Deep Reinforcement Learning Paradigm for Dense Wireless Networks in Smart Cities

More and more devices, such as Bluetooth and IEEE 802.15.4 devices forming Wireless Personal Area Networks (WPANs) and IEEE 802.11 devices constituting Wireless Local Area Networks (WLANs), share the 2.4 GHz Industrial, Scientific and Medical (ISM) band in the realm of the Internet of Things (IoT) and Smart Cities. However, the coexistence of these devices could pose a real challenge—co-channel interference that would severely compromise network performances. Although the coexistence issues has been partially discussed elsewhere in some articles, there is no single review that fully summarises and compares recent research outcomes and challenges of IEEE 802.15.4 networks, Bluetooth and WLANs together. In this work, we revisit and provide a comprehensive review on the coexistence and interference mitigation for those three types of networks. We summarize the strengths and weaknesses of the current methodologies, analysis and simulation models in terms of numerous important metrics such as the packet reception ratio, latency, scalability and energy efficiency. We discover that although Bluetooth and IEEE 802.15.4 networks are both WPANs, they show quite different performances in the presence of WLANs. IEEE 802.15.4 networks are adversely impacted by WLANs, whereas WLANs are interfered by Bluetooth. When IEEE 802.15.4 networks and Bluetooth co-locate, they are unlikely to harm each other. Finally, we also discuss the future research trends and challenges especially Deep-Learning and Reinforcement-Learning-based approaches to detecting and mitigating the co-channel interference caused by WPANs and WLANs.

The IEEE 802.11ax high-efficiency wireless local area network (HEW) is promising as a foundation for evolving the fifth-generation (5G) radio access network on unlicensed bands (5G-U). 5G-U is a continued effort toward rich ubiquitous communication infrastructures, promising faster and reliable services for the end user. HEW is likely to provide four times higher network efficiency even in highly dense network deployments. However, the current wireless local area network (WLAN) itself faces huge challenge of efficient radio access due to its contention-based nature. WLAN uses a carrier sense multiple access with collision avoidance (CSMA/CA) procedure in medium access control (MAC) protocols, which is based on a binary exponential backoff (BEB) mechanism. Blind increase and decrease of the contention window in BEB limits the performance of WLAN to a limited number of contenders, thus affecting end-user quality of experience. In this paper, we identify future use cases of HEW proposed for 5G-U networks. We use a self-scrutinized channel observation-based scaled backoff (COSB) mechanism to handle the high-density contention challenges. Furthermore, a recursive discrete-time Markov chain model (R-DTMC) is formulated to analyze the performance efficiency of the proposed solution. The analytical and simulation results show that the proposed mechanism can improve user experience in 5G-U networks.

It is difficult for wireless local area networks (WLANs), IEEE 802.11ax high-efficiency WLAN (HEW), to join next-generation innovations such as 5th generation (5G) and Internet of Things (IoT) because they still have their conventional channel access mechanism as their essential medium access control (MAC) protocol. The MAC protocol uses a traditional binary exponential backoff (BEB) algorithm to access channel resources that depend on the noncognitive increment of contention parameters for collision avoidance. In BEB, the collision issue increases with the increase in connected devices in the network due to a fixed contention window size. The larger the size of the network, the larger the collision in the network. To avoid such a circumstance, in this paper, we propose a sliding group window (sGW) mechanism dependent on collision-point assessment in order to improve the performance of MAC protocol for HEW. The proposed algorithm additionally presents a rebacking off for collision avoidance (ReBOCA) system for sGW, which combines the uniform dispersion of the contention parameters. This variation of an ordinary backoff algorithm permits the reasonable sliding of the user groups in the case of collision. The algorithm explicitly accounts for the peculiarities of dense environments and backward compatibility. Key aspects of the proposed solution include collision-point estimation, rebacking off for collision distribution convergence for fair treatment, and adaptive sliding of group windows to mitigate contention unfairness. We further formulated a closed-form Markov chain model for the performance analysis of our proposed sGW with ReBOCA scheme. Theoretical and practical results prove that our proposed scheme achieved maximal efficiency, even under dense environments. An increase in throughput with a lower packet collision probability was achieved with the proposed mechanism, and the efficiency increased as the number of contending stations increased than compared to traditional BEB performance. Our proposed ReBOCA mechanism enhanced network throughput by 38.18% than compared to the conventional BEB mechanism.

