The Lightweight Edge-Side Fault Diagnosis Approach Based on Spiking Neural Network

Network fault diagnosis methods play a vital role in maintaining network service quality and enhancing user experience as an integral component of intelligent network management.Considering the unique characteristics of edge networks,such as limited resources,complex network faults,and the need for high real-time performance,enhancing and optimizing existing network fault diagnosis methods is necessary.Therefore,this paper proposes the lightweight edge-side fault diagnosis approach based on a spiking neural network(LSNN).Firstly,we use the Izhikevich neurons model to replace the Leaky Integrate and Fire(LIF)neurons model in the LSNN model.Izhikevich neurons inherit the simplicity of LIF neurons but also possess richer behavioral characteristics and flexibility to handle diverse data inputs.Inspired by Fast Spiking Interneurons(FSIs)with a high-frequency firing pattern,we use the parameters of FSIs.Secondly,inspired by the connection mode based on spiking dynamics in the basal ganglia(BG)area of the brain,we propose the pruning approach based on the FSIs of the BG in LSNN to improve computational efficiency and reduce the demand for computing resources and energy consumption.Furthermore,we propose a multiple iterative Dynamic Spike Timing Dependent Plasticity(DSTDP)algorithm to enhance the accuracy of the LSNN model.Experiments on two server fault datasets demonstrate significant precision,recall,and F1 improvements across three diagnosis dimensions.Simultaneously,lightweight indicators such as Params and FLOPs significantly reduced,showcasing the LSNN’s advanced performance and model efficiency.To conclude,experiment results on a pair of datasets indicate that the LSNN model surpasses traditional models and achieves cutting-edge outcomes in network fault diagnosis tasks.

Residential Energy Scheduling for Variable Weather Solar Energy Based on Adaptive Dynamic Programming

The residential energy scheduling of solar energy is an important research area of smart grid. On the demand side, factors such as household loads, storage batteries, the outside public utility grid and renewable energy resources, are combined together as a nonlinear, time-varying, indefinite and complex system, which is difficult to manage or optimize. Many nations have already applied the residential real-time pricing to balance the burden on their grid. In order to enhance electricity efficiency of the residential micro grid, this paper presents an action dependent heuristic dynamic programming(ADHDP) method to solve the residential energy scheduling problem. The highlights of this paper are listed below. First,the weather-type classification is adopted to establish three types of programming models based on the features of the solar energy. In addition, the priorities of different energy resources are set to reduce the loss of electrical energy transmissions.Second, three ADHDP-based neural networks, which can update themselves during applications, are designed to manage the flows of electricity. Third, simulation results show that the proposed scheduling method has effectively reduced the total electricity cost and improved load balancing process. The comparison with the particle swarm optimization algorithm further proves that the present method has a promising effect on energy management to save cost.

Dynamic Slicing of Object Oriented Programs

Program slice has many applications such as program debugging, testing, maintenance, and complexity measurement. A static slice consists of all statements in program P that may effect the value of variable v at some point p , and a dynamic slice consists only of statements that influence the value of variable occurrence for specific program inputs. In this paper, we concern the problem of dynamic slicing of object oriented programs which, to our knowledge, has not been addressed in the literatures. To solve this problem, we present the dynamic object oriented dependence graph (DODG)which is an arc classified digraph to explicitly represent various dynamic dependence between statement instances for a particular execution of an object oriented program. Based on the DODG, we present a two phase backward algorithm for computing a dynamic slice of an object oriented program.

Analysis of SIRVI model with time dependent coefficients and the effect of vaccination on the transmission rate and COVID-19 epidemic waves

COVID-19 epidemic models with constant transmission rate cannot capture the patterns of the infection data in the presence of pharmaceutical and non-pharmaceutical interventions during a pandemic.Because of this,a new modification of SIR model that contain the vaccination compartment with time dependent coefficients and weak/lossimmunity is explored.Literature review confirms that the effect of vaccination on the time dependent transmission rate is still an open problem.This study answers this open problem.In this study,we first prove the well-posedness and investigate the model dynamics to show their continuous dependence on the model parameters.We then provide an algorithm to derive the time-dependent transmission function for the epidemiologic model and the data of the infected cases.The derived coupled nonlinear differential equations show the effect of vaccination on the transmission rate.Unlike previous studies,we first filter the published data and solve the nonlinear coupled differential equations using the finite difference technique,where the coefficient of the coupled nonlinear differential equations is a function of given data.We then show that time-dependent transmission function can be represented by linear combinations of Gaussian radial base function.We then validate the prediction of our models using numerical simulations,where we used the published data of COVID-19 confirmed cases by the Ministries of Health in Saudi Arabia and Poland.Finally,the numerical solutions of a SIRVI model with time dependent transmission rate show that the waves for currently active cases are in good agreement with the data of Saudi Arabia and Poland.

INS stochastic error detection during kinematic tests and impacts on INS/GNSS performance

Inertial Navigation System(INS)and Global Navigation Satellite System(GNSS)integration requires accurate modelling of both INS deterministic and stochastic errors.The Allan Variance(AV)analysis on INS static data is one method of determining INS stochastic errors.However,it is known that INS errors can vary depending on a vehicle’s motion and environment,and application of AV results from static data in kinematic operations typically results in an over-confident estimation of stochastic.In order to overcome this limitation,this paper proposes the use of Dynamic Allan Variance(DAV).The paper compares the resulting performance of the INS/GNSS integrated system by varying the stochastic coefficients obtained from the AV and DAV.The results show that the performance improved when utilizing the stochastic coefficients obtained from the DAV,applied on a kinematic dataset compared to the AV,applied on a static laboratory dataset.