This paper presents a systematic and comprehensive survey that reviews the latest research efforts focused on machine learning (ML) based performance improvement of wireless networks, while considering all layers of the protocol stack: PHY, MAC and network. First, the related work and paper contributions are discussed, followed by providing the necessary background on data-driven approaches and machine learning to help non-machine learning experts understand all discussed techniques. Then, a comprehensive review is presented on works employing ML-based approaches to optimize the wireless communication parameters settings to achieve improved network quality-ofservice (QoS) and quality-of-experience (QoE). We first categorize these works into: radio analysis, MAC analysis and network prediction approaches, followed by subcategories within each. Finally, open challenges and broader perspectives are discussed.

This paper presents a systematic and comprehensive survey that reviews the latest research efforts focused on machine learning (ML) based performance improvement of wireless networks, while considering all layers of the protocol stack: PHY, MAC and network. First, the related work and paper contributions are discussed, followed by providing the necessary background on data-driven approaches and machine learning to help non-machine learning experts understand all discussed techniques. Then, a comprehensive review is presented on works employing ML-based approaches to optimize the wireless communication parameters settings to achieve improved network quality-of-service (QoS) and quality-of-experience (QoE). We first categorize these works into: radio analysis, MAC analysis and network prediction approaches, followed by subcategories within each. Finally, open challenges and broader perspectives are discussed.

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%.

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.

The future 5G wireless infrastructure will support any-to-any connectivity between densely deployed smart objects that form the emerging paradigm known as the Internet of Everything (IoE). Compared to traditional wireless networks that enable communication between devices using a single technology, 5G networks will need to support seamless connectivity between heterogeneous wireless objects and IoE networks. To tackle the complexity and versatility of future IoE networks, 5G will need to guarantee optimal usage of both spectrum and energy resources and further support technology-agnostic connectivity between objects. One way to realize this is to combine intelligent network control with adaptive software defined air interfaces. In this paper, a flexible and compact platform is proposed for on-the-fly composition of low-power adaptive air interfaces, based on hardware/software co-processing. Compared to traditional Software Defined Radio (SDR) systems that perform computationally-intensive signal processing algorithms in software, consume significantly power and have a large form factor, the proposed platform uses modern hybrid FPGA technology combined with novel ideas such as RF Network-on-Chip (RFNoC) and partial reconfiguration. The resulting system enables composition of reconfigurable air interfaces based on hardware/software co-processing on a single chip, allowing high processing throughput, at a smaller form factor and reduced power consumption.

Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for realtime characterization of the communication performance as observed by the MAC layer. Our approach is data-driven and consists of three steps: extensive experiments for data collection, offline modeling and trace-driven performance evaluation. From our experiments and analysis, we find that a neural networks prediction model shows best performance.

To enhance system performance of future heterogeneous wireless networks the co-design of PHY, MAC, and higher layer protocols is inevitable. In this work, we present WiSCoP - a novel embedded platform for experimentation, prototyping and implementation of integrated cross-layer network design approaches. WiSCoP is built on top of a Zynq hardware platform integrated with FMCOMMS1/2/4 RF front-ends. We demonstrate the flexibility of WiSCoP by using it to prototype a fully standard compliant IEEE 802.15.4 stack with real-time performance and cross-layer integration.

Data science or “data-driven research” is a research approach that uses real-life data to gain insight about the behavior of systems. It enables the analysis of small, simple as well as large and more complex systems in order to assess whether they function according to the intended design and as seen in simulation. Data science approaches have been successfully applied to analyze networked interactions in several research areas such as large-scale social networks, advanced business and healthcare processes. Wireless networks can exhibit unpredictable interactions between algorithms from multiple protocol layers, interactions between multiple devices, and hardware specific influences. These interactions can lead to a difference between real-world functioning and design time functioning. Data science methods can help to detect the actual behavior and possibly help to correct it. Data science is increasingly used in wireless research. To support data-driven research in wireless networks, this paper illustrates the step-by-step methodology that has to be applied to extract knowledge from raw data traces. To this end, the paper (i) clarifies when, why and how to use data science in wireless network research; (ii) provides a generic framework for applying data science in wireless networks; (iii) gives an overview of existing research papers that utilized data science approaches in wireless networks; (iv) illustrates the overall knowledge discovery process through an extensive example in which device types are identified based on their traffic patterns; (v) provides the reader the necessary datasets and scripts to go through the tutorial steps themselves.

Software defined radio (SDR) technology enables implementation of wireless devices that support multiple air-interfaces and modulation formats, which is very important if consider proliferation of wireless standards. To enable such functionality SDR is using reconfigurable hardware platform such as Field Programmable Gate Array (FPGA). In this paper, we present design procedure and implementation result of SDR based QPSK modulator on Altera Cyclone IV FPGA. For design and implementation of QPSK modulator we used Altera DSP Builder Tool combined with Matlab/Simulink, Modelsim and Quartus II design tools. As reconfigurable hardware platform we used Altera DE2-115 development and education board with AD/DA daughter card. Software and Hardware-in-the-loop (HIL) simulation was conducted before hardware implementation and verification of designed system. This method of design makes implementation of SDR based modulators simpler ad faster.