Special Issue on Deep Reinforcement Learning for Emerging IoT Systems
10 Jul 2020-IEEE Internet of Things Journal (Institute of Electrical and Electronics Engineers (IEEE))-Vol. 7, Iss: 7, pp 6175-6179
TL;DR: An increasing number of IoT devices and the emerging IoT applications are driving exponential growth in wireless traffic in the foreseeable future, and current IoT system architectures are facing significant challenges to handle millions of devices; thousands of servers; the transmission and processing of large volume of data.
Abstract: Nowadays we are witnessing the formation of a massive Internet-of-Things (IoT) ecosystem that integrates a variety of wireless-enabled devices ranging from smartphones, wearables, and virtual reality facilities to sensors, drones, and connected vehicles. As IoT is penetrating every aspect of people’s life, work, and entertainment, an increasing number of IoT devices and the emerging IoT applications are driving exponential growth in wireless traffic in the foreseeable future. As a result, current IoT system architectures are facing significant challenges to handle millions of devices; thousands of servers; the transmission and processing of large volume of data, etc.
Citations
More filters
TL;DR: A deep-reinforcement-learning (DRL)-based intelligent routing scheme is proposed for IoT-enabled WSNs that significantly reduce delay and increase network lifetime and is compared with the state-of-the-art algorithms.
Abstract: Recently, the Internet of Things (IoT) has attracted much interest in its wide applications, such as smart healthcare, home automation, transportation, and smart city. In these IoT-based systems, wireless sensor networks (WSNs) are highly used to gather information needed by smart environments. However, due to huge heterogeneous data coming from different sensing devices, IoT-enabled WSNs face different challenges, such as high communication delay, low throughput, and poor network lifetime. In this article, a deep-reinforcement-learning (DRL)-based intelligent routing scheme is proposed for IoT-enabled WSNs that significantly reduce delay and increase network lifetime. The proposed algorithm divides the whole network into different unequal clusters depending on the current data load present in the sensor node that significantly prevents immature death of the network. An extensive experiment on the proposed algorithm is performed using ns3. The experimental results are compared with the state-of-the-art algorithms to demonstrate the efficiency of the proposed scheme in terms of the number of alive nodes, packet delivery, energy efficiency, and communication delay in the network.
59 citations
TL;DR: It was showed that the combination of AI and VR contributes to new trends, opportunities, and applications for human-machine interactive devices, education, agriculture, transport, 3D image reconstruction, and health.
Abstract: Although there are methods of artificial intelligence (AI) applied to virtual reality (VR) solutions, there are few studies in the literature. Thus, to fill this gap, we performed a systematic literature review of these methods. In this review, we apply a methodology proposed in the literature that locates existing studies, selects and evaluates contributions, analyses, and synthesizes data. We used Google Scholar and databases such as Elsevier's Scopus, ACM Digital Library, and IEEE Xplore Digital Library. A set of inclusion and exclusion criteria were used to select documents. The results showed that when AI methods are used in VR applications, the main advantages are high efficiency and precision of algorithms. Moreover, we observe that machine learning is the most applied AI scientific technique in VR applications. In conclusion, this paper showed that the combination of AI and VR contributes to new trends, opportunities, and applications for human-machine interactive devices, education, agriculture, transport, 3D image reconstruction, and health. We also concluded that the usage of AI in VR provides potential benefits in other fields of the real world such as teleconferencing, emotion interaction, tourist services, and image data extraction.
2 citations
TL;DR: In this article , a balanced routing algorithm with transmission range adjustment (BRATRA) is proposed to address the network efficiency problem, including the energy efficiency and utilization issues, in WSNs.
Abstract: In traditional wireless sensor networks (WSNs), packets are mainly transmitted in a multihop routing manner. The multihop transmission, however, leads to a hotspot problem in the sink connectivity area (SCA), and the overall network efficiency is reduced due to the quick battery power exhaustion of nodes in that area. This article proposes a novel balanced routing algorithm with transmission range adjustment (BRATRA) to address the network efficiency problem, including the energy efficiency and utilization issues. First, a balanced routing strategy is designed to deal with the SCA load imbalance problem. With the shortest balanced path, the amounts of forwarding packets for the nodes in the SCA and all the other intralayers become more even. From the perspective of power equilibrium in each routing path, each node then determines its accurate transmission radius according to the derived formula and performs power control to realize the even power utilization between interlayers, thereby prolonging the overall network lifetime. Performance evaluation validates that the proposed BRATRA strategy can achieve efficient power utilization in each intralayer and double the network lifetime as compared to the Dijkstra routing strategy. Additionally, it yields better power utilization fairness among nodes, and on average only 5% of battery power is unused for all network nodes, resulting in a network lifespan ten times larger than that using a conventional strategy.
TL;DR: In this paper , a balanced routing algorithm with transmission range adjustment (BRATRA) is proposed to address the network efficiency problem, including the energy efficiency and utilization issues, in WSNs.
Abstract: In traditional wireless sensor networks (WSNs), packets are mainly transmitted in a multihop routing manner. The multihop transmission, however, leads to a hotspot problem in the sink connectivity area (SCA), and the overall network efficiency is reduced due to the quick battery power exhaustion of nodes in that area. This article proposes a novel balanced routing algorithm with transmission range adjustment (BRATRA) to address the network efficiency problem, including the energy efficiency and utilization issues. First, a balanced routing strategy is designed to deal with the SCA load imbalance problem. With the shortest balanced path, the amounts of forwarding packets for the nodes in the SCA and all the other intralayers become more even. From the perspective of power equilibrium in each routing path, each node then determines its accurate transmission radius according to the derived formula and performs power control to realize the even power utilization between interlayers, thereby prolonging the overall network lifetime. Performance evaluation validates that the proposed BRATRA strategy can achieve efficient power utilization in each intralayer and double the network lifetime as compared to the Dijkstra routing strategy. Additionally, it yields better power utilization fairness among nodes, and on average only 5% of battery power is unused for all network nodes, resulting in a network lifespan ten times larger than that using a conventional strategy.