Machine learning (ML) has emerged as a promising avenue for enhancing the efficiency and intelligence of channel allocation processes. However, deploying ML algorithms on resource-constrained edge devices poses significant challenges due to their limited computational capabilities and storage capacities. In this study, we propose leveraging tiny ML (TinyML) techniques to address these challenges and optimize channel allocation within long range wide area network (LoRaWAN) deployments. Our key innovation lies in replacing traditional random channel allocation methods with TinyML-based approaches, wherein each edge device autonomously utilizes TinyML to select the most efficient channel prior to each uplink transmission. Furthermore, we conduct comprehensive comparisons between TinyML and conventional channel allocation techniques implemented on edge devices. Through extensive simulations, our results demonstrate that TinyML outperforms existing channel allocation mechanisms in terms of packet success ratio (PSR). Notably, when evaluating TinyML against conventional ML approaches in terms of model size and inference time, TinyML exhibits superior performance without compromising efficiency.

The connected and autonomous vehicles combined with deep reinforcement learning (DRL) are capable of handling complex driving scenarios. However, due to the random exploration feature of reinforcement learning (RL), unexpected actions and collisions that would be inevitable in the real world occur during training, resulting in property damage, injury, and loss of life. To address this issue, in this article, we propose a sophisticated safe DRL in autonomous lane changing that benefits from both exploration and optimization capabilities. The key idea is first to integrate the safety constraints into the RL algorithm to limit the actions that the agent can take during training, which is implemented by designing a vehicle convex occupancy approximation to estimate the candidate action set. Then, adaptive exploration strategies are used, in which an imaginary environment based on domain randomization is built to explore areas of the action–state space where it is uncertain about the outcomes. We present a Monte Carlo tree search to replace unsafe with safe action. The twin-delayed deep deterministic policy gradient is used as the RL algorithm to train action space agents. Experimental results show that our proposed framework significantly enhances safety during the lane-change process with faster and more stable learning than the other methods.

Zero-shot learning (ZSL) typically suffers from the domain shift issue since the projected feature embedding of unseen samples mismatch with the corresponding class semantic prototypes, making it very challenging to fine-tune an optimal visual-semantic mapping for the unseen domain. Some existing transductive ZSL methods solve this problem by introducing unlabeled samples of the unseen domain, in which the projected features of unseen samples are still not discriminative and tend to be distributed around prototypes of seen classes. Therefore, how to effectively align the projection features of samples in unseen classes with corresponding predefined class prototypes is crucial for promoting the generalization of ZSL models. In this paper, we propose a novel Iterative Class Prototype Calibration (ICPC) framework for transductive ZSL which consists of a pseudo-labeling stage and a model retraining stage to address the above key issue. First, in the labeling stage, we devise a Class Prototype Calibration (CPC) module to calibrate the predefined class prototypes of the unseen domain by estimating the real center of projected feature distribution, which achieves better matching of sample points and class prototypes. Next, in the retraining stage, we devise a Certain Samples Screening (CSS) module to select relatively certain unseen samples with high confidence and align them with predefined class prototypes in the embedding space. A progressive training strategy is adopted to select more certain samples and update the proposed model with augmented training data. Extensive experiments on AwA2, CUB, and SUN datasets demonstrate that the proposed scheme achieves new state-of-the-art in the conventional setting under both standard split (SS) and proposed split (PS).

The integration of software-defined networking (SDN) into legacy networks causes both operational and deployment issues. In this context, this article proposes a novel approach, called An Intelligent Solution for Improved Performance of Reliable and Time-sensitive Flows in hybrid SDN-based fog computing IoT systems (IHSF). The proposed IHSF approach has three solutions: 1) a novel algorithm to deploy SDN switches between legacy switches to improve network observability; 2) a ${K}$ -nearest neighbor regression algorithm to predict in real time the reliability of legacy links at the SDN controller based on historic data; this enables the SDN controller to make timely decisions, improving system performance; and 3) a reliable and time-sensitive deep deterministic policy gradient algorithm (RT-DDPG), which optimally computes forwarding paths in hybrid SDN-F for time-critical traffic flows generated by IoT applications. The simulation results show that our proposed IHSF solution has a better performance than the existing approach in terms of network observability time, number of disturbed flows, end-to-end delay, and packet delivery ratio.

