Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Solar Radiation Assessment and Forecasting Using Satellite Data(Springer Nature, 2019) Masoom, A.; Kashyap, Y.; Bansal, A.Since the availability of ground data is very sparse, satellite data provides an alternative method to estimate solar irradiation. Satellite data across various spectral bands may be employed to distinguish weather signatures, such as dust, aerosols, fog, and clouds. For a tropical country like India, which is potentially rich in solar energy resources, the study of these parameters is of crucial importance from the perspective of solar energy. Furthermore, a complete utilization of the solar energy depends on its proper integration with power grids. Because of its variable nature, incorporation of photovoltaic energy into electricity grids suffers technical challenges. Solar radiation is subjected to reflection, scattering and absorption by air molecules, clouds, and aerosols in the atmosphere. Clouds can block most of the direct radiation. Modern solar energy forecasting systems rely on real-time Earth observation from the satellite for detecting clouds and aerosols. © 2019, Springer Nature Singapore Pte Ltd.Item Ensemble RDLR Architecture for Short-Term Solar Power Forecasting(Institute of Electrical and Electronics Engineers Inc., 2024) Ayappane, H.; Kashyap, Y.Given the drastic shift of global sentiment towards renewable energy, it becomes incredibly important to match supply with demand. However the highly variable nature of weather makes it difficult to accurately predict the output of a solar power plant. Through this paper, we will approach this problem by using an ensemble model consisting of both machine learning and neural networks (NN) as base models to forecast the amount of energy that needs to be produced by a solar plant over a short-term time horizon, which in our case will be 0 minute (immediate), 5 minute, 30 minute and 90 minute. Each base model is fine tuned to encourage high diversity and low correlation to improve prediction accuracy. The expected stability or generalization from RF-DNN combined with the memory retention capability of the LSTM network should provide an ideal predictor for time series forecasting of a stochastic process like weather. © 2024 IEEE.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 Rooftop photovoltaic energy production management in india using earth-observation data and modeling techniques(MDPI AG rasetti@mdpi.com Postfach Basel CH-4005, 2020) Masoom, A.; Kosmopoulos, P.; Kashyap, Y.; Kumar, S.; Bansal, A.This study estimates the photovoltaic (PV) energy production from the rooftop solar plant of the National Institute of Technology Karnataka (NITK) and the impact of clouds and aerosols on the PV energy production based on earth observation (EO)-related techniques and solar resource modeling. The post-processed satellite remote sensing observations from the INSAT-3D have been used in combination with Copernicus Atmosphere Monitoring Service (CAMS) 1-day forecasts to perform the Indian Solar Irradiance Operational System (INSIOS) simulations. NITK experiences cloudy conditions for a major part of the year that attenuates the solar irradiance available for PV energy production and the aerosols cause performance issues in the PV installations and maintenance. The proposed methodology employs cloud optical thickness (COT) and aerosol optical depth (AOD) to perform the INSIOS simulations and quantify the impact of clouds and aerosols on solar energy potential, quarter-hourly monitoring, forecasting energy production and financial analysis. The irradiance forecast accuracy was evaluated for 15 min, monthly, and seasonal time horizons, and the correlation was found to be 0.82 with most of the percentage difference within 25% for clear-sky conditions. For cloudy conditions, 27% of cases were found to be within ±50% difference of the percentage difference between the INSIOS and silicon irradiance sensor (SIS) irradiance and it was 60% for clear-sky conditions. The proposed methodology is operationally ready and is able to support the rooftop PV energy production management by providing solar irradiance simulations and realistic energy production estimations. © 2020 by the authors.Item Algorithms for Hyperparameter Tuning of LSTMs for Time Series Forecasting(MDPI, 2023) Dhake, H.; Kashyap, Y.; Kosmopoulos, P.The rapid growth in the use of Solar Energy for sustaining energy demand around the world requires accurate forecasts of Solar Irradiance to estimate the contribution of solar power to the power grid. Accurate forecasts for higher time horizons help to balance the power grid effectively and efficiently. Traditional forecasting techniques rely on physical weather parameters and complex mathematical models. However, these techniques are time-consuming and produce accurate results only for short forecast horizons. Deep Learning Techniques like Long Short Term Memory (LSTM) networks are employed to learn and predict complex varying time series data. However, LSTM networks are susceptible to poor performance due to improper configuration of hyperparameters. This work introduces two new algorithms for hyperparameter tuning of LSTM networks and a Fast Fourier Transform (FFT) based data decomposition technique. This work also proposes an optimised workflow for training LSTM networks based on the above techniques. The results show a significant fitness increase from 81.20% to 95.23% and a 53.42% reduction in RMSE for 90 min ahead forecast after using the optimised training workflow. The results were compared to several other techniques for forecasting solar energy for multiple forecast horizons. © 2023 by the authors.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.