This paper presents end-to-end learning from spectrum data—an umbrella term for new sophisticated wireless signal identification approaches in spectrum monitoring applications based on deep neural networks. End-to-end learning allows to: 1) automatically learn features directly from simple wireless signal representations, without requiring design of hand-crafted expert features like higher order cyclic moments and 2) train wireless signal classifiers in one end-to-end step which eliminates the need for complex multi-stage machine learning processing pipelines. The purpose of this paper is to present the conceptual framework of end-to-end learning for spectrum monitoring and systematically introduce a generic methodology to easily design and implement wireless signal classifiers. Furthermore, we investigate the importance of the choice of wireless data representation to various spectrum monitoring tasks. In particular, two case studies are elaborated: 1) modulation recognition and 2) wireless technology interference detection. For each case study three convolutional neural networks are evaluated for the following wireless signal representations: temporal IQ data, the amplitude/phase representation, and the frequency domain representation. From our analysis, we prove that the wireless data representation impacts the accuracy depending on the specifics and similarities of the wireless signals that need to be differentiated, with different data representations resulting in accuracy variations of up to 29%. Experimental results show that using the amplitude/phase representation for recognizing modulation formats can lead to performance improvements up to 2% and 12% for medium to high SNR compared to IQ and frequency domain data, respectively. For the task of detecting interference, frequency domain representation outperformed amplitude/phase and IQ data representation up to 20%.

End-to-End Learning From Spectrum Data: A Deep Learning Approach for Wireless Signal Identification in Spectrum Monitoring Applications

In order to provide meaningful data about spectrum use, occupancy measurements describing the utilization rate of a specific frequency band should be conducted over a specific area instead of a single location. This paper presents a comprehensive methodology for the measurement and analysis of spectrum occupancy. This paper surveys spectrum measurement campaigns and associated interference maps, introducing the latter as a tool for spectrum analysis and management based on measurement data. An interference map characterizes the spectrum use by defining the level of interference over an area of interest in a certain frequency band. Building on findings from practical measurement studies, guidelines for spectrum occupancy measurements are given. While many scientific spectrum occupancy measurement papers tend to be too optimistic about the significance and generality of the results, we propose a cautionary perspective on drawing strong conclusions based on the often limited amount of data gathered. The different phases of the spectrum occupancy measurement and analysis process are described and a thorough discussion of interpolation methods is provided. Means to improve the measurement accuracy are discussed, especially regarding spatial domain considerations and the impact of the sampling interval on the results. A practical example of an improved measurement system design covering all the phases of the measurement process and used at the Turku, Finland; Blacksburg, VA, USA; and Chicago, IL, USA, spectrum observatories is given. Using the improved design, more realistic spectrum occupancy data can be obtained to lay the foundation for spectrum management decisions.

Spectrum Occupancy Measurements: A Survey and Use of Interference Maps

LoRa is a long range, low power, low bit rate, single hop wireless communication technology. It is intended to be used for Internet of Things (IoT) networks, where devices are battery powered and limited bandwidth is needed. In combination with its scalability and the low end device price, LoRa is a candidate technology for low bandwidth industrial applications with a high number of communication devices spread across large areas. The use case for this paper is taken from the flower industry, where a large number of trolleys need to communicate with a server during their movement across the auction floor area. Once trolleys are outside of the auction floor they can use the public LoRaWAN network to communicate with the server, without switching communication technology. The LoRaWAN network consists of multiple end nodes and a single gateway per cell, acting as a transparent bridge between the end nodes and the network server. The measurements show that with a single LoRa gateway we can cover an indoor area of around 34000m2 only with spreading factor 7, while for spreading factor 12 the total covered area will be even higher. Also, the area outside the factory is covered when switching to spreading factor 12. We also show that the number of nodes (trolleys) that can be served by a gateway in such a case can be as high as 6000.

