Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Solar Irradiation Forecast Enhancement Using Hybrid Architecture(Institute of Electrical and Electronics Engineers Inc., 2023) Chiranjeevi, M.; Karlamangal, S.; Moger, T.; Jena, D.Power balancing at the grid is much more involved process due to the fact that solar power generation is primarily weather dependent, as it is relied on solar irradiation, which is very volatile and unpredictable. Accurate solar irradiation forecasting can significantly increase the performance of solar power plants. This research is motivated by the current advancements in deep learning (DL) models and its practical use in the green energy field. The proposed model combines two DL architectures: convolutional neural network (CNN) and long short-term memory (LSTM). The effectiveness of the same is analysed by comparing with recurrent neural network (RNN) family architectures. The RNN family models are Long Short Term Memory (LSTM), Bi-directional LSTM (Bi-LSTM), Gated Recurrent Unit (GRU), and Bi-directional GRU (Bi-GRU). The simulations are conducted on a publicly available data set from Desert Knowledge Australia Solar Centre (DKASC), Australia. A meteorological station across the Northern Territory (NT Solar resource) collects high resolution solar and climate data from Darwin location, which is used for the experiment. From the results, it is evident that each of the bidirectional model outperform its unidirectional equivalent architectures. However, the hybrid network (CNN-LSTM) outperforms all the individual models as per the error metric analysis. © 2023 IEEE.Item Preprocessing Techniques of Solar Irradiation Data(Institute of Electrical and Electronics Engineers Inc., 2023) Chiranjeevi, M.; Karlamangal, S.; Moger, T.; Jena, D.; Agarwal, A.Solar energy being abundant, non-exhaustive, environmentally friendly attracts the people attention towards the alternate renewable energy. High-quality time series data is essential for producing an accurate estimate of solar power generation. In most cases, the plethora of information hidden in time series data cannot be accessed. Common issues with time series include outliers, noise, missing data, and a lack of order in the timestamps itself that impair forecasting accuracy. So, preprocessing of the input data is a mandate in order to achieve a precise and dependable forecast. This study proposes various pre-processing techniques to improve the performance of the forecasting accuracy. The different ways to handle the missing values and outliers detection by sliding window method and box plots are presented in this study. The solar irradiation data collected from solar center Alice Springs, Australia used for validation of the preprocessing results. The efficacy of the proposed method in detecting the missing values and outliers is effective from the obtained results. © 2023 IEEE.Item Solar Irradiation Prediction Hybrid Framework Using Regularized Convolutional BiLSTM-Based Autoencoder Approach(Institute of Electrical and Electronics Engineers Inc., 2023) Chiranjeevi, M.; Karlamangal, S.; Moger, T.; Jena, D.Solar irradiance prediction is an essential subject in renewable energy generation. Prediction enhances the planning and management of solar installations and provides several economic benefits to energy companies. Solar irradiation, being highly volatile and unpredictable makes the forecasting task complex and difficult. To address the shortcomings of the traditional approaches, this research developed a hybrid resilient architecture for an enhanced solar irradiation forecast by employing a long short-term memory (LSTM) autoencoder, convolutional neural network (CNN), and the Bi-directional Long Short Term Memory (BiLSTM) model with grid search optimization. The suggested hybrid technique is comprised of two parts: feature encoding and dimensionality reduction using an LSTM autoencoder, followed by a regularized convolutional BiLSTM. The encoder is tasked with extracting the key features in order to deduce the input into a compact latent representation. The decoder network then predicts solar irradiance by analyzing the encoded representation's attributes. The experiments are conducted on three publicly available data sets collected from Desert Knowledge Australia Solar Centre (DKASC), National Solar Radiation Database (NSRDB), and Hawaii Space Exploration Analog and Simulation (HI-SEAS) Habitat. The analysis of univariate and multivariate-multi step ahead forecasting performed independently and it is compared with the conventional approaches. Several benchmark forecasting models and three performance metrics are utilized to validate the hybrid approach's prediction performance. The results show that the proposed architecture outperforms benchmark models in accuracy. © 2013 IEEE.Item Solar irradiation forecast enhancement using clustering based CNN-BiLSTM-attention hybrid architecture with PSO(Taylor and Francis Ltd., 2024) Chiranjeevi, M.; Madyastha, A.; Maurya, A.K.; Moger, T.; Jena, D.Accurate solar irradiation forecasting is essential for optimising solar energy use. This paper presents a novel forecasting approach: the ‘Clustering-based CNN-BiLSTM-Attention Hybrid Architecture with PSO’. It combines clustering, attention mechanisms, Convolutional Neural Networks (CNN), Bidirectional Long-Short Term Memory (BiLSTM) networks, and Particle Swarm Optimisation (PSO) into a unified framework. Clustering categorises days into groups, improving predictive capabilities. The CNN-BiLSTM model captures spatial and temporal features, identifying complex patterns. PSO optimises the hybrid model’s hyperparameters, while an attention mechanism assigns probability weights to relevant information, enhancing performance. By leveraging spatial and temporal patterns in solar data, the proposed model improves forecasting accuracy in univariate and multivariate analyses with multi-step predictions. Extensive tests on real-world datasets from various locations show the model’s effectiveness. For example, with NASA power data, the model achieves a Mean Absolute Error (MAE) of 24.028 W/m2, Root Mean Square Error (RMSE) of 43.025 W/m2, and an R2 score of 0.984 for 1-hour ahead forecasting. The results show significant improvements over conventional methods. © 2024 Informa UK Limited, trading as Taylor & Francis Group.