With the continuous evolution of wireless communication and the explosive growth in data traffic, decentralized spectrum sensing has become essential for the optimal utilization of wireless resources. In this direction, we propose an over-the-air aggregation-based Federated Learning (FL) for a technology recognition model that can identify signals from multiple Radio Access Technologies (RATs), including Wi-Fi, Long Term Evolution (LTE), 5G New Radio (NR), Cellular Vehicle-to-Everything PC5 (C-V2X PC5), and Intelligent Transport Systems G5 (ITS-G5). In the proposed FL-based technology recognition framework, we consider edge network elements as clients to train local models and a central server to create the global model. In each client, a Convolutional Neural Network (CNN)-based model is trained from Inphase and Quadrature (IQ) samples collected from a certain combination of RATs. The possible combination of RATs considered in the clients is selected based on the capabilities of the real-world network elements that can be used as a client. The FL framework involves a process where multiple clients periodically send updates derived from local data to a central server, which then integrates these contributions to enhance a shared global model. This method ensures that the system stays current with the evolving real-world environment while also minimizing bandwidth required for training data transfer and allowing for the maintenance of personalized local models on each client’s end.

Dynamic Spectrum Sharing (DSS) is an enabler for a seamless transition from 4G Long Term Evolution (LTE) to 5G New Radio (NR) by utilizing existing LTE bands without static spectrum re-farming. In this paper, we propose a cross-band DSS scheme that utilizes the Multimedia Broadcast Multicast Service over a Single Frequency Network (MBSFN) feature of an LTE network and the Multicast Broadcast Service (MBS) feature of an NR network. The proposed DSS scheme utilizes LTE and NR resource controllers to assign muted MBSFN subframes on the LTE band and muted MBS subframes on the NR band based on traffic needs. In contrast to the state-of-the-art, the proposed DSS scheme does not require a coordination signaling channel between the LTE and NR networks. Instead, a machine learning-based Technology Recognition and Traffic Characterization (TRTC) system is used to identify and characterize traffic patterns. The LTE and NR resource controllers use the TRTC to sense the muted subframes and offload traffic accordingly.

In the evolving landscape of vehicular networks the need for robust scalable and decentralized learning mechanisms is paramount. This paper introduces a novel Decentralized Federated Learning (DFL) framework for wireless technology recognition in vehicular networks essential for intelligently allocating spectrum resources in multi-Radio Access Technology (multi-RAT) scenarios. In contrast with centralized learning at the base station level our approach leverages Roadside Units (RSUs) for model training and aggregation eliminating central server dependency and enhancing resilience to single points of failure. Each vehicle trains a Convolutional Neural Network (CNN) for wireless technology recognition using the Fourier transform of In-phase and Quadrature (IQ) samples collected from a specific combination of technologies. The proposed frame-work is comprised of two steps. First Centralized Federated Learning (CFL) is employed at the RSU level to create an aggregated model considering the users' connectivity status. Second DFL is utilized to establish a global model at each RSU by sharing models with neighboring RSUs. This approach not only preserves data privacy and security but also optimizes learning by leveraging local computations and minimizing the need for extensive data transmission. Our experimental analysis validates the viability of this approach in providing a scalable and resilient solution for technology recognition in vehicular networks. Our results indicate that DFL surpasses its centralized counterpart by 30% in sparse deployments with low connectivity rates.

The emergence of Time-Sensitive Networking (TSN) has enabled network determinism to a new level, offering high reliability and bounded latency for critical communications. However, the unpredictable nature of traffic generation also poses new challenges to TSN. While TSN is designed to maintain backward compatibility with the 802.1 standards, many end nodes may not be equipped to understand TSN. This can result in a less deterministic TSN, and suboptimal resource utilization, mainly driven by Residual Service Time (RST). To address these challenges, this study proposes three scheduling mechanisms to reduce RST: q-learning, active time slot update, and polynomial forecasting. Real-world data captured from our wireless-TSN (W-TSN) evaluation kit is used to compare the proposed approaches in terms of one-way latency. The results show that the machine learning approach outperforms the other methods in terms of overall latency. However, it is less effective in identifying the optimal time slot position compared to the other methods.