/pdf/lora-indoor-coverage-and-performance-in-an-industrial-1qmntyp2fp.pdf

LoRa indoor coverage and performance in an industrial environment: Case study

Wireless signal recognition plays an important role in cognitive radio, which promises a broad prospect in spectrum monitoring and management with the coming applications for the 5G and Internet of Things networks. Therefore, a great deal of research and exploration on signal recognition has been done and a series of effective schemes has been developed. In this paper, a brief overview of signal recognition approaches is presented. More specifically, classical methods, emerging machine learning, and deep leaning schemes are extended from modulation recognition to wireless technology recognition with the continuous evolution of wireless communication system. In addition, the opening problems and new challenges in practice are discussed. Finally, a conclusion of existing methods and future trends on signal recognition is given.

/pdf/a-survey-on-deep-learning-techniques-in-wireless-signal-4an3o6b3kj.pdf

A Survey on Deep Learning Techniques in Wireless Signal Recognition

The sixth-generation (6G) wireless communication network is expected to integrate the terrestrial, aerial, and maritime communications into a robust network which would be more reliable, fast, and can support a massive number of devices with ultra-low latency requirements. The researchers around the globe are proposing cutting edge technologies such as artificial intelligence (AI)/machine learning (ML), quantum communication/quantum machine learning (QML), blockchain, tera-Hertz and millimeter waves communication, tactile Internet, non-orthogonal multiple access (NOMA), small cells communication, fog/edge computing, etc., as the key technologies in the realization of beyond 5G (B5G) and 6G communications. In this article, we provide a detailed overview of the 6G network dimensions with air interface and associated potential technologies. More specifically, we highlight the use cases and applications of the proposed 6G networks in various dimensions. Furthermore, we also discuss the key performance indicators (KPI) for the B5G/6G network, challenges, and future research opportunities in this domain.

/pdf/the-shift-to-6g-communications-vision-and-requirements-u3ltn2x4jr.pdf

The shift to 6G communications: vision and requirements

Driven by the fast growth of wireless communication, the trend of sharing spectrum among heterogeneous technologies becomes increasingly dominant. Identifying concurrent technologies is an important step towards efficient spectrum sharing. However, due to the complexity of recognition algorithms and the strict condition of sampling speed, communication systems capable of recognizing signals other than their own type are extremely rare. This work proves that multi-model distribution of the received signal strength indicator (RSSI) is related to the signals' modulation schemes and medium access mechanisms, and RSSI from different technologies may exhibit highly distinctive features. A distinction is made between technologies with a streaming or a non-streaming property, and appropriate feature spaces can be established either by deriving parameters such as packet duration from RSSI or directly using RSSI's probability distribution. An experimental study shows that even RSSI acquired at a sub-Nyquist sampling rate is able to provide sufficient features to differentiate technologies such as Wi-Fi, Long Term Evolution (LTE), Digital Video Broadcasting-Terrestrial (DVB-T) and Bluetooth. The usage of the RSSI distribution-based feature space is illustrated via a sample algorithm. Experimental evaluation indicates that more than 92% accuracy is achieved with the appropriate configuration. As the analysis of RSSI distribution is straightforward and less demanding in terms of system requirements, we believe it is highly valuable for recognition of wideband technologies on constrained devices in the context of dynamic spectrum access.

https://biblio.ugent.be/publication/8539090/file/8539091.pdf

Wireless Technology Recognition Based on RSSI Distribution at Sub-Nyquist Sampling Rate for Constrained Devices.

The explosive emergence of wireless technologies and standards, covering licensed and unlicensed spectrum bands, has triggered the appearance of a huge amount of wireless technologies, with many of them competing for the same spectrum band instead of harmoniously sharing it. Unfortunately, the wireless spectrum is a scarce resource, and the available frequency bands will not scale with the foreseen demand for new capacity. Certain parts of the spectrum, in particular the license-free ISM bands, are overcrowded, while other parts, mostly licensed bands, may be significantly underutilized. As such, there is a need to introduce more advanced techniques to access and share the wireless medium, either to improve the coordination within a given band or to explore the possibilities of intelligently using unused spectrum in underutilized (e.g., licensed) bands. Therefore, in this paper, we present an open source software-defined radio-based framework that can be employed to devise disruptive techniques to optimize the sub-optimal use of radio spectrum that exists today. We describe three use cases where the framework can be employed along with intelligent algorithms to achieve improved spectrum utilization. In addition, we provide several experimental results showing the performance and effectiveness of the proposed framework.

