Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item Enhancing High-Frequency PV Power Forecast Using Optimal Hyperparameter Setting in LSTM(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, A.; Kashyap, Y.; Nasar, R.Solar energy plays a significant role in the world’s shift to renewable and sustainable energy. So, accurate forecasting techniques are essential for effective grid management and smooth integration into current energy infrastructures. Traditional solar forecasting approaches often encounter limitations in capturing the complex and nonlinear relationships inherent in solar power generation patterns. In response to these challenges, the present paper demonstrates the forecast analysis of high-frequency (HF) PV power components, which is obtained with the decomposition of actual PV power data. The focus of this paper is on the analysis of high-frequency PV power components as they exhibit high fluctuation. To capture this high fluctuation feature present in PV power, a moving average filter is applied to smooth the input data and potentially enhance the 60 min ahead forecasting performance using the long short-term memory (LSTM) model. The best-performing LSTM model has secured MAE= 1.114 % and RMSE = 2.608 % for 60 min ahead forecast. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.Item Enhancing Solar Energy Forecast Using Multi-Column Convolutional Neural Network and Multipoint Time Series Approach(MDPI, 2023) Kumar, A.; Kashyap, Y.; Kosmopoulos, P.The rapid expansion of solar industries presents unknown technological challenges. A dedicated and suitable energy forecast is an effective solution for the daily dispatching and production of the electricity grid. The traditional forecast technique uses weather and plant parameters as the model information. Nevertheless, these are insufficient to consider problematic weather variability and the various plant characteristics in the actual field. Considering the above facts and inspired by the excellent implementation of the multi-column convolutional neural network (MCNN) in image processing, we developed a novel approach for forecasting solar energy by transforming multipoint time series (MT) into images for the MCNN to examine. We first processed the data to convert the time series solar energy into image matrices. We observed that the MCNN showed a preeminent response under a ground-based high-resolution spatial–temporal image matrix with a 0.2826% and 0.5826% RMSE for 15 min-ahead forecast under clear (CR) and cloudy (CD) conditions, respectively. Our process was performed on the MATLAB deep learning platform and tested on CR and CD solar energy conditions. The excellent execution of the suggested technique was compared with state-of-the-art deep neural network solar forecasting techniques. © 2022 by the authors.Item Rooftop Photovoltaic Energy Production Estimations in India Using Remotely Sensed Data and Methods(MDPI, 2023) Kumar, A.; Kosmopoulos, P.; Kashyap, Y.; Gautam, R.We investigate the possibility of estimating global horizontal irradiance (GHI) in parallel to photovoltaic (PV) power production in India using a radiative transfer model (RTM) called libRadtran fed with satellite information on the cloud and aerosol conditions. For the assessment of PV energy production, we exploited one year’s (January–December 2018) ground-based real-time measurements of solar irradiation GHI via silicon irradiance sensors (Si sensor), along with cloud optical thickness (COT). The data used in this method was taken from two different sources, which are EUMETSAT’s Meteosat Second Generation (MSG) and aerosol optical depth (AOD) from Copernicus Atmospheric Monitoring Services (CAMS). The COT and AOD are used as the main input parameters to the RTM along with other ones (such as solar zenith angle, Ångström exponent, single scattering albedo, etc.) in order to simulate the GHI under all sky, clear (no clouds), and clear-clean (no clouds and no aerosols) conditions. This enabled us to quantify the cloud modification factor (CMF) and aerosol modification factor (AMF), respectively. Subsequently, the whole simulation is compared with the actual recorded data at four solar power plants, i.e., Kazaria Thanagazi, Kazaria Ceramics, Chopanki, and Bhiwadi in the Alwar district of Rajasthan state, India. The maximum monthly average attenuation due to the clouds and aerosols are 24.4% and 11.3%, respectively. The energy and economic impact of clouds and aerosols are presented in terms of energy loss (EL) and financial loss (FL). We found that the maximum EL in the