Browsing by Author "Pol, Suhas (TTU)"
Now showing 1 - 6 of 6
- Results Per Page
- Sort Options
Item A Novel Hybrid Method for Short-Term Wind Speed Prediction Based on Wind Probability Distribution Function and Machine Learning Models(2022) Dhakal, Rabin (TTU); Sedai, Ashish (TTU); Pol, Suhas (TTU); Parameswaran, Siva (TTU); Nejat, Ali (TTU); Moussa, Hanna (TTU)The need to deliver accurate predictions of renewable energy generation has long been recognized by stakeholders in the field and has propelled recent improvements in more precise wind speed prediction (WSP) methods. Models such as Weibull-probability-density-based WSP (WEB), Rayleigh-probability-density-based WSP (RYM), autoregressive integrated moving average (ARIMA), Kalman filter and support vector machines (SVR), artificial neural network (ANN), and hybrid models have been used for accurate prediction of wind speed with various forecast horizons. This study intends to incorporate all these methods to achieve a higher WSP accuracy as, thus far, hybrid wind speed predictions are mainly made by using multivariate time series data. To do so, an error correction algorithm for the probability-density-based wind speed prediction model is introduced. Moreover, a comparative analysis of the performance of each method for accurately predicting wind speed for each time step of short-term forecast horizons is performed. All the models studied are used to form the prediction model by optimizing the weight function for each time step of a forecast horizon for each model that contributed to forming the proposed hybrid prediction model. The National Oceanic and Atmospheric Administration (NOAA) and System Advisory Module (SAM) databases were used to demonstrate the accuracy of the proposed models and conduct a comparative analysis. The results of the study show the significant improvement on the performance of wind speed prediction models through the development of a proposed hybrid prediction model.Item CFD analysis of gravity-fed drag-type in-pipe water turbine to determine the optimal deflector-to-turbine position(2023) Gautam, Shishir; Sedai, Ashish (TTU); Dhakal, Rabin (TTU); Sedhai, Bijaya Kumar; Pol, Suhas (TTU)In-pipe hydroelectric power generation is a relatively new clean energy power generation technology. This new clean energy technology has been identified to be feasible after successful commercial installation in different parts of the world. Several researchers worldwide have studied the optimal turbine type, the optimal number of blades in turbine, introduction of suitable deflector, etc. for this technology. However, the effect of the turbine's position relative to the upstream deflector on its performance has not been studied so far. This research encompasses a numerical study of the in-pipe hydroelectric power generation turbine to identify the optimal position of the turbine from the deflector. The study was performed for a 160-mm diameter pipeline and a 126-mm turbine height and aims to predict the behavior of larger diameter pipelines for commercial installation. The numerical study was performed for a hollow-type drag turbine at 6 different rotational speeds and 10 different turbine positions. The results suggest that the performance characteristics of drag-type turbine are erratic, thus leaving little space to draw a firm conclusion about the turbine's performance. However, there was an increase in pressure difference, head and available theoretical power with the increase in rotational speed for all the positions. It was also found that such turbines were generally more efficient at slightly higher rotational speeds, i.e. speed greater than 40 rad/s, and at about the distance of 0.65D (where D is the pipe diameter) between deflector's eye and turbine.Highlights: •Drag-type water turbines can significantly contribute to the production of clean energy. •We varied the turbine position and rotational speed to see how these parameters affects the turbine performance. •Computational fluid dynamics approach is used to study the behavior of turbine at different operating conditions.Item Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production(2023) Sedai, Ashish (TTU); Dhakal, Rabin; Gautam, Shishir; Dhamala, Anibesh (TTU); Bilbao, Argenis (TTU); Wang, Qin; Wigington, Adam; Pol, Suhas (TTU)The Machine Learning/Deep Learning (ML/DL) forecasting model has helped stakeholders overcome uncertainties associated with renewable energy resources and time planning for probable near-term power fluctuations. Nevertheless, the effectiveness of long-term forecasting of renewable energy resources using an existing ML/DL model is still debatable and needs additional research. Considering the constraints inherent in current empirical or physical-based forecasting models, the study utilizes ML/DL models to provide long-term predictions for solar power production. This study aims to examine the efficacy of several existing forecasting models. The study suggests approaches to enhance the accuracy of long-term forecasting of solar power generation for a case study power plant. It summarizes and compares the statistical model (ARIMA), ML model (SVR), DL models (LSTM, GRU, etc.), and ensemble models (RF, hybrid) with respect to