One of the main challenges of integrating distributed generation into the power grid is islanding, which occurs when a disconnected power line is adversely energized by a local distributed generation source. If islanding is not quickly detected, it can present serious safety and hazardous conditions. Conventional passive detection techniques used today are entirely dependent on the parameters of the power system, which under certain operating conditions may fail to detect islanding. In this paper, a novel and efficient passive islanding detection technique for grid-connected photovoltaic-based inverters is presented. In this technique, the ripple content of the inverter output voltage at the point of common coupling is monitored for deviations using time-domain spectral analysis. Islanding is then detected whenever the ripple spectral content exceeds a preset threshold level for a certain period of time. The performance of this technique was extensively tested and quantified under a wide range of operating conditions. It was determined that the proposed technique did not exhibit any non-detection zone and was able to detect all types of islanding cases within 300 ms of the allowed delay time. Furthermore, the proposed technique was found to be robust and inherently immune to other degrading factors, since it is relatively independent of system parameters, power system scaling, or the number of distributed generation sources present within the islanding zone.

Distributed Generation (DG) sources have become an integral part of today’s decentralized power systems. However, current DG systems are mostly passive and do not provide intelligent information to help detect power quality issues. In this paper, a novel and intelligent event classification scheme is proposed to provide DG systems with real-time decision making capabilities. The proposed technique has the ability to provide information to help maintain the quality and reliability of DG systems under various disturbances or operating conditions. This event classification technique was developed using artificial neural networks (ANN) with a pre-defined set of local input parameters. The algorithm is implemented using four parallel ANNs that were designed to operate under a majority vote fusion algorithm representing the final classification output. A total of 310 event cases were generated to test the performance of the proposed technique. Simulation results showed that events were accurately classified within 10 cycles of their occurrences while achieving a 96.21% average classification accuracy.

Pneumonia is a life-threatening respiratory disease caused by bacterial infection. The goal of this study is to develop an algorithm using Convolutional Neural Networks (CNNs) to detect visual signals for pneumonia in medical images and make a diagnosis. Although Pneumonia is prevalent, detection and diagnosis are challenging. The deep learning network AlexNet was utilized through transfer learning. A dataset consisting of 5659 images was used for training, and a preliminary diagnosis accuracy of 72% was achieved.

The use of mobile devices has exponentially expanded in recent years. A device which was made with the sole purpose of making mobile audio phone calls is now the leading basis for functionality in the social world. The types of applications widely vary from audio and video calls, internet browsing, healthcare applications, to mobile games with online connectivity, among many others. These applications have expanded the original idea of what a mobile device could be, however there have been constant drawbacks to these devices, namely short battery life and limited available storage memory. Another current issue that exists with mobile devices is the higher data consumption when on mobile network data. To solve this problem, it is possible to use cloud computing to mitigate these large applications and use less data. Integrating in a mobile cloud system to allocate and store these applications will allow for the mobile devices to conserve battery and memory by avoiding large computational processes. Another major concern is security breaches resulting in data theft and/or invasion of privacy. In this paper, we present a new framework that will allow for a smart load balancer to efficiently allocate resources to increase application processing speed for data and request response of memory stored by mobile devices in a secure manner.

Residences consume a significant amount of electrical power. Unfortunately, some of it goes to waste as homeowners often unintentionally consume excessive amounts of power. Home energy management systems aid homeowners in their power consumption decisions by measuring their power consumption and presenting that information in a user-friendly format. In this paper, we propose the enhancement of the Pico-Grid Smart Home Energy Management System by using Mel Frequency Cepstral Coefficients. It is a consumer-grade energy management system capable of identifying loads by analyzing current draw and is distinguished from other home energy management systems by its incorporation of a novel hardware design created to ensure reliable sampling and a classifier consisting of several artificial neural networks (ANN). Each neural network corresponds to a classified device which allows the system to be trained to recognize additional devices without having to re-train the entire existing network. The classifier converts the current signal to the Mel-spaced Cepstrum domain in order to extract relevant features achieving an overall classification accuracy of 97.8% with average positive and negative predictive values of 93.2% and 98.7% respectively. This enables the system to potentially have a lower cost but higher accuracy than other similar designs that have been suggested thus far. This system aids homeowners in making energy-conscious decisions such as monitoring the energy costs of their home appliances and scheduling heavy loads during periods of low demand.

This paper proposes to design a small-scale photovoltaic system to regulate, store, convert and manage solar power for use in residential settings. The system utilizes a solar panel to supply power to batteries and an AC inverter. Batteries’ energy is used to satisfy the power needs of a standard household. The proposed constructed system is a scaled down physical model. The system consists of a programmable controller, photovoltaic panel, a buck converter used to charge the batteries, and a single-phase inverter to supply power for the residential loads. The controller monitors every aspect of the system including battery voltage and solar panel voltage and then determines where the home needs to draw its power from. The control system also plays a vital role in the buck converter design. An input from the solar panel is connected to the system, which then determines the duty cycle needed to step down the voltage from the panel to an acceptable and safe voltage to charge the battery. This design of a Photovoltaic system is able to meet the power demanded by an average house located in Statesboro, Georgia, and thus reduce the load on the municipal power grid.