Due to the fast growth of diverse wireless network deployments, the radio spectrum is becoming scarce. Hence, it is beneficial that different radio access technologies share the spectrum in a harmonious way. In this paper, we propose a co-existence scheme between Long Term Evolution (LTE) and Wi-Fi networks that utilizes a Multimedia Broadcast Multicast Service (MBMS) over a Single Frequency Network (MBSFN) feature of an LTE network. MBSFN is an LTE feature that provides support for multicast/broadcast traffic. We propose an adaptive scheme that configures muted subframes, initially intended for MBSFN operation, to allow Wi-Fi transmissions. For the adaptive configuration of muted MBSFN subframes, the LTE eNB uses its traffic queue and the Wi-Fi spectrum occupancy information, which is determined by a convolutional neural network-based technology recognition and traffic characterization system. The standard LTE System Information Blocks are used to convey the updated configuration to the LTE UE. Hence, the proposed coexistence scheme doesn’t require any modifications to a standard MBSFN-compliant LTE UE. Performance analysis is done for various traffic situations, and the results show that muted MBSFN subframe-based coexistence gives a 15% improvement in average aggregated throughput as compared to using Almost Blank Subframe-based coexistence.

The rapid advancement of wireless technologies requires efficient spectrum management considering issues such as interference management and fair coexistence between different technologies. Wireless technology recognition is one of the approaches used to enable intelligent spectrum management. This work proposes a technology classification and traffic characterization system that can recognize and characterize a wide range of wireless technologies that may coexist in the ITS 5.9 GHz band, namely LTE, Wi-Fi, 5G NR, C-V2X PC5, and ITS-G5 technologies. Compared to current state-of-the-art technology recognition solutions, a short time resolution window is selected based on the shortest possible frame duration of the considered technologies. We carried out a “complexity and accuracy trade-off” analysis for six distinct technology recognition models trained and validated at different sampling rates, including 1, 5, 10, 15, 20, and 25 Msps. In addition, the performance of the technology recognition models was evaluated under different channel conditions. For average to high SNR, a less complex CNN model with lower sampling rates (e.g., 5 Msps) can effectively distinguish the signal with 96% classification accuracy. On the other hand, high classification accuracy is obtained using complex, high sampling rate-based CNN models (e.g., 20 Msps) for low (less than 0 dB) SNR channels. A traffic characterization process is also proposed, where the output of the technology recognition is used to identify the traffic characteristics of the technologies in terms of channel occupancy time, transmission pattern, and frame count. The obtained results show that the proposed solution can be used to effectively characterize the identified traffic.

The need for supporting multimedia streaming services in cellular networks as standardized by 3GPP is expanding rapidly. Evolved Multimedia Broadcast Multicast Service (eM-BMS) was initially introduced in Release 9 and following releases have introduced several enhancements. Multimedia Broadcast Multicast Single Frequency Network (MBSFN) is one of the eMBMS enhancements targeting to reduce interference, however, its static parameter configuration yields inefficient resource allocation. Therefore, in this paper, an adaptive demand-driven MBSFN resource allocation algorithm is proposed aiming to efficiently utilize the radio resources. The algorithm flexibly assigns resources to multicast transmissions by varying MBSFN configuration parameters (the number and period of multicast subframes) and provides freed resources to unicast traffic. The proposed algorithm is implemented and evaluated using a Software Defined Radio platform which we made open source. As compared to the fixed MBSFN parameter configuration, our solution showcases an improvement of at least 24% and maximally by 40% in terms of multicast resource efficiency. Also, the total system throughput (multicast and unicast) improves by at least 4% and maximally by 24%.

In future 6G wireless networks, it is important to ensure that equal opportunity is offered to citizens and businesses regardless of location with a dynamic and efficient expansion of the infrastructure. Dynamic coverage and connectivity extension mechanisms exploiting multiple types of Mobile Access Points (MAPs) during a short amount of time for covering areas that cannot be easily reached, are developed by DEDICAT 6G project. This service is called Coverage Extension as a Service (CEaaS). This paper proposes a system architecture for CEaaS and the functionalities that the DEDICAT 6G platform will offer. This includes context awareness (i.e. knowledge about users and technology recognition), coverage extension decision making (i.e. MAP and swarm operation) and network operation decision making (i.e. MAP-user association and radio access technology selection). Furthermore, performance results of DEDICAT 6G framework for CEaaS are presented.

