Search

Federated continual learning (FCL) is emerging as a key technology for time-sensitive applications in highly adaptive environments including autonomous driving and industrial digital twin. Each FCL trains machine learning models using newly-generated datasets as soon as possible, to obtain a highly accurate machine learning model for new event predictions. The age of data, defined as the time difference between the generation time of a dataset and the current time, is widely adopted as a key criterion to evaluate both timeline and quality of training. In this paper, we study the problem of age-aware FCL in a mobile edge computing (MEC) network. We not only investigate optimization techniques that optimize the data selection and aggregator placement for FCL but also implement a real system as a prototype for age-aware FCL. Specifically, we first propose an approximation algorithm with a provable approximation ratio for the age-aware data selection and aggregator placement problem for FCL with a single request. In real application scenarios, there are usually multiple FCL requests that require to train models, and delays in the MEC network are usually uncertain. We then study the problem of age-aware data selection and aggregator placement problem for FCL with uncertain delays and multiple requests, by devising an online learning algorithm with a bounded regret based on contextual bandits. We finally implement a prototype for FCL in an MEC network, with various heterogeneous user equipments (UEs) and cloudlets with different computing capabilities in the network. Experiment results show that the performance of the proposed algorithms outperform existing studies, by achieving 47% lower age of data and 12% higher model accuracy.

In this paper, we study the deployment of $K$ heterogeneous UAVs to monitor Points of Interest (PoIs) in a disaster zone, where a PoI may represent a school building or an office building, in which people are trapped. A UAV can take images/videos of PoIs and send its collected information back to a nearby rescue station for decision-making. Unlike most existing studies that focused on only homogeneous UAVs, we here study the scheduling of $K$ heterogeneous UAVs, where different UAVs have different energy capacities and functionalities that lead to different monitoring qualities (monitoring rewards) of each PoI. For example, one type of UAVs can take only visual images while the other type of UAVs can take both visual and thermal infrared images. In this paper, we investigate a problem of scheduling $K$ heterogeneous UAVs to monitor PoIs so that the sum of monitoring rewards received by all UAVs is maximized, subject to energy capacity on each UAV. We propose the very first $\frac {1}{3}$ -approximation algorithm for this scheduling problem. We also evaluate the performance of the proposed algorithm, using real parameters of commercial UAVs. Experimental results show that the performance of the proposed algorithm is promising, which is improved by 25%, compared with existing algorithms.

Background: Actinidia eriantha Benth is a widely used natural product from Traditional Chinese Medicine in the Actinidiaceae family. However, its wild resources have been declining due to over-exploitation. It has become urgent to investigate the genetic diversity for the conservation of A. eriantha, to evaluate the current species and discover strategies for preservation.Methods: The internal transcribed spacer (ITS) was used to evaluate the genetic diversity among and within populations of this species. Dnasp, PERMUT and Arlequin 3.0 software were used to calculate the genetic diversity index, and MEGA 5.0 software was used to construct the neighbor-joining (NJ) tree.Results: A total of 27 haplotypes were obtained by ITS sequence analysis of 12 populations, and the most frequently haplotype observed was H1. AMOVA analysis revealed that the genetic variation rates were 10.91% (FST = 0.22290) and 77.71% (FSC = 0.12306) among and within populations, respectively, with high genetic diversity at the species level (Hd = 0.692). The genetic distance among populations ranged from 0 to 0.004. The results of Permut analysis showed that there was no significant correlation between genetic distance and geographic distance (NST > GST). The NJ tree was divided into two Clades (Clade A and Clade B), Clade B has obvious geographical specificity, and haplotypes of this clade are all specific to the GX-ZY population. Four types were found according to ITS sequences of A. eriantha, haplotypes H1 and H5 were ancient haplotypes.Conclusion: Our findings indicated that genetic diversity within populations was higher than observed among populations. This study is significant for further research endeavors focused on the efficient collection and preservation of wild resources of A. eriantha.