In this article, we study the co-channel problem in the 2-tier architecture of vehicular networks [i.e., vehicle-to-vehicle (V2V) communication and vehicle-to-infrastructure (V2I) communication]. The communication technology we consider here is dedicated to short-range radio communication (DSRC), cellular vehicle-to-everything (C-V2X), or a hybrid of both. The V2I communication will interfere V2V communication, and vice versa, because the roadside unit (RSU) cannot sense V2V communication during the downlink period when the V2V communication is in the coverage of RSU. We note that V2V communication will have higher priority since it conveys critical messages for road safety in connected and automated vehicle (CAV) systems. We propose a p-opportunity channel access scheme (p-OCAS) for the RSU to solve the problem. Simulation results validate the correctness of the analytical model. The investigation showed that p-OCAS can substantially minimize the interference from RSU to V2V communications according to the V2V session arrival rate to automated vehicles as well as maintain a high throughput of RSU.

Due to the random access (RA) process, machine-type communication (MTC) devices of a group may delay until the time point of the next polling of another groups and lead to a serious access delay problem. To solve this problem, in this paper, we investigate a dynamic backoff indicator (BI) assignment (DBA) algorithm that lets the delayed MTC devices speed up to finish their RA within an expected period of time. The proposed method also realizes the crucial concept of cyber-physical systems (CPS). Simulation results and analyses validate the effects of CPS on reducing collision probability in large-scale MTC.

Group paging is one of the solutions proposed to deal with the radio access network (RAN) overload problem resulted from bursty machine-type communications (MTC) traffic in long-term evolution-advanced (LTE-A) networks. In group paging, the base station normally reserves a fixed amount of random access opportunities (RAOs) for the grouped users to perform random access (RA) during a paging access interval. However, the number of contending users is quickly decreased and thus, static allocation of RAOs is not efficient. This paper presents a dynamic resource allocation (DRA) scheme which dynamically adjusts the reserved RAOs for group paging based on the estimated number of contending users in each RA slot. Simulation results demonstrate that, compared with the traditional static allocation scheme, the proposed DRA scheme can improve the utilization of RAOs by 9% under a target access success probability constraint of 90%.

Simultaneous channel accesses from mass machine-type communications (MTC) devices may congest the random-access channels (RACHs) of LTE-A networks. Currently, 3GPP selects extended access barring (EAB) mechanism as the baseline solution to relieve the congestion of RACHs by barring low-priority devices. Different settings of EAB parameters may re-shape the arrival process of MTC traffic and thus, lead to unpredictable performance. This paper presents an analytical model to investigate the performance of the EAB algorithm on the RACHs in LTE-A networks. Computer simulations were conducted to verify the accuracy of the analysis. The optimal values of paging cycle and repetition period of system information block type 14 (SIB14) can then be obtained from the analytical model subject to a target quality-of-service (QoS) constraint.

The mobile wireless metropolitan area networks (WMAN) architecture adopts power saving mechanism to prolong the battery lifetime of mobile devices. Due to the burst characteristic of non-real-time service, the exponentially growing sleep window, which is employed in the IEEE 802.16e and IEEE 802.16m, seems not the best approach in term of packet response time. To let the sleep window match the traffic pattern, base station (BS) should collect traffic information and then notify mobile station (MS) the appropriate sleep window size. As a solution, we propose an advanced power saving mechanism, namely A-PSM, which simply adjusts the sleep window according to the average packet inter-arrival time in order to improve the power saving capability. To reduce the negotiation overhead and accomplish the synchronization of sleep pattern between BS and MS, the information of measured inter-packet arrival time is piggybacked on every downlink packet sent from BS. Moreover, a parameter of tolerable delay is proposed to control the packet delay when the inter-packet arrival time suddenly becomes longer. As confirmed by the performance evaluation, the proposed A-PSM can easily achieve better power saving capability, as compared to the IEEE 802.16e and IEEE 802.16m under all kinds of traffic arrival rates.

