Detecting the faults related to the operating condition of induction motors is a very important task for avoiding system failure. In this paper, a novel methodology is demonstrated to detect the working condition of a three-phase induction motor and classify it as a faulty or healthy motor. The electrical current signal data is collected for five different types of fault and one normal operating condition of the induction motors. The first part of the methodology illustrates a pattern recognition technique based on the empirical wavelet transform, to transform the raw current signal into two dimensional (2-D) grayscale images comprising the information related to the faults. Second, a deep CNN (Convolutional Neural Network) model is proposed to automatically extract robust features from the grayscale images to diagnose the faults in the induction motors. The experimental results show that the proposed methodology achieves a competitive accuracy in the fault diagnosis of the induction motors and that it outperformed the traditional statistical and other deep learning methods.

This paper aims to investigate the techno-economic feasibility analysis of stand-alone diesel system, stand-alone PV/storage system, PV/diesel hybrid system, PV/diesel/storage hybrid system for the Pratas island in Taiwan. The power supply of outlying islands in Taiwan still use fossil fuel generators. The fuel cost is higher than that of on shore of Taiwan, and it has a great impact on the environment. This problem can be mitigated by hybrid energy systems. Through the investigation to know the existing generator set and Photovoltaic (PV) operating status, load consumption, etc., the study collects the required data for statistical meteorological analysis and economic analysis, and uses Hybrid Optimization Models for Energy Resources (HOMER) to simulate techno-economics of the stated hybrid energy systems. The analysis contains the capital cost, net present cost (NPC), cost of energy (COE) and fuel saving in different capacities for each power supply system with different constraints. From the simulation results, the lowest COE is 0.3569 $/kWh that can be found at the PV/diesel hybrid system configuration scheme with a total PV system capacity of 200 kWp, the renewable fraction (RF) is 15.3% and the excess electricity fraction is 2.6%, which is lower than the generally acceptable 5%. Although the COE of PV/diesel/storage hybrid is higher than that of stand-alone diesel system, the annual total CO2 emissions is reduced by 31.63%, which is of great benefit to environmental protection.

Renewable energy sources; which are abundant in nature and climate friendly are the only preferable choice of the world to provide green energy. The limitation of most renewable energy sources specifically wind and solar PV is its intermittent nature which are depend on wind speed and solar irradiance respectively and this leads to power fluctuations. To compensate and protect sensitive loads from being affected by the power distribution side fluctuations and faults, dynamic voltage restorer (DVR) is commonly used. This research work attempts to withstand and secure the effect of voltage fluctuation of grid connected hybrid PV-wind power system. To do so battery and super magnetic energy storage (SMES) based DVR is used as a compensating device in case of voltage sag condition. The compensation method used is a pre-sag compensation which locks the instantaneous real time three phase voltage magnitude and angle in normal condition at the point of common coupling (PCC) and stores independently so that during a disturbance it used for compensation. Symmetrical and asymmetrical voltage sags scenario are considered and compensation is carried out using Power System Computer Aided Design or Electro Magnetic Transient Design and Control (PSCAD/EMTDC) software.

Promoting the development of green technologies and replacing fossil fuel vehicles with electric ones can abate the environmental anxieties and issues associated with energy supply security. The increasing demand for electric vehicles requires an upgrade and expansion of the available charging infrastructure to accommodate the fast public adoption of this type of transportation. Ethiopia set a pro-electric cars policy and made them excise-free even before the first electric vehicle charging stations were launched by Marathon Motors Engineering in 2021. This paper presents the first ever technical, economic and environmental evaluation of electric vehicle charging stations powered by hybrid intermittent generation systems in three cities in Ethiopia. This paper tests this model using three different battery types: Lead-acid (LA), Flow-Zince-Bromine (ZnBr) and Lithium-ion (LI), used individually. Using these three battery technologies, the proposed hybrid systems are then compared in terms of system sizing, economy, technical performance and environmental stability. The results show that the feasible configuration of Solar Photovoltaic (PV)/Diesel Generator (DG)/ZnBr battery systems provide the lowest net present cost (NPC), with values of $2.97M, $2.72M and $2.85M, and cost of energy (COE), with values $0.196, $0.18 and $0.188, in Addis Ababa, Jijiga and Bahir Dar, respectively. Of all feasible systems, the Wind Turbine (WT)/PV/LI, PV/LI and WT/PV/LI configurations have the highest values of NPC and COE in Addis Ababa, Jijiga and Bahir Dar. Using this configuration, the results demonstrate that ZnBr battery is the most favorable choice because the economic parameters, including total NPC and COE, are found to be lowest.

Fault location with the highest possible accuracy has a significant role in expediting the restoration process, after being exposed to any kind of fault in power distribution grids. This paper provides fault detection, classification, and location methods using machine learning tools and advanced signal processing for a radial distribution grid. The three-phase current signals, one cycle before and one cycle after the inception of the fault are measured at the sending end of the grid. A discrete wavelet transform (DWT) is employed to extract useful features from the three-phase current signal. Standard statistical techniques are then applied onto DWT coefficients to extract the useful features. Among many features, mean, standard deviation (SD), energy, skewness, kurtosis, and entropy are evaluated and fed into the artificial neural network (ANN), Multilayer perceptron (MLP), and extreme learning machine (ELM), to identify the fault type and its location. During the training process, all types of faults with variations in the loading and fault resistance are considered. The performance of the proposed fault locating methods is evaluated in terms of root mean absolute percentage error (MAPE), root mean squared error (RMSE), Willmott’s index of agreement (WIA), coefficient of determination ( ${\mathrm{R}}^2$ ), and Nash-Sutcliffe model efficiency coefficient (NSEC). The time it takes for training and testing are also considered. The proposed method that discrete wavelet transforms with machine learning is a very accurate and reliable method for fault classifying and locating in both a balanced and unbalanced radial system. 100% fault detection accuracy is achieved for all types of faults. Except for the slight confusion of three line to ground (3LG) and three line (3L) faults, 100% classification accuracy is also achieved. The performance measures show that both MLP and ELM are very accurate and comparative in locating faults. The method can be further applied for meshed networks with multiple distributed generators. Renewable generations in the form of distributed generation units can also be studied.

As the cost of the battery energy storage system (BESS) is lower, the penetration rate of battery storage is rising in the behind-the-meter (BTM) market. BESS with time-of-use rates (TOU) for charge and discharge scheduling can be used to reduce electricity costs. This research uses 6,600KW contract capacity for industrial customers as the study case. Through the BESS techno-economic simulation in Hybrid Optimization Models for Energy Resources (HOMER) Grid software, the optimal capacity planning can be obtained from the electricity demand. The results show that the contract capacity can be adjusted to 6,100kW with a project benefit of $68,557, levelized cost of energy (LCOE) of 0.09338 $/kWh, net present cost (NPC) of $−$24,768,508, internal rate of return (IRR) of 3.72%, return of investment (ROI) of 2.16%, and discounted payback of 8.37 years in the 500kW/1065kWh required BESS capacity case. The sensitivity of the electricity price, key components cost, and real interest rate are evaluated and the method will be applied as a reference for planning the BTM BESS of other utility customers.