Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Frilled Lizard Optimization: A Novel Bio-Inspired Optimizer for Solving Engineering Applications

This research presents a novel nature-inspired metaheuristic algorithm called Frilled Lizard Optimization(FLO),which emulates the unique hunting behavior of frilled lizards in their natural habitat.FLO draws its inspiration from the sit-and-wait hunting strategy of these lizards.The algorithm’s core principles are meticulously detailed and mathematically structured into two distinct phases:(i)an exploration phase,which mimics the lizard’s sudden attack on its prey,and(ii)an exploitation phase,which simulates the lizard’s retreat to the treetops after feeding.To assess FLO’s efficacy in addressing optimization problems,its performance is rigorously tested on fifty-two standard benchmark functions.These functions include unimodal,high-dimensional multimodal,and fixed-dimensional multimodal functions,as well as the challenging CEC 2017 test suite.FLO’s performance is benchmarked against twelve established metaheuristic algorithms,providing a comprehensive comparative analysis.The simulation results demonstrate that FLO excels in both exploration and exploitation,effectively balancing these two critical aspects throughout the search process.This balanced approach enables FLO to outperform several competing algorithms in numerous test cases.Additionally,FLO is applied to twenty-two constrained optimization problems from the CEC 2011 test suite and four complex engineering design problems,further validating its robustness and versatility in solving real-world optimization challenges.Overall,the study highlights FLO’s superior performance and its potential as a powerful tool for tackling a wide range of optimization problems.

Accurate threat hunting in industrial internet of things edge devices

Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and processing.Any kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire IIoT.Moreover,they can allow malicious software installed on end nodes to penetrate the network.This paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge devices.The proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority voting.Experimental evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.

Fault Detection for Microgrid Feeders Using Features Based on Superimposed Positive-sequence Power

With the integration of distributed generation(DG) into a microgrid, fault detection has become a major task to accomplish. A scheme for microgrid feeder protection based on a newly proposed feature, ΔRP, defined as the ratio of the sum of positive-sequence real power(PSRP) at the two ends of the feeder to the larger of the PSRPs among the two ends, is proposed. If ΔRP is larger than a threshold, an internal fault is detected;otherwise, the fault is external or there is no fault. The proposed scheme is tested in various scenarios, including fault type, fault resistance, fault location, fault inception angle, varying DG penetration levels, and simultaneous, evolving, and composite faults. In addition to this, the proposed scheme offers a robust performance when subjected to noise, synchronization error, changes in sampling frequency, and changes in the topology of a microgrid. The dominancy of the proposed scheme is proven by a comprehensive comparative study with various available recent schemes. Test results on the IEEE 13-bus network indicate the viability of the proposed protection scheme for a microgrid. Finally, the proposed scheme has been validated on a real-time simulator.