, so that ML algorithms and NNs could be able to actually learn from data and optimize their parameters to solve such tasks at hand. This contrasts to the model-driven frameworks that inherently impart specialized domain knowledge and thus do not require to learn from data. Therefore, a mismatch between the dataset used for training and the actual data may severely degrade the performance of ML algorithms and NN s, especially in practical scenarios where the data statistics and distribution are unknown. In this work we analyze a recently proposed NN for detecting compressed signals, under practical scenarios of dataset samples mismatch, where channel delay profile and statistics mismatches are considered. Numerical results generated by computer simulations show that the NN is robust to statistics mismatches, whereas a significant degradation in performance is observed for channel delay profile mismatches.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116822079","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":"Influences of logical link design in 5G campus systems","authors":"G. Cainelli, L. Underberg, L. Rauchhaupt","doi":"10.1109/FNWF55208.2022.00072","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00072","url":null,"abstract":"5G technology is gaining further momentum to be applied in industrial automation use cases. This entails the necessity of accurate performance testing of 5G system capabilities to build trust in a communication network before and during its deployment in an industrial application. In this paper, a performance analysis of a commercially available Rel. 15 5G system composed of a 5G standalone network and industrial 5G devices was carried out. A sophisticated approach to conduct performance testing of communication networks from an industrial application's perspective is presented. The performance tests are conducted in an industrial test hall with real-world propagation conditions. Results of selected test cases in two different testing setups are presented. The performance testing results reveal a significant interdependence of timing behavior of uplink and downlink traffic, when both are running on the same device or on two separate devices. Based on the findings, conclusions are drawn, which are especially of interest to the end users.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124677389","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}
Xiang Liu, Junwei Li, Xuming Wu, Jinglong Zhu, Yan Zeng, Da Liu, Xiang Wang, Dechao Zhang
{"title":"Fiber-to- The-Room (FTTR) Technologies for the 5th Generation Fixed Network (F5G) and Beyond","authors":"Xiang Liu, Junwei Li, Xuming Wu, Jinglong Zhu, Yan Zeng, Da Liu, Xiang Wang, Dechao Zhang","doi":"10.1109/FNWF55208.2022.00068","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00068","url":null,"abstract":"We review a series of innovative optical network technologies for the 5th generation fixed network (F5G) and beyond, aiming to support enhanced fixed broadband, full fiber connection, and guaranteed reliable experience. Particularly, the emerging fiber-to-the-room (FTTR) technology that offers telecom-quality Wi-Fi experience and premium home broadband connectivity is described. Proof-of-concept demonstrations of fast seamless Wi-Fi roaming, dynamic Wi-Fi power management, centralized traffic scheduling, and AI-enabled network slicing are presented. A throughput increase of up to 96% and a reduced roaming latency of 20 ms have been achieved by the FTTR-enabled coordination of the Wi-Fi access points. Finally, future network evolution beyond F5G is discussed.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129853086","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":"Performance Analysis of Large Aperture mMIMO UCCA Arrays in a 5G User Dense Network","authors":"Md Imrul Hasan, SK Nayemuzzaman, M. Saquib","doi":"10.1109/FNWF55208.2022.00098","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00098","url":null,"abstract":"The fifth generation (5G) wireless network signals suffer from significant path loss due to the use of higher frequencies in Sub-6 GHz and millimeter-wave (mmWave) bands. Inter-user interference in an ultra-dense network offers additional challenges to provide a high data rate. Therefore, it is desirable to generate narrow beams to extend the coverage of a 5G network by increasing antenna gain, and improve its capacity/data rate by reducing inter-user interference. Unlike the conventional massive multiple-input multiple-output (mMIMO) rectangular planar antenna array, an mMIMO uniform concentric circular antenna (UCCA) array with a larger inter-ring spacing (i.e., inter-ring spacing> ⋋/2) is capable of generating a significantly narrow beam with a moderate side-lobe level while utilizing the same number of antennas. This fact leads us to investigate the use of large aperture mMIMO UCCA arrays in a 5G user-dense network in order to improve its performance.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129122078","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}
Ana Hermosilla, Jorge Gallego-Madrid, P. Martinez-Julia, Ved P. Kafle, Kostis Trantzas, C. Tranoris, Rafael Direito, Diogo Gomes, Jordi Ortiz, S. Denazis, A. Skarmeta