We propose a new centralized power control scheme for closed access femtocell networks. Since femto base station (FBS) can be deployed unpredictably in a macro cell area, interference to macro subscribers and interference between FBS in downlink (DL) cause a transimit problem. In this paper, we describe the system model using a noncooperative game model.We formulate a utility function to provide FBS proper power strength and to minimize interference. Our power control algorithm based on the game model can be applied to the centralized environment. This novel power control algorithm leads transmission power to reach a steady state condition, i.e. Nash Equilibrium (NE). Through mathematical analysis and numerical results, we show that our proposed power control algorithm has several good characteristics.

A multi-hop mobile ad hoc network (MANET) is generally configured as a peer-to-peer network with no centralised hubs or controllers that coordinate channel resources. Nodes in a MANET usually equip one single transceiver for data transmissions. However, the single transceiver architecture will cause a difficulty of being implemented in multichannel environment if the network transmission capacity would be improved by adopting parallel multichannel access. To solve this thorny problem, this study presents a distributed medium access control (MAC) layer protocol called ad hoc multichannel negotiation protocol (AMNP) for multichannel transmissions in the multi-hop MANET. Additionally, two problems, the multichannel hidden terminal problem and the multichannel broadcast transmission problem, caused by single transceiver operations in the multichannel environment, which have not been revealed in academia, is presented and solved in this study. Finally, an enhanced AMNP with channel scheduling (AMNP/s) scheme is introduced to improve the channel utilisation. The author show, via simulations, that AMNP/s provides a higher throughput compared to its single-channel counterpart by promoting simultaneous transmissions in different channels. Simulation results also show that AMNP/s derives higher performance than other multichannel transmission schemes that use multiple transceivers.

The most challenging technical issue in worldwide interoperability for microwave access (WiMAX) networks is to find a way to counteract the interference as well as to solve the fading problem in transmissions. Although IEEE 802.16e standard proposes several mechanisms to handle this difficult problem, there are still many external interferences that may collapse ongoing transmissions. To tackle this thorny problem, the authors develop a method called fault-tolerant transmission mechanism (FTM), which re-permutes and scatters slots in each frame space of the downlink transmission in the medium access control (MAC) layer to achieve a higher probability of success in transmissions. FTM can produce approximately 30% more throughput than the IEEE 802.16 standard can and significantly raise the successful transmission probability, while having each transmitted burst size limited to no more than 20 slots (5% of the total downlink frame space). Therefore by adjusting the burst size, rearranging slot places and comparing their patterns, FTM can provide a more reliable, more secure and more efficient transmission mechanism than IEEE 802.16e transmission mechanism. In addition, it is fully compatible with orthogonal frequency-division multiple access (OFDMA) WiMAX systems.

Due to the strict time constraints, the real-time services for multimedia applications in wireless networks are difficult to deal with as a packet scheduler schedules the related packets. The system performance of a base station (BS) mainly also depends on the packet scheduler policy. So far as our knowledge, the relatively existing packet scheduler schemes arrange the packets based on the corresponding delay time requirements for improving throughput or reducing dropping rate, not focus on deliberating how to reduce the delay time of packets efficiently as an important purpose. From this perspective, we have proposed our downlink delay-minimized scheduling (DDMS) algorithm for reducing the corresponding delay time for mobile stations (MSs) as our main contribution plus improves system throughput of the BS. Simulation results reveal that our DDMS algorithm outperformed in the reducing delay time, throughput and dropping rate by comparing with the other real-time polling service schemes.

The most challenging issue in worldwide interoperability for microwave access network technologies is to find a way to counteract the interference as well as solve the fading problems in transmission. Although IEEE 802.16e standard is proposed to tackle this difficult problem, there are still many e

According to the property of different modulations, the wireless ad hoc network can be treated as a new type of network named multi-rate/multi-range wireless network (M2WN). By the property of M2WN, this paper proposes a new multicast routing protocol, named as multi-rate/multi-range multicast routing protocol (M3RP), to reduce the end-to-end transfer delay as well as to reduce the network resource consumption. Simulation results show that M3RP can achieve higher packet delivery ratio, lower network resource consumption, and lower average end-to-end transfer delay than the conventional minimum-hops approach with fixed data rate especially in heavy traffic load.

