Deep learning-based forecasting of electricity consumption.

Building energy management systems (BEMS) are integrated computerized systems that track and manage the energy use of many pieces of building-related machinery and equipment, including lighting, power systems, and HVAC systems. Modern buildings must have BEMSs in order to reduce energy usage while maintaining comfort. Not only for energy-saving purposes, BEMS is essential in enhancing the quality of the energy supply, which helps to gain a better understanding of how energy is used and the building's energy usage. When the dynamics of a building's energy usage are known, it is possible to determine which changes are most likely to reduce consumption. Numerous connected devices, operating modes, energy usage, and environmental factors can all be monitored and controlled in real-time using BEMS. Changing operating times and setting points to maximize comfort and efficiency is made simple by this. In this paper, we have primarily addressed the two significant issues of model optimization and electricity consumption forecasts. Future forecasting has been done using the LSTM based time series approach. We generated data on the amount of electricity consumed by a hospital facility and tested our suggested methodologies on actual data. The findings gained demonstrated that the strategies were successful with both types of data. On actual data, the trend in electricity consumption can be accurately predicted. Several model optimizers enhanced the suggested methods' performance as well. Our objective function gain accuracy result of 95%.

Assessing the reliability and degradation of 10-35 years field-aged PV modules.

The objective of this study was to conduct a reliability analysis on photovoltaic (PV) modules from the oldest PV installation site in Pakistan. Four sets of modules; Type A & B (30 years old), Type C (10 years old), and Type D (35 years old) were identified for this analysis. It has been observed that modules have shown degradation after working for a good number of years in the field. Comparing with nameplate data (available for Type B & C only), a drop of 28.68% and 2.99 percentage points (pp) was observed in the output power (Pmax) and efficiency (Eff.) respectively for Type B, while a drop of 22.21% and 4.05 pp was observed in Pmax and Eff. respectively for Type C. A greater drop in ISC and Pmax was observed in Type B, which is attributed to severe browning of EVA in them. While the greater drop in Pmax, in case of Type C, is attributed to the poor quality of materials used. Amongst the different defects observed, the junction box defects which include cracking and embrittlement, etc., and backsheet defects which include discoloration, delamination and cracking, etc. were found in all four types of modules. Other defects include browning of EVA, observed in Type B and D, and corrosion of frame and electrical wires, found in Type A, B, and D. This first-ever study will provide valuable information in understanding the degradation mechanism and henceforth, improving the long term reliability of PV modules in the humid-subtropical conditions of Pakistan.

Novel perovskite solar cell with Distributed Bragg Reflector.

This paper reports numerical modeling of perovskite solar cell which has been knotted with Distributed Bragg Reflector pairs to extract high energy efficiency. The geometry of the proposed cells is simulated with three different kinds of perovskite materials including CH3NH3PbI3, CH3NH3PbBr3, and CH3NH3SnI3. The toxic perovskite material based on Lead iodide and lead bromide appears to be more efficient as compared to non-toxic perovskite material. The executed simulated photovoltaic parameters with the highest efficient structure are open circuit voltage = 1.409 (V), short circuit current density = 24.09 mA/cm2, fill factor = 86.18%, and efficiency = 24.38%. Moreover, a comparison of the current study with different kinds of structures has been made and surprisingly our novel geometry holds enhanced performance parameters that are featured with back reflector pairs (Si/SiO2). The applied numerical approach and presented designing effort of geometry are beneficial to obtain results that have the potential to address problems with less efficient thin-film solar cells.

A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal.

Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional neural network (CNN) with two convolutional layers, two down-sampling layers, and a fully connected layer is proposed in this work. The same 1D data was transformed into two-dimensional (2D) images to improve the model's classification accuracy. Then, we applied the 2D CNN model consisting of input and output layers, three 2D-convolutional layers, three down-sampling layers, and a fully connected layer. The classification accuracy of 97.38% and 99.02% is achieved with the proposed 1D and 2D model when tested on the publicly available Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Both proposed 1D and 2D CNN models outperformed the corresponding state-of-the-art classification algorithms for the same data, which validates the proposed models' effectiveness.

Optimization of CNN through Novel Training Strategy for Visual Classification Problems.

The convolution neural network (CNN) has achieved state-of-the-art performance in many computer vision applications e.g., classification, recognition, detection, etc. However, the global optimization of CNN training is still a problem. Fast classification and training play a key role in the development of the CNN. We hypothesize that the smoother and optimized the training of a CNN goes, the more efficient the end result becomes. Therefore, in this paper, we implement a modified resilient backpropagation (MRPROP) algorithm to improve the convergence and efficiency of CNN training. Particularly, a tolerant band is introduced to avoid network overtraining, which is incorporated with the global best concept for weight updating criteria to allow the training algorithm of the CNN to optimize its weights more swiftly and precisely. For comparison, we present and analyze four different training algorithms for CNN along with MRPROP, i.e., resilient backpropagation (RPROP), Levenberg-Marquardt (LM), conjugate gradient (CG), and gradient descent with momentum (GDM). Experimental results showcase the merit of the proposed approach on a public face and skin dataset.