Search

The implementation of Open Radio Access Network (O-RAN) architecture in Internet of Things (IoT) systems has garnered significant attention as a means to fulfill the stringent requirements of ultra-low latency and ultra-low energy consumption in future IoT systems. Although the traditional edge network architecture has been extensively employed, it continues to pose challenges in terms of synchronizing the integration of global and local information for the design of an optimal offloading strategy in edge servers, thus hindering the reduction of latency and energy consumption in IoT devices. In an effort to decrease the latency and energy consumption of IoT devices (IoTDs), we propose a computation offloading problem and employs the Successive Convex Approximation (SCA) algorithm to convert the non-convex problem into a convex problem. The proposed strategy aims to minimize the energy consumption of IoTDs while ensuring Quality of Service (QoS) requirements. The results of the experiment demonstrate that the average energy consumption of terminal devices can be reduced by 20%. Additionally, this strategy is found to be more effective in reducing IoTDs' latency and energy consumption as compared to the traditional edge network architecture.

Two-dimensional optical orthogonal codes have important applications in optical code division multiple access networks. In this paper, a generic construction of two-dimensional optical orthogonal codes with at most one pulse per wavelength (AM-OPPW 2D OOCs) is proposed. As a result, some optimal AM-OPPW 2D OOCs with new parameters can be yielded. The new AM-OPPW 2D OOC may support more subscribers and heavier asynchronous traffic compared with known constructions.

Accurate tropical cyclone (TC) intensity and size estimation are key in disaster management and prevention. While great breakthroughs have been made in TC intensity estimation research, there is currently a lack of research on TC size reflecting TC influence radius. Therefore, we propose a lightweight multi-task learning model (TC-MTLNet) with adaptive loss balance to simultaneously estimate TC intensity and size. Adaptive loss balance is utilized to solve the problem of inconsistent convergence speed of TC intensity and size estimation tasks. The model based on four 2-D convolutions, four 3-D convolutions and three fully connected layers takes up less computational and storage space and improves the accuracy of TC intensity and size estimation by sharing knowledge among multiple tasks. In addition, due to the imbalanced distribution of TC samples, with significantly few low-intensity and high-intensity TC satellite data, this phenomenon poses a great challenge to TC intensity and size estimation. So, we utilize the influence of nearby samples to calibrate the sample density to weight the loss function to enable the model to be generalized to all samples. The result shows that the root-mean-square error (RMSE) of TC intensity estimation is $\text{8.40}\,\text{kts}$, which is 33.5% lower than that of the Advanced Dvorak Technique (ADT) and 11.4% lower than that of the deep learning method (3DAttentionTCNet). The mean absolute error (MAE) of the TC size estimation is $\text{20.89}\,\text{nmi}$, which is a 16% reduction compared to the Multi-Platform Tropical Cyclone Surface Winds Analysis (MTCSWA).

Abstract Multi-cloud computing is becoming a promising paradigm to provide abundant computation resources for Internet-of-Things (IoT) devices. For a multi-device multi-cloud network, the real-time computing requirements, frequently varied wireless channel gains and changeable network scale, make the system more dynamic. It is critical to satisfy the dynamic nature of network with different constraints of IoT devices in multi-cloud environment. In this paper, we establish a continuous-discrete hybrid decision offloading model, each device should learn to make coordinated actions, including cloud server selection, offloading ratio and local computation capacity. Therefore, both continuous-discrete hybrid decision and coordination among IoT devices are challenging. To this end, we first develop a probabilistic method to relax the discrete action (e.g. cloud server selection) to a continuous set. Then, by leveraging a centralized training and distributed execution strategy, we design a cooperative multi-agent deep reinforcement learning (CMADRL) based framework to minimize the total system cost in terms of the energy consumption of IoT device and the renting charge of cloud servers. Each IoT device acts as an agent, which not only learns efficient decentralized policies, but also relieves IoT devices’ computing pressure. Experimental results demonstrate that the proposed CMADRL could efficiently learn dynamic offloading polices at each IoT device, and significantly outperform the four state-of-the-art DRL based agents and two heuristic algorithms with lower system cost.