https://biblio.ugent.be/publication/8583125/file/8583126.pdf

A Spectrum Sharing Framework for Intelligent Next Generation Wireless Networks

Due to interference between co-located wireless networks, obtaining accurate channel assessment becomes increasingly important for wireless network configuration. This information is used, among others, for cognitive radio solutions and for intelligent channel selection in wireless networks. Solutions such as spectrum analyzers are capable of scanning a wide spectrum range, but are not dedicated for channel occupation assessment because they are extremely costly and not able to perform continuous recording for a time period longer than a few seconds. On the other hand, low-cost solutions lack the flexibility and required performance in terms of configuration and sensing efficiency. To remedy the situation, this paper presents an alternative for channel assessment on top of a commercial software-defined radio platform. Although there exist software solutions for performing spectrum sensing on such platforms, to the best of our knowledge, continuous spectrum sensing and long-term recording remain challenging. We propose a pioneering solution that is capable of seamless spectrum sensing over a wide spectrum band and guarantees sufficient flexibility in terms of configurations. The proposed solution is validated experimentally. We demonstrate two advantages of seamless spectrum sensing: the capability of accurate channel occupancy measurement and detecting transient signals such as Bluetooth.

https://biblio.ugent.be/publication/4192048/file/4192056.pdf

Advanced spectrum sensing with parallel processing based on software-defined radio

Diverse wireless standards, designed for diverse traffic types, operate in the same wireless environment without coordination, often leading to interference and inefficient spectrum usage. Although C-RAN (Cloud/centralized RAN) is a promising architecture to achieve intra-operator network coordination, the architecture encounters challenge when low latency services and diverse access technologies are expected over non-fiber fronthaul. So, multi-standard multi-channel access point with low processing latency is preferred to be at the edge of network instead of central cloud. But, developing this kind of equipment is difficult as multiple radio chips and drivers have to be integrated and coordinated. In ORCA (Orchestration and Reconfiguration Control Architecture) project, a SDR architecture is developed on a single chip radio platform including hardware accelerators wrapped by unified software APIs, which offer the following capabilities: (1) concurrent data transmission over multiple virtual radios; (2) runtime composition and parametric control of radios; and (3) radio resource slicing, supporting independent operation of multiple standards in different bands, time slots or beams. Such an architecture offers a fast development cycle, as only software programming is required for creating and manipulating multiple radios. The architecture further achieves an efficient utilization of hardware resources, as accelerators can be shared by multiple virtual radios.

Radio Hardware Virtualization for Coping with Dynamic Heterogeneous Wireless Environments

Wireless network deployments in industry often grow organically with new technologies added over time, among which many use the non-licensed spectrum to avoid licensing costs. As a result, technologies competing for the same spectrum end up deployed in the same area, causing coexistence problems to manifest themselves at a later stage. To avoid unexpected performance degradation, there is a need to evaluate the impact of additional wireless technologies on an existing network before the actual deployment. This paper proposes to simplify the impact assessment by emulating the signals of the potential wireless network with a single software-defined radio. To evaluate the emulator’s performance, the impact of Bluetooth on Wi-Fi technology is considered as the reference scenario. A series of real-life experiments with configurable traffic load and network scale are conducted to estimate the impact of Bluetooth network on a Wi-Fi link, and the corresponding measurements are repeated with the emulated Bluetooth signals. To the best of the authors’ knowledge, we are the first to propose such a solution, and it is shown that the use of our emulator gives a reliable indication of the expected impact at the location of the Wi-Fi link. As such, this paper provides an important step toward a simple, cost efficient, and reliable solution, to assess the impact of a wireless network prior to its deployment.

Wei Liu

Papers

Wireless Technology Recognition Based on RSSI Distribution at Sub-Nyquist Sampling Rate for Constrained Devices.

A Spectrum Sharing Framework for Intelligent Next Generation Wireless Networks

Advanced spectrum sensing with parallel processing based on software-defined radio

Radio Hardware Virtualization for Coping with Dynamic Heterogeneous Wireless Environments

Assessing the Coexistence of Heterogeneous Wireless Technologies With an SDR-Based Signal Emulator: A Case Study of Wi-Fi and Bluetooth