This article presents a cascaded three-level voltage source converter (VSC) based STATCOM employing an artificial neuron network (ANN) controller with a new simple circuit of space vector pulse width modulation (SVPWM) technique. The main aim of utilizing ANN controller and SVPWM technique is to minimize response time (RT) of STATCOM and improve its performance regard to PF amplitude, and total harmonic distortion (THD) of VSC output current during the period of lagging/leading PF loads (inductive/capacitive loads). The performance of STATCOM is tested using MATLAB/SIMULINK in IEEE 3-bus system. The simulation results clearly proved that the STATCOM with intelligent controller is more efficient compared to a conventional controller (PI controller), where ANN enables the voltage and current to be in the same phase rapidly (during 1.5 cycles) with THD less than 5%.
<span>This paper proposes a shunt hybrid power filter (HPF) for harmonic currents and reactive power compensation under a distorted voltage and in a polluted environment. For this purpose, the reference current of the shunt HPF is computed based on the instantaneous reactive power (p-q) theory with self-tuning filter (STF). In order to adjust the dc voltage as a reference value, PI and ANN controllers have been utilized. Moreover, the system has been implemented and simulated in a MATLAB-SIMULINK platform, and selected results are presented. Therefore, the results verified the good dynamic performance, transient stability and strong robustness of the ANN controller. Furthermore, the shunt HAPF with ANN controller has been found to be in agreement with the IEEE 519-1992 standard recommendations on harmonic levels.</span>
Deep neural networks (DNNs) have been successfully deployed in widespread domains, including healthcare applications. DenseNet201 is a new DNN architecture used in healthcare systems (i.e., presence detection of the surgical tool). Specialized accelerators such as GPUs have been used to speed up the execution of DNNs. Nevertheless, GPUs are prone to transient effects and other reliability threats, which can impact DNN models' reliability. Safety-critical systems, such as healthcare applications, must be highly reliable because minor errors might lead to severe injury or death. In this paper, we propose a selective mitigation technique that relies on in-depth analysis. First, we inject the DenseNet201 model implemented on a GPU via NVIDIA's SASSIFI fault injector. Second, we perform a comprehensive analysis from the perspective of kernel and layer to identify the most vulnerable portions of the injected model. Finally, we validate our technique by applying it to the top-vulnerable kernels to selectively protect the only sensitive portions of the model to avoid unnecessary overheads. Our experiments demonstrate that our mitigation technique achieves a significant reduction in the percentage of errors that cause malfunction (errors that lead to misclassification) from 6.463% to 0.21%. Moreover, the performance overhead (the execution time) of our technique is compared with the well-known protection techniques: Algorithm-Based Fault Tolerance (ABFT), Double Modular Redundancy (DMR), and Triple Modular Redundancy (TMR). The proposed solution shows only 0.3035% overhead compared to these techniques while correcting up 84.8% of the SDC errors in DenseNet201, remarkably improving the healthcare domain's model reliability.
Location is an indispensable segment for WirelessSensor Network (WSN), since when events happened, we need to know location. The distance vector-hop (DV-Hop) technique is a popular range-free localization algorithm due to its cost efficiency and non-intricate process. Nevertheless, it suffers from poor accuracy, and it is highly influenced by network topology; Especially, more hop counts lead to more errors. In the final phase, least squares are employed to address nonlinear equation, which will gain greater location errors. Aimed at addressing problems mentioned above, an enhanced DV-Hop algorithm based on weighted factor, along with new weighted least squares location technique, is proposed in this paper, and it is called WND-DV-Hop. First, the one hop count of unknown node was corrected by employed received signal strength indication (RSSI) technology. Next, in order to reduce average hop distance error, a weighted coefficient based on beacon node hop count was constructed. A new weighted least squares method was embedded to solve nonlinear equation problem. Finally, considerable experiments were carried out to estimate the performance of WND-DV-Hop, compared the outcomes with state-of-the-art DV-Hop, IDV-Hop, Checkout-DV-Hop, and New-DV-Hop depicted in literature. The empirical findings demonstrated that WND-DV-Hop significantly outperformed other localization algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.