{"title":"Deployment of 5G Network Applications over Multidomain and Dynamic Platforms","authors":"Ana Hermosilla, Jorge Gallego-Madrid, P. Martinez-Julia, Ved P. Kafle, Kostis Trantzas, C. Tranoris, Rafael Direito, Diogo Gomes, Jordi Ortiz, S. Denazis, A. Skarmeta","doi":"10.1109/FNWF55208.2022.00055","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00055","url":null,"abstract":"5G mobile communications are bringing a plethora of applications that are challenging existing network infrastructures. These services demand a dynamic, flexible and adaptive infrastructure capable of fulfilling the rigorous requirements they need to operate correctly. Another key point is the need of real-time reactions in the architecture configurations to effectively satisfy changes in the user's behavior. To address these issues, Network Function Virtualization (NFV) and Software-Defined Networking (SDN) paradigms arise as enablers of the network infrastructures of the future. These technologies will permit the design and development of a new set of network applications that will be dynamically managed and orchestrated over multiple domains in an effortless way. In this work, we present an architecture that interconnects two facilities located in Spain and Japan, which permits the deployment of distributed applications. Besides, we detail how the control and data planes are managed to enable the operation of the system.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130428384","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}
D. Cvetkovski, N. Maletic, J. Gutiérrez, P. Flegkas, N. Makris, Alexandros Dalkalitsis, Petros Arvanitis, M. Anastasopoulos, Petros Georgiadis, A. Tzanakaki
{"title":"Railway services support over a 5G infrastructure exploiting a multi-technology wireless transport network","authors":"D. Cvetkovski, N. Maletic, J. Gutiérrez, P. Flegkas, N. Makris, Alexandros Dalkalitsis, Petros Arvanitis, M. Anastasopoulos, Petros Georgiadis, A. Tzanakaki","doi":"10.1109/FNWF55208.2022.00108","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00108","url":null,"abstract":"Transportation, and particularly railways, has been one of the main vertical sectors targeted by 5G, where achieving seamless connectivity to and in the train is still a real challenge. Nowadays, efforts are steered towards the standardization of the Future Rail Mobile Communication System (FRMCS), having 5G as the cornerstone to deploy all type of vertical services on top of a common 5G cellular system. There is work ongoing in the 5G-VICTORI project focused on the assessment of the capability to seamlessly serve all communication requirements of train operators and passengers in railways. This paper proposes a 5G platform for railway verticals to deploy their services that makes use of a wireless transport infrastructure consisting of heterogeneous networks, e.g. Sub-6 GHz, millimeter wave (mmWave). This platform provides network and compute/storage resources to the ground and on-board 5G segments. The paper delves into the challenges for handover management across the proposed multi-technology transport infrastructure and presents the implementation of a vertical application on top of such platform.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131423274","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}
Mohammadreza Salarbashishahri, S. Okegbile, Jun Cai
{"title":"A Shapley value-enhanced evaluation technique for effective aggregation in Federated Learning","authors":"Mohammadreza Salarbashishahri, S. Okegbile, Jun Cai","doi":"10.1109/FNWF55208.2022.00024","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00024","url":null,"abstract":"5G networks make it possible to transfer real-time sensory data between millions of devices, forming the internet of things. A typical method to utilize these data is to train a machine learning algorithm to extract the features. Federated learning (FL) is a platform for a coalition of clients to train a model collaboratively without sharing their data to preserve data privacy. Data and model poisoning attacks, free-riding attacks, and model divergence due to clients' non-independent and identically distributed (non-IID) datasets are some challenges in conventional federated learning. The lack of an evaluation method in federated averaging (FedAvg) in FL makes it impossible to identify malicious users or amend the divergence of the global model. In this study, we propose a Shapley-based aggregation algorithm called Shapley averaging (ShapAvg) to aggregate the global model more effectively by evaluating the clients' models. In this algorithm, each client's weight in the weighted average will be proportional to its contribution to the global model performance. The results show that the proposed method outperforms FedAvg when using non-IID datasets and in case of data poisoning or free-riding attacks.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"17 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134369786","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":"Offloading in 5G Cellular Networks: Unexplored Strategies","authors":"Gourish Goudar, Sanket Mishra","doi":"10.1109/FNWF55208.2022.00090","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00090","url":null,"abstract":"With the escalating demands for data-intensive content, and the convergence of mobile and connected devices, there is a growing requirement of high bandwidth speeds in multimedia applications. 