The emerging digital twin technique enhances the network management efficiency and provides comprehensive insights on network performance, through mapping physical objects to their digital twins. The user satisfaction on digital twin-enabled service relies on the freshness of digital twin data, which is measured by the Age of Information (AoI). Due to long service delays, the use of the remote cloud for delay-sensitive service provisioning faces serious challenges. Mobile Edge Computing (MEC), as an ideal paradigm for delay-sensitive services, is able to realize real-time data communication between physical objects and their digital twins at the network edge. However, the mobility of physical objects and dynamics of user query arrivals make seamless service provisioning in MEC become challenging. In this paper, we investigate dynamic digital twin placements for improving user service satisfaction in MEC environments, by introducing a novel metric to measure user service satisfaction based on the AoI concept and formulating two user service satisfaction enhancement problems: the static and dynamic utility maximization problems under static and dynamic digital twin placement schemes. To this end, we first formulate an Integer Linear Programming (ILP) solution to the static utility maximization problem when the problem size is small; otherwise, we propose a performance-guaranteed approximation algorithm. We then propose an online algorithm with a provable competitive ratio for the dynamic utility maximization problem, by considering dynamic user query services. Finally, we evaluate the performance of the proposed algorithms via simulations. Simulation results demonstrate that the proposed algorithms outperform the comparison baseline algorithms, improving the algorithm performance by at least 10.7%, compared to the baseline algorithms.

In the coming era of Metaverse, Augmented Reality (AR) has become a key enabler of diverse applications including healthcare, education, smart cities, and entertainments. To provide users with interactive and immersive experience, most AR applications require extremely high responsiveness and ultra-low processing latency. Mobile edge computing (MEC) has demonstrated great potentials in meeting such stringent latency requirements and resource demands of AR applications, by implementing AR requests in edge servers within the proximity of users. In this paper, we investigate the reward maximization problem for AR applications with uncertain resource demands in an MEC network, such that the accumulative reward of services provided for AR applications is maximized, while ensuring that the responsiveness of AR applications is enhanced, subject to network resource capacity. To this end, we formulate an exact solution when the problem size is small, otherwise we devise an efficient approximation algorithm with a provable approximation ratio for the problem. We also develop an online learning algorithm with a bounded regret for the dynamic reward maximization problem without the knowledge of future arrivals of AR requests, by adopting the Multi-Armed Bandits (MAB) technique. Considering maximizing the reward may defer the implementations of some urgent yet low-award requests, we propose a fairness-aware online learning algorithm for the dynamic reward maximization problem, through a data rate prediction mechanism that adopts a multi-task and multi-timescale Long Short-Term Memory (MT2-LSTM) method. Finally, we evaluate the performance of the proposed algorithms for AR applications by building a real test bed. Experimental results show that the proposed algorithms outperform existing studies by improving the award by 13%.

Benefitting from the breakthrough of wireless power transfer technology, the lifetime of Wireless Sensor Networks (WSNs) can be significantly prolonged by scheduling a mobile charger (MC) to charge sensors. Compared with omnidirectional charging, the MC equipped with directional antenna can concentrate energy in the intended direction, making charging more efficient. However, all prior arts ignore the considerable energy leakage behind the directional antenna (i.e., back lobe), resulting in energy wasted in vain. To address this issue, we study a fundamental problem of how to utilize the neglected back lobe and schedule the directional MC efficiently. Towards this end, we first build and verify a directional charging model considering both main and back lobes. Then, we focus on jointly optimizing the number of dead sensors and energy usage effectiveness. We achieve these by introducing a scheduling scheme that utilizes both main and back lobes to charge multiple sensors simultaneously. Finally, extensive simulations and field experiments demonstrate that our scheme reduces the number of dead sensors by 49.5% and increases the energy usage effectiveness by 10.2% on average as compared with existing algorithms.