This paper analyzes the characteristics of time division multiple access (TDMA) scheme to improve the performance of data transmissions in wireless networks. After analyzing these characteristics, we design an efficient medium access control (MAC) mechanism based on our analysis. Because of the variable characteristics of TDMA we analyzed, we could get a time slot period to achieve the system throughput more optimal. Our proposed protocol is based on our analysis and schedule with a carefully computation. The slot(s) can be divided into several minislots as the contention interval which is used by subscribers to transmit the control packets to base station. We conclude with an approximate optimal throughput through our MAC mechanism.

Using time division multiple access (TDMA) scheme to access the shared medium in communication systems has been well studied in literature. The major problems of TDMA system are how to efficiently schedule the time slots for nodes so that fit their actual needs of bandwidth and how to allocate an adequate time period for data transmissions according to the varied amount of traffic by time. Recently many TDMA schemes had been proposed such as the topology-unaware TDMA method, which uses the probabilistic method to access medium, to enhance the performance of TDMA system. However, this method would lead to heavy collisions while the traffic load and the neighbors are increasing accordingly. To tackle this drawback, we propose a stealing-TDMA (sTDMA) protocol using ACK mechanism to reserve time slots for solving collision problems. The performance analysis shows the significant improvements in reducing collision probability and power saving.

The radio spectrum of the IEEE 802.16 medium access control (MAC) protocol ranges from 2 to 66 GHz, which is one of the potential solutions for broadband wireless access (BWA) or beyond third generation (B3G)/4G networks. However, with the characteristic of radio propagation, the maximum transmission distance is proportioned inversely to the frequency which the subscriber station (SS) carries. According to this property, the base station (BS) can easily allocate appropriate channels for SSs according to the received signals which SSs transmit. Therefore, in this paper, we investigate the relationship between the signal propagation and the distance, and then we proposed a novel macrocell channel allocation scheme (MCAS) for dynamic channel allocation (DCA) in radio access networks (RAN). The MCAS enables the BS to allocate appropriate channels to SSs according to the received signal-to-noise ratio (SNR) value from the SSs. The MCAS not only increases the capacity of the system but also saves the overall power consumption of the system well. Simulation results show that the proposed MCAS increases the power saving up to 47.83% over the original IEEE 802.16 standard specifications.

Increasing the capacity of wireless communication is an open and interesting research area which has attracted much attention. The familiar solution is dividing the radio spectrum into several independent radio channels, which can be operated and accessed simultaneously by all nodes within its radio transmitting power. All solutions of researches adopt multiple transceivers to fulfil this goal. Nevertheless, these schemes will be short of implementation and may increase the prime cost since most wireless devices only equip one transceiver. Moreover, with a few exceptions, most researchers have emphasized centralized resource allocation algorithms for cellular systems where the base station keeps track of the requirements of the various users and is thus responsible for the management of network resources. However, on the other hand, multihop mobile ad hoc networks (MANETs) are generally configured as peer-to-peer networks with no centralized hubs or controllers. Therefore, in this paper, we proposed a multichannel medium access control (MAC) protocol, named ad hoc multichannel negotiation protocol (AMNP), for multichannel transmission in distribution fashion. We address the issue of distributed resource allocation for multihop MANETs by presenting an AMNP that builds on the multichannel request-to-send/clear-to-send (MRTS/MCTS) bandwidth reservation mechanism under the constraint of single transceiver. We show via simulations that AMNP provides a higher throughput compared to its single channel counterpart by promoting simultaneous transmissions in different channels. Simulation results also show that the performance of proposed AMNP derives well than other multichannel approaches with multiple transceivers.