The channel-hopping-based rendezvous is essential to alleviate the problem of under-utilization and scarcity of the spectrum in cognitive radio networks. It dynamically allows unlicensed secondary users to schedule rendezvous channels using the assigned hopping sequence to guarantee the self-organization property in a limited time. In this paper, we use the interleaving technique to cleverly construct a set of asynchronous channel-hopping sequences consisting of d sequences of period xN2 with flexible parameters, which can generate sequences of different lengths. By this advantage, the new designed CHSs can be used to adapt to the demands of various communication scenarios. Furthermore, we focus on the improved maximum-time-to-rendezvous and maximum-first-time-to-rendezvous performance of the new construction compared to the prior research at the same sequence length. The new channel-hopping sequences ensure that rendezvous occurs between any two sequences and the rendezvous times are random and unpredictable when using licensed channels under asynchronous access, although the full degree-of-rendezvous is not satisfied. Our simulation results show that the new construction is more balanced and unpredictable between the maximum-time-to-rendezvous and the mean and variance of time-to-rendezvous.

In quasi-synchronous frequency-hopping multiple access (QS-FHMA) systems, low-hit-zone (LHZ) frequency-hopping sequence (FHS) sets have been well-applied to reduce mutual interference (MI). In this paper, we propose three constructions of LHZ FHS sets with new parameters via interleaving techniques. The obtained sequences can be verified that they are optimal with respect to the Peng–Fan–Lee bound.

The performance of network elements depends heavily on their parameter setting in cellular networks. Current practice of parameter setting relies largely on expert experience and self-organizing networks, which is often suboptimal. Therefore, how to find the optimal parameter combinations automatically is increasingly concerned by mobile network operators. In this article, a collaborative learning approach is proposed to meet this demand by predicting the performance of network elements under different parameter combinations before setting. The proposed approach captures the time-aware correlation between different network elements and their parameter combinations based on factorization machine to boost the prediction accuracy. Extensive experiment results demonstrate that the proposed approach outperforms the existing prediction approaches on a large-scale real-world network dataset from a metropolitan LTE network.

Through information sharing, vehicles can know the surrounding road condition information timely in Vehicular Adhoc Networks. To ensure the validity of these messages and the security of vehicles, the message authentication, privacy-preserving, and delay problems are three important issues. Although many conditional privacy-preserving authentication schemes have been proposed to ensure secure communication, there still exist some imperfections such as frequent interactions or unlinkability. From this, our paper proposes a novel hierarchical blockchain-assisted authentication scheme to solve these existing issues comprehensively. First, unlinkability is achieved by a dynamic key derivation algorithm. Second, the proposed scheme can reduce correlation processing delay, queuing delay, and deployment costs by adopting hierarchical Vehicle Fog Computing. Third, cross-region authentication is achieved by taking advantage of the properties of blockchain. In addition, we demonstrate our scheme can fulfill the security criteria of the Vehicular Adhoc Network by security analysis. Furthermore, the simulations are carried out to show its availability by using JAVA and NS-3. The findings reveal that the suggested method outperforms earlier schemes in terms of computation cost and communication cost. All in all, making the authentication scheme more efficient and concise is the focus of our future research.

Mobile Edge Computing (MEC) is a technology designed for the on-demand provisioning of computing and storage services, strategically positioned close to users. In the MEC environment, frequently accessed content can be deployed and cached on edge servers to optimize the efficiency of content delivery, ultimately enhancing the quality of the user experience. However, due to the typical placement of edge devices and nodes at the network's periphery, these components may face various potential fault tolerance challenges, including network instability, device failures, and resource constraints. Considering the dynamic nature of MEC,making high-quality content caching decisions for real-time mobile applications, especially those sensitive to latency, by effectively utilizing mobility information, continues to be a significant challenge. In response to this challenge, this paper introduces FT-MAACC, a mobility-aware caching solution grounded in multi-agent deep reinforcement learning and equipped with fault tolerance mechanisms. This approach comprehensively integrates content adaptivity algorithms to evaluate the priority of highly user-adaptive cached content. Furthermore, it relies on collaborative caching strategies based onmulti-agent deep reinforcement learningmodels and establishes a fault-tolerancemodel to ensure the system's reliability, availability, and persistence. Empirical results unequivocally demonstrate that FT-MAACC outperforms its peer methods in cache hit rates and transmission latency. [ABSTRACT FROM AUTHOR]