This paper presents an intelligent spectrum mobility management scheme for cognitive radio networks. The spectrum mobility could involve spectrum handoff (i.e., the user switches to a new channel) or stay-and-wait (i.e., the user pauses the transmission for a while until the channel quality improves again). An optimal spectrum mobility management scheme needs to consider its long-term impact on the network performance, such as throughput and delay, instead of optimizing only the short-term performance. We use a machine learning scheme, called the Transfer Actor-Critic Learning (TACT), for the spectrum mobility management. The proposed scheme uses a comprehensive reward function that considers the channel utilization factor (CUF), packet error rate (PER), packet dropping rate (PDR), and flow throughput. Here, the CUF is determined by the spectrum sensing accuracy and channel holding time. The PDR is calculated from the non-preemptive M/G/1 queueing model, and the flow throughput is estimated from a link-adaptive transmission scheme, which utilizes the rateless (Raptor) codes. The proposed scheme achieves a higher reward, in terms of the mean opinion score, compared to the myopic and Q-learning based spectrum management schemes.
1 January 2008 in International Journal of Telemedicine and Applications
New wireless technologies, such as wireless LAN and sensor networks, for telecardiology purposes give new possibilities for monitoring vital parameters with wearable biomedical sensors, and give patients the freedom to be mobile and still be under continuous monitoring and thereby better quality of patient care. This paper will detail the architecture and quality-of-service (QoS) characteristics in integrated wireless telecardiology platforms. It will also discuss the current promising hardware/software platforms for wireless cardiac monitoring. The design methodology and challenges are provided for realistic implementation.
27 December 2022 in IEEE Transactions on Aerospace and Electronic Systems
Autonomous and decentralized UAV networks are used in many applications, including disaster management, environment monitoring and surveillance. The performance of the routing protocols in these networks drops significantly due to frequent route breaks and traffic congestion at high node speeds. This is partly because the routing metrics used in many of the existing protocols are sensitive to the intra-flow interference after the source node starts transmission on the selected route. Moreover, these schemes do not estimate potential packet drops or take preventive measures, such as route switching and queue management. To address these issues, we present a cross-layer, mobility and congestion-aware optimized link state routing (MCA-OLSR) protocol for an autonomous and decentralized UAV network, which incorporates the following mechanisms: ( i ) Multi-metric route selection which includes hop count, route lifetime, estimated time-to-destination and number of interfering links; ( ii ) Preemptive route switching which prevents packet transmission over the broken and congested routes; and ( iii ) Queue management to prioritize transmission of packets based on their survivability score. We also present key observations on routing protocol design and a theoretical analysis to show the impact of data rate, route length and interfering links on the packet service rate and congestion. The proposed routing scheme achieves a significantly higher packet delivery ratio and lower route computation overhead for delay-sensitive data flows at different data rates, node densities and high speeds, as compared to the standard and multi-metric OLSR protocols.
8 January 2018 in IEEE Transactions on Cognitive Communications and Networking
In the software defined networking (SDN)-based wireless mesh network (WMN) architecture (SD-WMN), the network is monitored and managed in a centralized manner. Although the use of SDN simplifies the WMN management, it is still not clear whether the SDN architecture, which was originally designed for wired links, can effectively handle the dynamic topology of WMNs. This paper addresses the traffic balancing issue introduced by node mobility. To reduce the response time of SDN controller for dynamic network topology, a two-layer supervised learning model is proposed that helps the controller to predict the node mobility and link failure probability. Then, an alternative route selection scheme is proposed, which achieves optimal traffic balancing while minimizing the control plane overhead. Efficiency of the proposed SD-WMN architecture is validated in the widely used network simulator -ns-3. Our results demonstrate the network throughput enhancement achieved by the proposed SD-WMN architecture with link-failure adaptive traffic control.
12 July 2018 in IEEE Wireless Communications Letters
This paper studies the problem of neighbor discovery (i.e., finding 1-hop neighbor nodes) in a wireless ad-hoc network, with exclusive use of directional antennas. We model the neighbor discovery process as a learning automaton, operating in a non-stationary learning environment with unknown dynamics. The node learns about its environment from its past observations and adjusts its strategy to achieve a faster discovery rate. The asymptotic behavior of the proposed learning scheme is analyzed, and is shown to converge to an equi-probable probability distribution. The proposed scheme achieves significantly faster network-wide neighbor discovery in densely populated networks.
A swarm of unmanned aerial vehicles (UAVs) requires the transmission of mission-related data across the network. The resource constraints and dynamic nature of the swarm bring critical challenges to the design of UAV routing protocols. Most of the conventional ad hoc routing schemes are not intelligent and cannot adapt to the dynamic nature of UAV swarming networks. On the other hand, some artificial intelligence (AI)-based routing schemes may consume significant computational resources in the UAVs. In this paper, a low-cost, adaptive routing protocol, namely skeleton-based swarm routing (SSR), is proposed, which exploits an intelligent online learning algorithm and the topology features of the mission-driven UAV swarm to distribute the traffic over optimal routes. Here, the skeleton represents the most stable parts of the swarm formation. SSR architecture consists of three modules: 1) A geometric addressing module, which assigns geometric coordinates to each node based on the swarm skeleton structure; 2) A leaf-like routing pipe which allows the selection of multiple candidate routes around the shortest path; 3) An intelligent low-complexity learning model which determines how to distribute the packets inside the routing pipe to achieve load-balanced, high-throughput transmissions. The proposed skeleton-based scheme can also facilitate the UAV formation construction and morphing. The simulation results show that the proposed SSR protocol can noticeably improve the network performance (up to 100% throughput improvement) compared to the single path routing schemes, such as the ad-hoc on-demand distance vector (AODV) and link-quality and traffic-load aware optimized link state routing (LTA-OLSR) protocols.