The IEEE 802.11 standard and enhanced amendments have defined fourteen transmission rates (1/2/5.5/6/9/11/12/18/22/24/33/36/48/54 Mbit/s) for mobile stations to transmit and receive data frames. With the characteristic of modulation schemes, a higher level modulation scheme requires a higher signal-to-noise ratio (SNR) and, consequently, the data rate is inversely proportional with the transmission distance. Using a higher level modulation scheme, a higher network throughput can be expected; however, the frame error probability will also become higher. Doubtlessly, it is an open issue of selecting a proper modulation scheme for a pair of mobile stations in a time-varying indoor environment. This paper proposes a safe multiple access-rates transmission (SMART) scheme for enhancing the reliability of data transmission in the IEEE 802.11 multi-rate infrastructure wireless networks. The SMART scheme provides reliable transmission by reserving a retransmission period, which immediately follows the transmitted frame and is estimated from a lower transmission rate, for each transmitted frame. If any error occurs on the transmitted frame, the sender will retransmit it right away by using a lower transmission rate to make sure of successful retransmission. Otherwise, the reserved period will be taken by the access point (AP), which often has the longest waiting queue and is the bottleneck in infrastructure wireless networks. The efficiency of the proposed SMART scheme is evaluated by simulation. Simulation results show that the derived performance of the SMART scheme is significantly better than standard under the real environment with asymmetric traffic load.

In IEEE 802.11 infrastructure wireless local area networks (WLAN), all mobile stations (STAs) are coordinated by an access point (AP), which is a static device and plays the role of the bridge between wired and wireless networks. Such coordination is achieved by restricting all STAs to access the channel listened by AP. Within the 2.4 GHz unlicensed industry, science, and medicine (ISM) band defined in the IEEE 802.11 2.4 GHz physical layer (PHY) specifications, three of fourteen channels, which are independent and exclusive, can be used to transfer data packets at a same area concurrently. However, in most small/medium enterprises or home environments, one AP is sufficient for covering whole service area. This implies that the other two channels' capacity has being wasted by the single channel operation defined in standard. In order to overcome the drawback, we propose a new and simple CSMA based media access control (MAC) protocol, named wireless switch protocol (WSP), for promoting the IEEE 802.11 aggregate network throughput. This is simply achieved by allowing any pair of STAs in WLAN to exchange data packets in another idle channel after their handshaking with each other in the common channel, which is specified by AP. Simulation results show that the total network throughput of WSP is obviously depending on the time taken by the changing frequency channel and the intranet and Internet traffic distribution, where the intranet and Internet mean the data exchanged between mobile STAs, and between STA and wired host, respectively. If all data packets are intranet traffic and the traffic load is heavy, the improving ratio of derived goodput of proposed WSP and that of the IEEE 802.11 standard approximates 400%. In the worse case that all traffic is Internet traffic, the proposed WSP still obtains the similar throughput as that of IEEE 802.11 standard.

The IEEE 802.11 wireless local area networks (WLANs) standard supports several equal-capacity communication channels which can be simultaneously shared and accessed by mobile stations. In such multichannel communication system, a mobile station basically can transmit on any of these channels based on a suitable access control protocol. However, with the feature of one transceiver per mobile station, the standard restricts mobile stations to operate in one selected channel and the other channel capacities are wasted inevitably. In this paper, we propose a new carrier sense multiple access (CSMA) based protocol, called multichannel access protocol (MAP), to support parallel transmissions in IEEE 802.11 ad hoc WLANs. To realize the proposed MAP protocol over contemporary ad hoc WLANs, the MAP protocol is not only compliant with the IEEE 802.11 standard but also taking one transceiver constrain into consideration. All mobile stations with MAP will contend for channel access right in a dedicated channel during a periodical contention reservation interval (CRI) and then transmit data frames over different channels by a channel scheduling algorithm (CSA). Given a number of requests, the problem of finding a proper schedule for these requests to be served on a multichannel system so that the longest channel busy period is minimal is known to be NP-hard (Hou, et al. 1994). The time complexity of proposed heuristic CSA is O(|X| log |X| + |X|M/sup 2/) where |X| and M denote the number of successful requests in the CRI and the number of available channels respectively. Simulation results show that the proposed MAP protocol with CSA achieves an obviously higher throughput than conventional IEEE 802.11 WLAN with single channel.