In future's high density Wireless Local Area Networks (WLANs), to improve the overall throughput, we envision the optimization of the MAC protocols and mechanisms. Traditionally, it's clear in the literature that Transmit Power Control (TPC) is chosen as one of the most powerful tools for optimizing MAC protocols. However, the TPC is not always possible to implement due to hardware and licensing limitations on one hand, and on the other, its unbalanced use results in starvation situations. In the same context, the Clear Channel Assessment (CCA) threshold adaptation is proving its effectiveness. This adaptation is preferable to TPC that behaves aggressively towards transmitters having lower transmit power. In this paper we show that CCA adaptation mechanism may be used effectively to optimize the spatial reuse in dense WLAN deployments. For a dense IEEE 802.11n network topology, our simulations show a global gain of 190% in aggregate throughput compared to the current bound assumed by the present MAC protocol.

The idea of smart and sustainable cities is incomplete without using information and communication technologies. Wireless Local Area Network (WLAN) plays a vital role in connecting different services, transferring data and providing indoor localization. WLAN fingerprinting technique has become the most common approach for indoor localization in smart cities. This technique utilizes received signal strength (RSS) and channel status from the installed WLAN Access Points (AP). Currently, WLAN planning relies on the site survey, which is laborious and uneconomical for large areas. The WLAN has a limited number of channels assigned in the frequency reuse strategy. An inefficient channel assignment strategy will lead towards increased interference, thus degrading the overall service. This paper proposes a WLAN channel assignment strategy for large and crowded indoor areas. The proposed scheme assigns the channels to installed APs for indoor localization in fingerprinting framework. The proposed technique ensures that the proposed AP channel assignment algorithm in our network-planning scheme mitigates interference.

Currently, Internet of Things (IoT) has become common in various applications, including smart factories, smart cities, and smart homes. In them, wireless local-area networks (WLANs) are widely used due to their high-speed data transfer, flexible coverage ranges, and low costs. To enhance the performance, the WLAN configuration should be optimized in dense WLAN environments where multiple access points (APs) and hosts exist. Previously, we have studied the active AP configuration algorithm for dual interfaces using IEEE802.11n and 11ac protocols at each AP under non-channel bonding (non-CB). In this paper, we study the algorithm considering the channel bonding (CB) to enhance its capacity by bonding two channels together. To improve the throughput estimation accuracy of the algorithm, the reduction factor is introduced at contending hosts for the same AP. For evaluations, we conducted extensive experiments using the WIMENT simulator and the testbed system using Raspberry Pi 4B APs. The results show that the estimated throughput is well matched with the measured one, and the proposal achieves the higher throughput with a smaller number of active APs than the previous configurations.

Despite unprecedented advancements, wireless local area network (WLAN) technologies for the Internet of Things (IoT), such as IEEE 802.11ah (i.e., WiFi-HaLow), are prone to serious security threats, owing to their constrained computational and memory resources, which limit the use of heavyweight intrusion protection and security protocols. To address this problem, security administrators (sec-admins) must perform regular and comprehensive vulnerability assessments of IoT devices. An Internet-wide port scan (IWPS) is the initial step. However, the medium access control mechanism of IEEE 802.11ah, designed specifically for heterogeneous IoT traffic and low-power operations, can degrade network performance in the case of traditional port-scan traffic. Moreover, Internet-security (IPSec) protocol support is mandatory for IPv6-enabled IoT devices to ensure data confidentiality, integrity, and availability. Although the objective of a port scan is to improve IoT security, the resultant network performance can adversely affect IPSec services. Therefore, in this study, we optimize the IWPS to maximize the IoT security over IEEE 802.11ah WLAN. To this end, we propose novel mathematical models to evaluate IoT security based on port-scan network performance and IPsec services, which derives an optimal scan rate for sec-admins. The effectiveness of the proposed framework is verified by comprehensive numerical analysis, which shows that our approach minimizes the risk to IoT devices while probing them at an optimal scan rate.

This paper presents the design and implementation of a novel four‐port multiple input multiple output (MIMO) antenna with reconfigurable filtering characteristics. The proposed filtering MIMO antenna is constructed using a super wideband (SWB) monopole. The feedline of the monopole radiator is integrated with a microstrip filter network. Reconfigurable filtering characteristics are realized using a feed selection network making the antenna work at two modes viz. SWB mode (2.2 to over 20 GHz) and dual narrow‐band (d‐NB) mode (2.45 and 5.8 GHz). The feed selection is accomplished using a PIN diode. An interlocked four‐port MIMO antenna is then constructed using the proposed reconfigurable filtering monopole antenna. The proposed antenna exhibits an average gain greater than 5.2 dBi in both operating modes and has total efficiency greater than 80%. The MIMO parameters such as envelope correlation coefficient (ECC), diversity gain (DG), and mean effective gain (MEG) are evaluated and presented. The prototype MIMO antenna is fabricated and the experimental results are validated in real‐time. The proposed reconfigurable MIMO antenna is suitable for wireless local area network (WLAN), Internet of things (IoT), dedicated short‐range communication (DSRC), ultra‐wideband (UWB), and SWB applications in the automotive scenario.