year 2018 due to clouds and aerosols were 458 kWh m−2 and 230 kWh m−2, respectively, observed at Thanagazi location. The results of this study highlight the capabilities of Earth observations (EO), in terms not only of accuracy but also resolution, in precise quantification of atmospheric effect parameters. Simulations of PV energy production using EO data and techniques are therefore useful for real-time estimates of PV energy outputs and can improve energy management and production inspection. Success in such important venture, energy management, and production inspections will become much easier and more effective. © 2023 by the authors.Item Synthesis of BNiO3 Nanocomposites for Photocatalytic Hydrogen Production Applications(Springer, 2024) Choudhary, R.K.; Kumaraswamy, G.N.; Baitha, R.; Kumar, M.; Shekokar, S.R.; Kumar, A.; Hussain, M.H.; Kumar, P.The pursuit of sustainable and clean energy sources has prompted significant research efforts toward developing efficient photocatalytic materials for hydrogen production. In this study, we present a comprehensive review of the synthesis of BNiO3 nanocomposites and their potential application as efficient photocatalysts for hydrogen production. The synthesis of BNiO3 nanocomposites involves the integration of bismuth oxide (Bi2O3) and nickel oxide nanoparticles with boron nitride nanosheets. Various synthesis techniques have been employed to fabricate these nanocomposites, including sol–gel, hydrothermal, and co-precipitation methods. The choice of synthesis method significantly influences the nanocomposites' structural, morphological, and optical properties, thereby affecting their photocatalytic performance. The morphological characterization techniques, such as scanning electron microscopy, transmission electron microscopy, and X-ray diffraction, have been utilized to investigate the structural and morphological properties of BNiO3 nanocomposites. The photocatalytic activity of BNiO3 nanocomposites for hydrogen production has been extensively studied. The mechanism of hydrogen production involves the absorption of solar energy by the BNiO3 nanocomposites, followed by the generation of electron–hole pairs. This report provides valuable insights into the synthesis techniques, characterization methods, and photocatalytic performance of BNiO3 nanocomposites. Further research is warranted to optimize the synthesis parameters and explore novel strategies for enhancing the efficiency and stability of these nanocomposites, ultimately contributing to the development of sustainable energy solutions. © The Institution of Engineers (India) 2024.Item MSSEAG-UNet: A Novel Deep Learning Architecture for Cloud Segmentation in Fisheye Sky Images and Solar Energy Forecast(Institute of Electrical and Electronics Engineers Inc., 2025) Kumar, A.; Kashyap, Y.; Sharma, K.; Vittal, K.; Shubhanga, K.N.This study analyzes sky images captured using a ground-based fisheye camera, aiming to address the challenge of accurately segmenting clouds, which is difficult due to their fuzzy and indistinct boundaries and uneven lighting conditions. Accurate segmentation of clouds in ground-based sky images is crucial for accurate solar energy forecasting. Motivated by these challenges, this article has proposed a novel deep learning architecture called multispatial squeeze-and-excite attention gated U-Net (MSSEAG-UNet) for cloud segmentation in ground-based fisheye sky images. The proposed architecture integrates a multispatial convolutional (MS-CNN) block and squeeze-and-excitation (SE) blocks in the encoder path to improve multiscale feature extraction (MFF) and recalibrate feature maps, while an attention block is incorporated in the decoder path to emphasize key cloud features. The segmentation performance of the MSSEAG-UNet is compared with five benchmark models, and results show that the proposed model outperforms than all benchmarks models. Furthermore, the segmented cloud images produced by the MSSEAG-UNet are used to calculate the cloud percentage, which is then integrated with the original sky images using a multicolumn convolutional model for global horizontal irradiance (GHI) forecast. GHI forecast is conducted for 15-, 30-, and 60-min ahead timesteps, with the best results achieved for the 60-min forecast, yielding mean absolute error (MAE), mean square error (mse), and RMSE values of 6.245%, 0.683%, and 8.265%, respectively. These results highlight the effectiveness of the proposed approach in improving both cloud segmentation accuracy and short-term solar irradiance forecasting. © 1980-2012 IEEE.