We present a data flushing data transfer (DFDT) protocol for IEEE 802.11 wireless ad hoc network. The basic mechanism of DFDT is quite the same as the distributed coordination function (DCF) of the medium access control (MAC) of IEEE 802.11, which uses a random access delay backoff time after a busy medium condition and RTS/CTS dialogue before sending actual payload data (direct data/ACK could also be used). The enhancement introduced by DFDT is mainly produced by the compilation process (CP), which fits as many MAC layer packets as possible into one physical layer packet within the limit of a predetermined length. By using the CP, we lower the protocol overhead, the packet arrival rate of the physical layer, and network contention all with one action. DFDT takes the advantages of the RTS/CTS mechanism but has less the overhead. Simulation results backed by numerical analysis show growing improvement in performance, limited by the saturation of the network, as the network load gets higher.

In wired networks, the broadcast data packets can be easily and safely delivered to destinations. Nevertheless, it is a big challenge to transfer the broadcast frames over the IEEE 802.11 based multi-hop ad hoc wireless networks due to the high bit error rate, the high collision probability, and the lake of acknowledgement (ACK). Unfortunately, most of routing protocols need the broadcast function to exchange important information between nodes. From our observations, the efficiency of the routing protocol, such as dynamic source routing (DSR) and ad-hoc on-demand distance vector (AODV), finding the path from source to destination is strongly depending on the supported broadcast scheme in the underlying media access control (MAC) protocol. In this paper, we first investigate the uncertain broadcast problem in the IEEE 802.11 MAC protocol while delivering the necessary broadcast frames. Since no acknowledgement will be sent by any recipient of the broadcast frame in IEEE 802.11 MAC protocol, we propose a highly reliable broadcast scheme to solve such uncertain problem. The proposed scheme, which is still compatible with standard, can efficiently minimize bandwidth consumption as well as propagation delay.

Wireless technologies and applications received great attention in recent years. The medium access control (MAC) protocol is the main element that determines the efficiency in sharing the limited communication bandwidth of the wireless channel in wireless local area networks (WLANs). The request-to-send/clear-to-send (RTSICTS) mechanism is an optional handshaking procedure used by the IEEE 802.11 wireless network to reduce the possibility of collision. The RTS-Threshold (RT) value which determines when the RTS/CTS handshaking mechanism should be used is an important parameter to investigate; since different RT values will produce different performance characteristics in data transmission. This paper presents an analysis of the influence of the RT parameter on the IEEE 802.11 wireless network, and gives a guideline to dynamically adjust the RT value. Simulation results of this paper show that the RTSICTS mechanism should be always turned on (RT = 0) to achieve an excellent performance while saving complex work designing a dynamic RT mechanism which will not have notable effect.

This paper discusses the issue of routing packets over an IEEE 802.11 wireless ad hoc network with multiple data rates (1, 2, 5.5, and 11 Mb/s). With the characteristics of modulation schemes, the data rate of a wireless network is inversely proportional with the transmission distance. The conventional shortest path of the minimum-hops approach will be no longer suitable for the contemporary multi-rate/multi-range wireless networks (MR/sup 2/WN). We propose an efficient delay-oriented multi-rate/multi-range routing protocol (MR/sup 2/RP) for MR/sup 2/WN to maximize the channel resource utilization as well as to minimize the network end-to-end transfer delay. By analyzing the medium access delay of the IEEE 802.11 medium access control (MAC) protocol, the proposed MR/sup 2/RP is capable of predicting the end-to-end transfer delay of a routing path and find the best one. The proposed MR/sup 2/RP may choose a longer path but with less contention competitors and buffer queuing delay. Simulation results show that MR/sup 2/RP performs the load balancing and fast routing very well and its call blocking probability is obviously lower than that of conventional minimum-hops approach with fixed transmission rate.

In wireless ad hoc mobile network, a host which desires to communicate with another host may need some intermediate nodes to relay data packets. To maximize the channel resource utilization and minimize the network transfer delay along the path, the shortest path with minimum hops approach is often adapted. However, by considering employing the medium access control (MAC) protocol, the minimum transfer delay from source to destination may be achieved by choosing a longer path but with less contention delay. We propose an efficient delay-oriented routing protocol for mobile ad hoc wireless networks. The expected access contention delay of the IEEE 802.11 protocol is analyzed to support the routing decision. Simulation results show that the derived path length in the proposed delay-oriented routing protocol is slightly higher than that of the conventional shortest path with minimum hops approach but it can significantly reduce both the average transfer delay and packet loss rate.