5G will be a game-changer in the business operations and in providing a engaging customer experience. The 5G vision promises to deliver high-speed downloads with low latency. Managing the exponential growth in data traffic is one of the mobile operator's most challenging issues in 5G networks. Mobile data offloading is a potential and low-cost method for alleviating cellular network congestion. To make this conceivable, we need a new paradigm for hybrid networks that capitalizes on the presence of several alternative communication ways. This entails significant modifications in how data is handled, thereby influencing the behavior of network protocols. This paper presents various techniques for data offloading in cellular 5G networks, discussing the requirements, advantages, and limitations. The research work in this paper provides a detailed presentation of the gaps identified in 5G networks data offloading techniques, the requirements and challenges, and a way forward to solve the challenges, including the most recent technological advancements such as deep learning, edge computing, WiFi-6, social networks and software-defined networks (considering the heterogeneity aspect of the network).","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133132431","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":"Autoencoder Communications with Optimized Interference Suppression for NextG RAN","authors":"Kemal Davaslioglu, T. Erpek, Y. Sagduyu","doi":"10.1109/FNWF55208.2022.00037","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00037","url":null,"abstract":"This paper models an end-to-end communications system for the NextG radio access network (RAN) as an autoencoder (AE) subject to interference effects. The transmitter (coding and modulation) and receiver (demodulation and decoding) are represented as deep neural networks (DNNs) of the encoder and decoder, respectively. The AE communications systems is trained with interference training and randomized smoothing to operate under unknown and dynamic interference (jamming) effects. Compared to conventional communications, the AE communications with interference training and randomized smoothing can achieve up to 36 dB interference suppression with a channel reuse of four for the single antenna case. This paper also extends the AE communications formulation to the multiple-input multiple-output (MIMO) case under interference effects and shows the bit error rate (BER) improvement compared to conventional MIMO communications.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132755199","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}
Morteza Kheirkhah, Ulises Olvera-Hernandez, T. Çogalan, Alain A. M. Mourad
{"title":"SDAC: An Architectural Enhancement to Enable Artificial Intelligence in 5G Systems","authors":"Morteza Kheirkhah, Ulises Olvera-Hernandez, T. Çogalan, Alain A. M. Mourad","doi":"10.1109/FNWF55208.2022.00113","DOIUrl":"https://doi.org/10.1109/FNWF55208.2022.00113","url":null,"abstract":"This paper explores two new ideas to enable Artificial Intelligence (AI) and Machine Learning (ML) in 5G Systems, which is an essential need for modern networks, allowing users to utilize multiple access technologies (cellular and Wi-Fi) simultaneously. The first idea proposes to connect a meddler component so-called “Stack Data Analytics Coordinator” (SDAC), with each radio protocol stack (e.g., 5G-NR or Wi-Fi) at both user equipment (UE) and access network nodes (e.g., gNB and Wi-Fi AP/Controller). SDAC acts as a coordinator between data providers (which could be in a protocol stack) and analytics providers (which could be anywhere in the 5GS and UE). However, if an analytics consumer is within the protocol stack (e.g., at the MAC layer), then SDAC allows an analytics provider to be operating close to the protocol stack (e.g., at the same box), minimizing end-to-end communication latency between these components. Furthermore, SDACs allow UE, WLAN (Wireless LAN), RAN (Radio Access Network), and Core Network (CN) to directly interact with each other and exchange statistics, measurements, and analytics in a flexible manner (i.e., fast and with low overhead). Hence, they facilitate the AI/ML deployments within UE, RAN, WLAN, and CN. To realize SDAC, several new interfaces are defined, including Napp, Nsdac, Nwifi, and N5g. The second idea extends the network data analytics services concept, currently standardized in the 5G Core, into UE, RAN, and WLAN environments. This service expansion unifies the deployment of AI/ML techniques and also the way in which data and analytics should be stored and retrieved within UE, RAN, WLAN and CN. This way, e.g., an SDAC residing at RAN, close to a gNB, can interact with Network Data Analytics Functions (NWDAFs) operating in RAN, UE, and other locations.","PeriodicalId":300165,"journal":{"name":"2022 IEEE Future Networks World Forum (FNWF)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122345149","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}