Dr Rafik Zitouni

The evolution of network technologies has witnessed a paradigm shift toward open and intelligent networks, with the Open Radio Access Network (O-RAN) architecture emerging as a promising solution. O-RAN introduces disaggregation and virtualization, enabling network operators to deploy multi-vendor and interoperable solutions. However, managing and automating the complex O-RAN ecosystem presents numerous challenges. To address this, machine learning (ML) techniques have gained considerable attention in recent years, offering promising avenues for network automation in O-RAN. This paper presents a comprehensive survey of the current research efforts on network automation usingML in O-RAN.We begin by providing an overview of the O-RAN architecture and its key components, highlighting the need for automation. Subsequently, we delve into O-RAN support forML techniques. The survey then explores challenges in network automation usingML within the O-RAN environment, followed by the existing research studies discussing application of ML algorithms and frameworks for network automation in O-RAN. The survey further discusses the research opportunities by identifying important aspects whereML techniques can benefit.

Long Range Wireless Access Network (LoRaWAN) emerged as one of the promising Low Power Wide Area Networks (LPWAN) for IoT applications. It allows end-devices to reach a gateway and then the core network with a star topology in a wide area. Long Range (LoRa) transceivers send data packets according to a configuration or a set of parameter's values: Spreading Factor (SF), Payload size (PS), Bandwidth (BW) and Coding Rate (CR). These parameters must be fixed or adapted to application's requirements. Adaptive Data Rate (ADR) control system of LoRaWAN has been proposed to adapt modulation parameters dynamically based on the recent received packets. However, ADR control system doesn't adjust parameters considering the evolution of applications' Quality of Service (QoS) requirements. In this paper, we propose to cluster a set of LoRa transmission settings based on the measured QoS metrics such as Bit Error Rate (BER), Time on Air (ToA) and Received Signal Strength Indication (RSSI). We consider the set of settings' vectors as a cloud of points in a vector space while measured metrics are points' coordinates. Our method aims to map a set of LoRa transmission settings that offers the same QoS to the same cluster. We generate a set of transmission settings randomly and apply the Fuzzy C-Means (FCM) clustering algorithm on the resulting QoS metrics, Results show that the FCM clustering algorithm attribute membership values that best fit application requirements. This result could be used by LoRaWAN network servers to map each LoRa transmission setting to the application running on end devices.

IEEE 802.11p/bd and 3GPP LTE-Vehicular & 5G NR-V2X technologies counteract the doubly-selectivity properties of wireless vehicular communications thanks to the Orthogonal Frequency Division Multiplexing (OFDM). However, this waveform is the source of adjacent channel interference caused by high out-of-band emissions and luck of spectrum access fairness as well as channel capacity limitations. Filter Bank Multiple Carrier (FBMC) and Universal Filtered Multiple Carrier (UFMC) are efficient waveforms reducing the inter-channel interference for 5G physical layer and beyond. This paper provides simulation measurements of the channel capacity under these waveforms by applying the Non-Orthogonal Multiple Access (NOMA) technology with respect to the 3GPP specifications. The results put in evidence less spurious emission and low Bit Error Probability (BEP) using FBMC compared to both OFDM and UFMC waveforms. The spectral efficiency is enhanced as well, thanks to the combination of NOMA with FBMC. The simulation source code is shared for reproduction and further development.

Underwater wireless localization systems are expensive due to the cost of hydrophones. The method and the architecture of the localization system should be adapted to the environment constraints. This work deals with the trade-off between the affordability and the accuracy of underwater localization. We prototyped our low-cost hydrophone-based beacon location system. Simulation results show that our location precision error is under 1.5 meters in a constrained area at very low cost.

This paper deals with the security issues of IoT networks and particularly with vulnerabilities of Message Queuing Telemetry Transport (MQTT) protocol. We proposed Fuzzing attack techniques to detect new security breaches in MQTT. Fuzz involves the random data generation and transmission to the input of MQTT brokers or clients in order to identify breaches by analyzing their responses. We focus on the development of a containerized test architecture as well as on the generation of scenarios using the Fuzzing. We chose Docker as a container of applications based on a single virtual machine. Through our empirical tests, we found Docker lighter and better efficient than traditional Virtual Machines. We demonstrated that the implementation of a fuzzing technique on Docker within small-scale is efficient to detect a number of MQTT security flaws.