Wireless Local Area Networks (WLANs), particularly Wi-Fi, serve as the backbone of modern connectivity, supporting billions of devices globally and forming a critical component in Internet of Things (IoT) ecosystems. However, the increasing ubiquity of WLANs also presents an expanding attack surface for adversaries—especially Advanced Persistent Threats (APTs), which operate with high levels of sophistication, resources, and long-term strategic objectives. This paper provides a holistic security analysis of WLANs under the lens of APT threat models, categorizing APT actors by capability tiers and examining their ability to compromise WLANs through logical attack surfaces. The study identifies and explores three primary attack surfaces: Radio Access Control interfaces, compromised insider nodes, and ISP gateway-level exposures. A series of empirical experiments—ranging from traffic analysis of ISP-controlled routers to offline password attack modeling—evaluate the current resilience of WLANs and highlight specific vulnerabilities such as credential reuse, firmware-based leakage, and protocol downgrade attacks. Furthermore, the paper demonstrates how APT resources significantly accelerate attacks through formal models of computational scaling. It also incorporates threat modeling frameworks, including STRIDE and MITRE ATT&CK, to contextualize risks and map adversary tactics. Based on these insights, this paper offers practical recommendations for enhancing WLAN resilience through improved authentication mechanisms, network segmentation, AI-based anomaly detection, and open firmware adoption. The findings underscore that while current WLAN implementations offer basic protections, they remain highly susceptible to well-resourced adversaries, necessitating a shift toward more robust, context-aware security architectures.

Over the last decade, increasing availability of Internet of Things (IoT) devices and broadband communications technologies has enabled a number of smart applications in many cities. Among various smart city applications, a smart street lighting application is considered as one of the most cost-effective choices for a smart city today, if relying on existing street lights that are already deployed and networked across a city. Piggy-bagging on a readily available networked street lighting infrastructure, several city-wide services can be offered rapidly and cost effectively. Examples of additional devices that can be deployed along with networked street lights are such as environmental sensors, traffic sensors, IP cameras, digital signage, and more. To enable connections among different sensing and control devices, communication technologies and networks are of crucial components. There are a wide variety of communication technologies that can be used, namely, Sigfox, long range (LoRa), Weightless, Symphony Link, random phase multiple access (RPMA), narrowband IoT (NB-IoT), long-term evolution category 0/1/M (LTE category 0/1/M), power line communications (PLC), ZigBee, IPv6 low-power wireless personal area network (6LoWPAN), wireless local area network (WLAN), wireless mesh, worldwide interoperability for microwave access (WiMAX), and Cellular (2G/3G/ 4G/5G). The chapter aims at providing a comprehensive discussion of various communication technologies that can serve smart street lighting and other add-on applications in a smart city. These technologies are evaluated on the basis of communication network requirements of different applications pertaining to their data rate, latency, reliability, and security.

In recent years, the widespread deployment of the Internet of Things (IoT) applications has contributed to the development of smart cities. A smart city utilizes IoT-enabled technologies, communications and applications to maximize operational efficiency and enhance both the service providers’ quality of services and people’s wellbeing and quality of life. With the growth of smart city networks, however, comes the increased risk of cybersecurity threats and attacks. IoT devices within a smart city network are connected to sensors linked to large cloud servers and are exposed to malicious attacks and threats. Thus, it is important to devise approaches to prevent such attacks and protect IoT devices from failure. In this paper, we explore an attack and anomaly detection technique based on machine learning algorithms (LR, SVM, DT, RF, ANN and KNN) to defend against and mitigate IoT cybersecurity threats in a smart city. Contrary to existing works that have focused on single classifiers, we also explore ensemble methods such as bagging, boosting and stacking to enhance the performance of the detection system. Additionally, we consider an integration of feature selection, cross-validation and multi-class classification for the discussed domain, which has not been well considered in the existing literature. Experimental results with the recent attack dataset demonstrate that the proposed technique can effectively identify cyberattacks and the stacking ensemble model outperforms comparable models in terms of accuracy, precision, recall and F1-Score, implying the promise of stacking in this domain.

