Fault diagnosis in photovoltaic (PV) arrays is essential in enhancing power output as well as the useful life span of a PV system. Severe faults such as Partial Shading (PS) and high impedance faults, low location mismatch, and the presence of Maximum Power Point Tracking (MPPT) make fault detection challenging in harsh environmental conditions. In this regard, there have been several attempts made by various researchers to identify PV array faults. However, most of the previous work has focused on fault detection and classification in only a few faulty scenarios. This paper presents a novel approach that utilizes deep two-dimensional (2-D) Convolutional Neural Networks (CNN) to extract features from 2-D scalograms generated from PV system data in order to effectively detect and classify PV system faults. An in-depth quantitative evaluation of the proposed approach is presented and compared with previous classification methods for PV array faults – both classical machine learning based and deep learning based. Unlike contemporary work, five different faulty cases (including faults in PS – on which no work has been done before in the machine learning domain) have been considered in our study, along with the incorporation of MPPT. We generate a consistent dataset over which to compare ours and previous approaches, to make for the first (to the best of our knowledge) comprehensive and meaningful comparative evaluation of fault diagnosis. It is observed that the proposed method involving fine-tuned pre-trained CNN outperforms existing techniques, achieving a high fault detection accuracy of 73.53%. Our study also highlights the importance of representative and discriminative features to classify faults (as opposed to the use of raw data), especially in the noisy scenario, where our method achieves the best performance of 70.45%. We believe that our work will serve to guide future research in PV system fault diagnosis.

Faults detection and analysis in PV system are considered critical for ensuring safety and increasing output power of PV arrays. PV faults do not only reduce output power and efficiency but also lessen the working life time of a system. Most common and chronic PV faults are line to line, line to ground, shadowing fault, and arc fault while less common and acute faults are hotspot, degradation, bypass diode, and connection faults. Event of PV fault detection failures, such as most recent in Mount Holly, USA in 2011 evinced the improvement in current fault detection and mitigation techniques to shrink such failures. There are various limitations in the existing fault detection techniques, as identified in this paper, which may cause misdetection of the faults. This paper is focused on mathematical formulation of various PV faults and lead to the latter’s critical analysis in terms of efficiency, accuracy, complexity, and reliability. The presented work also helps to identify nature and causes of occurrence of a PV fault. This research work serves as a special set of references and recommendations for researchers and PV manufacturing industry to improve fault detection prospects in solar PV systems.

Categorization of PV faults is an essential task for improving the efficiency and reliability of a photovoltaic (PV) system. Output characteristics of a solar (PV) system can be severely affected under various fault conditions including short circuit, module mismatch, open circuit, and multiple faults under shading conditions. Such PV faults can potentially be analyzed through the PV characteristic curve analysis using a multilayer neural network with a scaled conjugate gradient algorithm (SCG). This paper presents an extensive investigation for categorization, i.e., classification of the above-mentioned PV faults using the SCG algorithm. The major contribution of the presented research work is the categorization of PV faults in sixteen different classes considering polycrystalline and thin-film PV technologies with two different configurations, including SP and TCT. The fault classification is achieved with high accuracy of 99.6% and a fast-computational time of 0.08 sec. The results are validated through the plot of the Confusion Matrix and Region of Convergence (ROC) with their performance evaluation in MATLAB. The achieved accuracy and fast computational time prove the effectiveness of the multilayer neural network-based approach for classification of the PV faults to increase power output, efficiency, and lifespan of PV systems.

A huge body of research is concentrated on developing advance load control strategies for reducing energy consumption and ensuring smooth operation of power system. Air conditioning loads are considered major energy consuming electrical loads in residential and business buildings, and that may cause significant rise in energy consumption. This paper presents an implementation of fuzzy controller with different number and shapes of membership functions for smoothing energy consumption of an air conditioning load while dealing with thermal disturbances. Simulations are conducted in MATLAB Simulink and the results demonstrate that the fuzzy controller with triangular membership function gives the desired performance with an error of less than 1% and saves 25% energy consumption. The obtained results are found effective in terms of smoothing energy consumption pattern of an air conditioning load without compromising consumer’ s comfort. Performance of the designed controller is also compared with different controllers including self-tuning adaptive fuzzy controller, linear quadratic regulator (LQR) and nonlinear controllers. The presented fuzzy controller stands-out in terms of desired performance, simplicity and implementation.

Electric mobility seems to bring a paradigm shift in the road transport sector worldwide. Huge consumption of fossil fuels and ever-increasing traffic congestion have caused concerns over future energy consumption, economy growth, and greenhouse gas emissions in the Gulf Cooperation Council region’s member countries. The introduction of electric vehicles (EVs) in the two most populous countries of the region, i.e., the Kingdom of Saudi Arabia and UAE is considered a promising option to address environmental pollution and future economy-related fears region. This paper presents key drivers for the countries to adopt electric transportation. This research study investigates the impact of EVs penetration on energy, economy, and environment of KSA and UAE through EV stockpile forecasting using linear regression analysis. The obtained results suggest that expected growth in KSA and UAE’s power sector will enable them to keep up 5% and 30% EVs penetration by 2030, respectively. In this regard, a set of policies are proposed, which will enable the countries to pace up their efforts to achieve the intended greenhouse gases (GHG) emission reduction goals. Though the presented research is focused on the case study of KSA and UAE, the research findings are generalized enough to be applied to all other regions of the region. The suggested set of policies will serve as guidelines for the relevant stakeholders about the necessary measures required for sustainable road transport electrification in KSA and UAE.

In the South Asian countries, including Bangladesh, India, and Pakistan, the current energy scenario is considered non-sustainable due to diverse issues such as economic, environmental, geopolitical, technological options for energy exploitation, and negligible volume of regional energy trade. Though, within the region, India is leading a phase of energy transition and economic transformation through renewable energy development. The countries need to exhibit well in the development of their renewable sources following the rapid pace of renewable energies worldwide. This paper offers an overview of the energy scenario, growth of renewable energies, evolution, and approach for energy policy by highlighting key challenges and barriers for the ecological energy mix of the countries. Importantly, the paper assesses the current energy mix in South Asia, highlighting the anomaly of its fossil fuel-based future outlook, its ambitions to move towards less environmental pollution, and sustainable energy mix through a strategic tool SWOT analysis; strengths, weaknesses, opportunities, and threats (SWOT). In particular, this study examines the government policies to expand the implementation of renewable sources with an insight into the existing regulatory structure of the energy sector. The presented research findings suggest that to achieve the ambitious target to reduce emission discharge by up to 30% by the year 2030 under Intended Nationally Determined Contributions (INDCs), the Governments of the three countries must take preemptive measures. It includes the stage-wise reduction of subsidies on fossil fuels, market integration within the region, and swift realization of the existing initiatives through strong political will, good governance, adoption of the latest technologies, and a pragmatic action plan, and energy cooperation across the region.