In this paper we study the deployment of an Unmanned Aerial Vehicle (UAV) network that consists of multiple UAVs to provide emergent communication service for people who are trapped in a disaster area, where each UAV is equipped with a base station that has limited computing capacity and power supply, and thus can only serve a limited number of people. Unlike most existing studies that focused on homogeneous UAVs, we consider the deployment of heterogeneous UAVs where different UAVs have different computing capacities. We study a problem of deploying $K$ heterogeneous UAVs in the air to form a temporarily connected UAV network such that the network throughput– the number of users served by the UAVs, is maximized, subject to the constraint that the number of people served by each UAV is no greater than its service capacity. We then propose a novel $O\left({\sqrt {\frac {s}{K}}}\right)$ -approximation algorithm for the problem, where $s$ is a given positive integer with $1 \le s\le K$ , e.g., $s=3$ . We also devise an improved heuristic, based on the approximation algorithm. We finally evaluate the performance of the proposed algorithms. Experimental results show that the numbers of users served by UAVs in the solutions delivered by the proposed algorithms are increased by 25% than state-of-the-arts.

Series compensation is an effective way to reduce the dc side passive filters of diode rectifier (DR), but the stability judgement of such series compensation system (SCS) by the impedance-ratio-based stability criteria is complicated, because this kind of system has many cascade forms and complex coupling interactions. This article proposes a stability analysis method for the SCS composed of DR and series voltage compensator, based on which an impedance optimization strategy is present to solve the instability problem. First, the simplified two-port small-signal model of SCS is established. The stability analysis is based on common characteristics of the system, which can fully reveal the dc bus oscillation mechanism combined with equivalent loop gain and the stable condition can be obtained for control system optimization. From the point of view of reshaping the impedance of series loop, a virtual-impedance-based control strategy with simple implementation is adopted to improve the system stability without affecting its dynamic performance, and the controller and parameters design are given considering the requirements of impedance optimization. An experimental prototype is established to validate the accuracy of stability analysis and the effectiveness of proposed control.

To unveil the hidden value in the datasets of user equipments (UEs) while preserving user privacy, federated learning (FL) is emerging as a promising technique to train a machine learning model using the datasets of UEs locally without uploading the datasets to a central location. Customers require to train machine learning models based on different datasets of UEs, through issuing FL requests that are implemented by FL services in a mobile edge computing (MEC) network. A key challenge of enabling FL in MEC networks is how to minimize the energy consumption of implementing FL requests while guaranteeing the accuracy of machine learning models, given that the availabilities of UEs usually are uncertain. In this paper, we investigate the problem of energy minimization for FL in an MEC network with uncertain availabilities of UEs. We first consider the energy minimization problem for a single FL request in an MEC network. We then propose a novel optimization framework for the problem with a single FL request, which consists of (1) an online learning algorithm with a bounded regret for the UE selection, by considering various contexts (side information) that influence energy consumption; and (2) an approximation algorithm with an approximation ratio for the aggregator placement for a single FL request. We third deal with the problem with multiple FL requests, for which we devise an online learning algorithm with a bounded regret. We finally evaluate the performance of the proposed algorithms by extensive experiments. Experimental results show that the proposed algorithms outperform their counterparts by reducing at least 13% of the total energy consumption while achieving the same accuracy.

In this paper, we study the employment of a mobile charger to charge lifetime-critical sensors under the multi-node partial-charging model, in which the charger can simultaneously charge the sensors within its charging range and each sensor may be partially charged each time. We notice that existing studies only scheduled the charger to minimize the number of dead sensors, but did not consider the charging scheduling for the sensors that have already run out of their energy, and the dead sensors will be last charged by the mobile charger. Then, their dead durations may be very long. In this paper, we consider not only how to minimize the number of dead sensors but also reduce the dead durations of sensors. To this end, we first formulate a sensor lifetime maximization problem, which is to find a charging tour for a mobile charger to charge sensors, such that the sum of sensor lifetimes is maximized. We then propose a novel $\frac{1}{3}$13-approximation algorithm for the problem. We finally evaluate the performance of the proposed algorithm through experiments. Experimental results show that both the average and maximum sensor dead durations by the proposed algorithm are up to 70% shorter than those by existing algorithms.