The new era of autonomous vehicles is considered as one of hot topics in Cyber Physical Systems exploration. It uses many sensors and functions to improve vehicle perception. The decision maker offers a flexible way to define the vehicle behaviour whereas the convoy driving mode is one important use case to explore more driving related issues. This paper reports an overview of on-going work on FPGA prototyping to improve the overall speed of the decision-making process and enable the convoy to drive at the higher speed safely. We present a data fusion methodology using heterogeneous Sensors (Lidar & Camera). Our methodology is based on an FPGA approach to speed up the processing time. A prototype has been built to explore new issues and solutions.

Vehicular ad-hoc networks play an important role in providing safety on the road. Vehicles generate and exchange emergency and control messages to avoid dangerous situations. According to IEEE 1609.4 standard, all these messages share the same control channel interval even if the emergency messages are with a highest priority. Besides that, network's characteristics, such as vehicle density and high mobility, would make the diffusion of emergency messages a challenging task. Especially with the absence of acknowledgements and retransmission. Network coding could be seen as a solution where a block of data packets could be sent on the same transmission process. Firstly, we analyze the messages' dissemination, and we propose a thoroughly model for success probability according to the emergency messages' generation probabilities. Further, we propose a new network coding access scheme. The emergency messages take the priority in the channel access and it could be retransmitted several times. Thus, the scheme deals with the emergency messages' loss and latency. NS-3 simulations show that our model increases emergency messages' reliability.

Long Range (LoRa) is a proprietary modulation technique that uses Chirp Spread Spectrum (CSS) modulation for low power and wide area communications. Despite the advantages of LoRa technology, the reconfiguration of transmission parameters such as Spreading Factor (SF) and Transmission Power (Ptx), remains limited to maximize the uplink traffic. In this paper, we look upon additional parameters such as the Bandwidth (BW) and the Coding Rate (CR). We apply Fuzzy C-Means (FCM) algorithm to acquire knowledge about the quality of each transmission setting. Then, we use this knowledge in Q-learning and Markov Decision Process (MDP) algorithms as a state transition matrix to converge better and faster to the set of transmission settings that maximize the uplink data rate. As the solution should cope with different scenarios, we vary the number of End Devices (EDs), Base Stations (BSs), Packet Sizes (PSs) and Packet Rates (PRs). In addition, we compare our solution with many algorithms such as EXP3, ADR and EXPLoRaTS. Simulation results show that MDP with FCM clustering preprocessing improves better several Quality of Service (QoS) metrics including the Data Rate (DR), Packet Delivery Ratio (PDR), Time on Air (ToA) and Transmission Energy (Etx). Thus, the PDR and the DR were improved by 25%, the ToA was reduced by 40% and Etx was reduced by 20%.

Time Slotted Channel Hopping (TSCH) is a new Medium Access Control (MAC) protocol proposed by the IEEE 802.15.4e standard. It is designed to meet the requirements of industrial networks, such as high Packet Delivery Ratio (PDR) and bounded delays, along with low energy consumption. TSCH is now the basis of a full stack for Industrial Internet of Things (IIoT) proposed by the International Engineering Task Force (IETF), known as 6TiSCH (IPv6 over the TSCH mode of IEEE 802.15.4e). Since 6TiSCH networks are expected to offer high performance and fast bootstrapping, the network formation time could be impacted by the network size and the rate of control packets. In this paper, we demonstrate that non cooperative nodes, which can be malicious, could also drastically increase the network joining time. First, we propose the attack model and its implementation on the 6TiSCH simulator. Then, we carry out a set of experiments for different network sizes. Finally, we show through simulation results the impact of the proposed attack on the joining time.

Performance and communication security in the Internet of Things (IoT) area draw a major concern for both academic and industrial communities. Indeed, an emerging number of IoT protocols are getting involved in the protocol stack, implying that the need for new security measures is also increasing. The Media Access Control (MAC) protocol Time Slot Channel Hopping (TSCH) has recently gained significant popularity thanks to its reliability and robustness. It quickly became the basis of IPv6 over the TSCH mode of IEEE 802.15.4e (6TiSCH), a complete communication stack tailored for Industrial IoT networks. In this paper, we are interested in the lack of cooperation of some network nodes, referred to as selfishness, which often leads to network performance degradation. We introduce this concept in 6TiSCH networks for the first time, and we show how they get immunized. We first define a selfishness framework, and we integrate it into the 6top Protocol (6P). Then, we introduce a fuzzy logic-based technique enabling the detection of selfish nodes, along with an anticipatory countermeasure that tells cooperative nodes how to deal with selfish neighbors. We implement and integrate the proposed algorithms into the 6TiSCH simulator, and we conduct a thorough experimental study. Simulation results show how much the latency, Packet Delivery Ratio (PDR), and throughput are affected and how our proposal can significantly improve them.