Wireless networks have a key role in operational deployment, mobility, the flexibility of network organization and the variety of possible applications, in many cases being the only economically justified solution. Based on the above, for the deployment of wireless networks, the correct theoretical design of the wireless network is an important issue: the required number of devices, their characteristics, placement, energy characteristics of channels, distribution routes and coverage areas, etc. Correct theoretical analysis will ensure error-free construction of the network for the successful implementation of the tasks and will not lead to the need to attract additional material costs. One of the key tasks of wireless communication construction is a reliable assessment of the energy characteristics of a wireless communication channel. Modern global manufacturers of telecommunications equipment build both backbone equipment and equipment to cover WLAN (wireless local area networks) areas, based on IEEE 802.11 standards. One of the most modern standards of the IEEE 802.11 group is the IEEE 802.11ac standard, which is characterized by several improved technical characteristics compared to its predecessor IEEE 802.11n and older versions. That is why the task of evaluating the performance of modern wireless communication equipment based on IEEE 802.11ac standards and analyzing the evaluation of the energy characteristics of the communication channel to predict the parameters and performance characteristics of a point-to-point, point-to-multipoint or other wireless transmission systems within a certain wireless communication network. The following results of solving this problem are presented in this paper: – theoretical evaluation of the energy characteristics of the wireless communication channel. – laboratory studies of wireless communication equipment of the 802.11ac standard based on simulating a communication line using attenuators. – verification of the results of laboratory studies in field conditions based on the model for assessing the quality of communication in a wireless channel created based on the 802.11ac standard.

In this paper, the performance of carrier sense multiple access with collision avoidance (CSMA/CA) based multi-user MIMO (MU-MIMO) uplink wireless local area networks (WLANs) is analysed. Analytical models are provided to compute the throughput of each user and the total energy consumption in a WLAN with a single user MIMO (SU-MIMO) technique as well as a MU-MIMO technique. By means of the analytical models, the throughput, fairness and energy consumption performances are studied for several WLAN scenarios. The numerical results show that the MU-MIMO technique provides higher throughput than the SU-MIMO technique only when the number of MIMO communication antennas is high and the medium access parameters of the users are configured properly. Further, the SU-MIMO technique is found to be more energy efficient than the MU-MIMO technique. However, the MU-MIMO technique provides better fairness over the SU-MIMO technique.

The advent of 5G technology has revolutionized wireless communication, offering unprecedented data rates, reduced latency, and enhanced connectivity. A critical component driving these advancements is Multiple-Input Multiple-Output (MIMO) technology. MIMO utilizes multiple antennas at both the transmitter and receiver ends to improve communication performance. In the context of the Internet of Things (IoT), MIMO plays a pivotal role in enhancing network efficiency, reliability, and capacity and can improve system capacity and reduce interference between different users. By leveraging MIMO, IoT devices can achieve higher data throughput and better signal quality, even in challenging environments. This is particularly important for IoT applications that require real-time data transmission and low latency, such as smart cities, autonomous vehicles, and industrial automation. Additionally, MIMO technology helps in mitigating interference and improving spectrum utilization, making it an essential enabler for the massive connectivity demands of IoT networks in the 5G era. However, due to the high channel dimension, complex channel estimation and precoding algorithms in the system, the system hardware and software overhead will increase. The precoding algorithms of massive MIMO systems are divided into three types: digital, analog and hybrid. The three types of precoding algorithms are summarized and compared, and the advantages and disadvantages of different precoding algorithms and applicable scenarios are summarized. The channel estimation schemes are divided into training estimation and blind estimation, and the advantages and disadvantages of the two types of schemes are summarized. It is pointed out that the reasonable use of the channel sparsity of massive MIMO can improve the quality of channel estimation and reduce the estimation overhead.

Nowadays, interest for compatible simulators with high flexibility to explore the performance of Wireless Local Area Networks (WLANs) is definitely increasing. One of the main reasons of such interest is the upcoming 5G technology, related to the Internet-of-Things (IoT). In this paper, we present a MATLAB-based link-level simulator for WLAN with still used (IEEE 802.11g/n/ac) and upcoming (IEEE 802.11ah/af) technologies. Realization of the whole WLAN link-level simulator is highly inspired by the recognized Vienna LTE-simulator. As a result, it is possible to join together these simulators to explore the performance of WLAN and LTE, operating in the same radio frequency (RF) band. From the point of future 5G based cellular networks, such exploring is important because different coexistence scenarios can occur between wireless communications systems in the ISM and UHF bands.