Automatic Repair Method for D2D Communication Routing Buffer Overflow Vulnerability in Cellular Network

Repairing D2D communication routing buffer overflow in a cellular network is of great significance in improving communication quality and security. Due to the increase of user usage, the communication data are easy to exceed the boundary of the buffer, resulting in the reduction of covered data information. The traditional repair methods mainly repair through the characteristics of covered data information, ignoring the impact of network topology information transmission delay and packet loss during calculation, resulting in the problem of low communication security. A cellular network routing buffer overflow repair algorithm based on the homomorphic analysis of node residual energy is proposed; the cellular network D2D communication routing protocol is designed; the cellular network D2D communication protocol path index is determined; then, the cellular network D2D communication routing protocol is designed by analyzing node residual energy; and the cellular network D2D communication network routing optimization method based on AHP is designed. Big constructs the energy model of cellular network D2D communication network, solves and sets the routing optimization objective function, realizes the control of network routing, and repairs the buffer overflow. The experiment results show that the improved method can effectively reduce the packet loss rate of communication data, improve the anti-interference ability of the system, and ensure the security of network communication.

Edge Network Routing Protocol Base on Target Tracking Scenario

Edge computing perfectly integrates cloud computing centers and edge-end devices together, but there are not many related researches on how the edge-end node devices work to form an edge network and what the protocols used to implement the communication among nodes in the edge network. Aiming at the problem of coordinated communication among edge nodes in the current edge computing network architecture, this paper proposes an edge network routing and forwarding protocol based on target tracking scenarios. This protocol can meet the dynamic changes of node locations, and the elastic expansion of node scale. Individual node failures will not affect the overall network, and the network ensures efficient real-time with less communication overhead. The experimental results display that the protocol can effectively reduce the communications volume of the edge network, improve the overall efficiency of the network, and set the optimal sampling period, so as to ensure that the network delay is minimized.

An IPv6 Passive-Aware Network Routing Algorithm Based on Utility Value Combined with Deep Neural Network

Passive sensing networks can maintain the operation of the network by capturing energy from the environment, thereby solving the energy limitation problem of network nodes. Therefore, passive sensing networks are widely used in data collection in complex environments. However, the complexity of the network deployment environment makes passive sensing nodes unable to obtain stable energy from the surroundings. Therefore, better routing strategies are needed to save network energy consumption. In response to this problem, this paper proposes an IPv6 passive-aware network routing algorithm for the Internet of Things. This method is based on the characteristics of passive sensing networks. By analyzing the successful transmission rate of the network node transmission link, transmission energy consumption, end-to-end transmission delay, and waiting delay of IPv6 packets, the utility evaluation function of the route is obtained. After the utility evaluation function is obtained, the network routing is selected through the utility evaluation function. Then, the utility value and the deep neural network method are combined to train the classification model. The classification model assigns the best routing strategy according to the characteristics of the current network, thereby improving the energy consumption and delay performance of the network.

GPF: A Green Power Forwarding Technique for Energy-Efficient Network Operations

The energy consumption of network infrastructures is increasing; therefore, research efforts designed to diminish this growing carbon footprint are necessary. Building on prior work, which determined a difference in the energy consumption of network hardware based on their forwarding configurations and developed a real-time network energy monitoring tool, this research proposes a novel technique to incorporate individual device energy efficiency into network routing decisions. A new routing metric and algorithm are presented to select the lowest-power, least-congested paths between destinations, known as Green Power Forwarding (GPF). In addition, a network dial is developed to enhance GPF by allowing network administrators to tune the network to optimally operate between energy savings and network performance. To ensure the scope of this research for industry adoption, implementation details for different generations of networking infrastructure (past, present, and future) are also discussed. The experiment results indicate that significant energy and, in turn, cost savings can be achieved by employing the proposed GPF technique without a reduction in network performance. The future directions for this research include developing dynamically-tuning network dial modes and extending the principles to inter-domain routing.

Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms

Recent advancements in deep reinforcement learning (DRL) have led to its application in multi-agent scenarios to solve complex real-world problems, such as network resource allocation and sharing, network routing, and traffic signal controls. Multi-agent DRL (MADRL) enables multiple agents to interact with each other and with their operating environment, and learn without the need for external critics (or teachers), thereby solving complex problems. Significant performance enhancements brought about by the use of MADRL have been reported in multi-agent domains; for instance, it has been shown to provide higher quality of service (QoS) in network resource allocation and sharing. This paper presents a survey of MADRL models that have been proposed for various kinds of multi-agent domains, in a taxonomic approach that highlights various aspects of MADRL models and applications, including objectives, characteristics, challenges, applications, and performance measures. Furthermore, we present open issues and future directions of MADRL.

Hedging the Drift: Learning to Optimize Under Nonstationarity

We introduce data-driven decision-making algorithms that achieve state-of-the-art dynamic regret bounds for a collection of nonstationary stochastic bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and traffic network routing in changing environments. We show how the difficulty posed by the (unknown a priori and possibly adversarial) nonstationarity can be overcome by an unconventional marriage between stochastic and adversarial bandit learning algorithms. Beginning with the linear bandit setting, we design and analyze a sliding window-upper confidence bound algorithm that achieves the optimal dynamic regret bound when the underlying variation budget is known. This budget quantifies the total amount of temporal variation of the latent environments. Boosted by the novel bandit-over-bandit framework that adapts to the latent changes, our algorithm can further enjoy nearly optimal dynamic regret bounds in a (surprisingly) parameter-free manner. We extend our results to other related bandit problems, namely the multiarmed bandit, generalized linear bandit, and combinatorial semibandit settings, which model a variety of operations research applications. In addition to the classical exploration-exploitation trade-off, our algorithms leverage the power of the “forgetting principle” in the learning processes, which is vital in changing environments. Extensive numerical experiments with synthetic datasets and a dataset of an online auto-loan company during the severe acute respiratory syndrome (SARS) epidemic period demonstrate that our proposed algorithms achieve superior performance compared with existing algorithms. This paper was accepted by George J. Shanthikumar for the Management Science Special Issue on Data-Driven Prescriptive Analytics.

Fuzzy Logic-based Data Controlled Wireless Sensor Network Routing Protocol for Flood Early Warning

Floods account for 15% of all natural disasters related deaths. Therefore, early flood warning systems using wireless network of sensors installed in flood prone areas is necessary to provide early notice of impending flood. This research focuses on the use of an energy efficient routing protocol to prolong the life time of the Network. The importance of this is to minimize energy consumption as necessary for reliable field operations. It adopts the use of mandami Fuzzy logic-based data controlled routing protocol (F-DCRP).Simulation was carried out for the F-DCRP, LEACH and Crisp Data controlled routing protocol (DCRP). The performance of the three protocols were obtained and compared. The result showed that Cluster head (CH) load was better shared uniformly among all the nodes. Percentage of packets dropped showed that the proposed F-DCRP was 10% lower compared to DCRP and 50% lower compared to LEACH resulting in more packets sent per round and greater reliability compared to LEACH and DCRP. The network lifetime was also improved by 40 % when compared to LEACH and DCRP.