Nowadays, broadband applications that use the licensed spectrum of the cellular network are growing fast. For this reason, Long-Term Evolution-Unlicensed (LTE-U) technology is expected to offload its traffic to the unlicensed spectrum. However, LTE-U transmissions have to coexist with the existing WiFi networks. Most existing coexistence schemes consider coordinated LTE-U and WiFi networks where there is a central coordinator that communicates traffic demand of the co-located networks. However, such a method of WiFi traffic estimation raises the complexity, traffic overhead, and reaction time of the coexistence schemes. In this article, we propose Experience Replay (ER) and Reward selective Experience Replay (RER) based Q-learning techniques as a solution for the coexistence of uncoordinated LTE-U and WiFi networks. In the proposed schemes, the LTE-U deploys a WiFi saturation sensing model to estimate the traffic demand of co-located WiFi networks. We also made a performance comparison between the proposed schemes and other rule-based and Q-learning based coexistence schemes implemented in non-coordinated LTE-U and WiFi networks. The simulation results show that the RER Q-learning scheme converges faster than the ER Q-learning scheme. The RER Q-learning scheme also gives 19.1% and 5.2% enhancement in aggregated throughput and 16.4% and 10.9% enhancement in fairness performance as compared to the rule-based and Q-learning coexistence schemes, respectively.

In the past few years, machine learning (ML) techniques have been extensively applied to provide efficient solutions to complex wireless network problems. As such, Convolutional Neural Network (CNN) and Q-learning based ML techniques are most popular to achieve harmonized coexistence of Wi-Fi with other co-located technologies such as LTE. In the existing coexistence schemes, a co-located technology selects its transmission time based on the level of Wi-Fi traffic generated in its collision domain which is determined by either sniffing the Wi-Fi packets or using a central coordinator that can communicate with the co-located networks to exchange their status and requirements through a collaboration protocol. However, such approaches for sensing traffic status increase cost, complexity, traffic overhead, and reaction time of the coexistence schemes. As a solution to this problem, this work applies a ML-based approach that is capable to determine the saturation status of a Wi-Fi network based on real-time and over-the-air collection of medium occupation statistics about the Wi-Fi frames without the need for decoding. In particular, inter-frame spacing statistics of Wi-Fi frames are used to develop a CNN model that can determine Wi-Fi network saturation. The results demonstrate that the proposed ML-based approach can accurately classify whether a Wi-Fi network is saturated or not.

Recently, the operation of LTE in unlicensed bands has been proposed to cope with the ever-increasing mobile traffic demand. However, the deployment of LTE in such bands implies sharing spectrum with mature technologies such as Wi-Fi. Several studies have discussed this coexistence problem by suggesting that LTE implements different adaptation mechanisms that allow transmission possibilities to Wi-Fi. While such adaptation mechanisms exist, they still negatively impact Wi-Fi performance, mainly due to the lack of collaboration/coordination mechanisms that inform about the co-located networks’ activities. In this paper, we propose a distributed spectrum management framework that enhances the performance of Wi-Fi, as a particular case, by detecting harmful co-located wireless networks and changes the Wi-Fi’s operating central frequency to avoid them. The framework is based on a Convolutional Neural Network (CNN) that can identify different wireless technologies and provides spectrum usage statistics. Experiments were carried out in a real-life testbed, and the results show that Wi-Fi maintains its performance when using our framework. This translates in an increase of at least 40% on the overall throughput compared to a non-managed operation of Wi-Fi.

Recently, the expansion of wireless network deployments is resulting in increased scarcity of available licensed radio spectrum. As the domain of wireless communications is progressing rapidly, many industries are looking into wireless network solutions that can increase their productivity. Private LTE is a promising wireless network solution as it can be customised independently without the control of a mobile network operator while providing reliable and spectrum efficient services. For this reason, the deployment of Private LTE in the unlicensed spectrum and its coexistence with Wi-Fi is becoming a popular topic in research. In this paper, we propose a coexistence scheme for private LTE network in unlicensed spectrum that enables a fair spectrum sharing with co-located Wi-Fi networks. This is achieved by exploiting various LTE frame configurations consisting of different combinations of downlink, uplink, special subframe and muted subframes. The configuration of a single frame is decided based on a rule based algorithm that exploits Wi-Fi spectrum occupancy statistics that is obtained from a technology recognition system which is based on a Convolutional Neural Network. The performance of the proposed private LTE scheme and its coexistence with Wi-Fi is investigated for different traffic scenarios showcasing how the proposed scheme can lead to a harmless coexistence of LTE and Wi-Fi.