long-term prediction. The performances of the univariate and multivariate models are summarized and compared based on their ability to accurately predict solar power generation for the next 1, 3, 5, and 15 days for a 100-kW solar power plant in Lubbock, TX, USA. Conclusions are drawn predicting the accuracy of various model changes with variation in the prediction time frame and input variables. In summary, the Random Forest model predicted long-term solar power generation with 50% better accuracy over the univariate statistical model and 10% better accuracy over multivariate ML/DL models.Item Renewable energy resource assessment for rural electrification: a case study in Nepal(2023) Sedai, Ashish (TTU); Dhakal, Rabin; Koirala, Pranik; Gautam, Shishir; Pokhrel, Rajat; Lohani, Sunil Prasad; Moussa, Hanna (TTU); Pol, Suhas (TTU)Renewable energy could mitigate remote area energy crises through rural electrification. Karnali province, one of the seven federal provinces of Nepal, is such a remote location and is most deprived in terms of electricity access. Around 67% of the population of the Karnali province is not connected to the national grid electricity supply. High altitude, mountainous topography makes it difficult to provide grid access to the region. This study summarizes the current electricity access status in Nepal and Karnali province specifically. The paper discusses the energy, economic and environmental (3E) analysis of different renewable energy resources like solar and wind energy for the grid-isolated region in Mugu and Jumla district of Karnali province. The study investigates the feasibility of a 200-kW solar power plant installation in Gamghadi, the capital of Mugu district and a 100-kW wind power plant installation in Tila village, Jumla district. The study suggests whether a similar installation of the distributed energy plant is a solution to mitigate the energy crisis problem in the high Himalayas regions, like Karnali province of Nepal. Based on the high-level resource assessment, the study estimates an investment cost ranging from 7 to 9 million USD would be necessary for the installation of such distributed solar PV and wind turbines.Item Sizing PV and BESS for Grid-Connected Microgrid Resilience: A Data-Driven Hybrid Optimization Approach(2023) Murshed, Mahtab; Chamana, Manohar (TTU); Schmitt, Konrad Erich Kork; Pol, Suhas (TTU); Adeyanju, Olatunji (TTU); Bayne, StephenThis article presents a comprehensive data-driven approach on enhancing grid-connected microgrid grid resilience through advanced forecasting and optimization techniques in the context of power outages. Power outages pose significant challenges to modern societies, affecting various sectors such as industries, households, and critical infrastructures. The research combines statistical analysis, machine-learning algorithms, and optimization methods to address this issue to develop a holistic approach for predicting and mitigating power outage events. The proposed methodology involves the use of Monte Carlo simulations in MATLAB for future outage prediction, training a Long Short-Term Memory (LSTM) network for forecasting solar irradiance and load profiles with a dataset spanning from 2009 to 2018, and a hybrid LSTM-Particle Swarm Optimization (PSO) model to improve accuracy. Furthermore, the role of battery state of charge (SoC) in enhancing system resilience is explored. The study also assesses the techno-economic advantages of a grid-tied microgrid integrated with solar panels and batteries over conventional grid systems. The proposed methodology and optimization process demonstrate their versatility and applicability to a wide range of microgrid design scenarios comprising solar PV and battery energy storage systems (BESS), making them a valuable resource for enhancing grid resilience and economic efficiency across diverse settings. The results highlight the potential of the proposed approach in strengthening grid resilience by improving autonomy, reducing downtime by 25%, and fostering sustainable energy utilization by 82%.Item Wind energy as a source of green hydrogen production in the USA(2023) Sedai, Ashish (TTU); Dhakal, Rabin (TTU); Gautam, Shishir; Kumar Sedhain, Bijaya; Singh Thapa, Biraj; Moussa, Hanna (TTU); Pol, Suhas (TTU)The study incorporates an overview of the green hydrogen-production potential from wind energy in the USA, its application in power generation and the scope of substituting grey and blue hydrogen for industrial usage. Over 10 million metric tons of grey and blue hydrogen is produced in the USA annually to fulfil the industrial demand, whereas, for 1 million metric tons of hydrogen generated, 13 million metric tons of CO2 are released into the atmosphere. The research aims to provide a state-of-the-art review of the green hydrogen technology value chain and a case study on the production of green hydrogen from an 8-MW wind turbine installed in the southern plain region of Texas. This research estimates that the wind-farm capacity of 130 gigawatt-hours is required to substitute grey and blue hydrogen for fulfilling the current US annual industrial hydrogen demand of 10 million metric tons. The study investigates hydrogen-storage methods and the scope of green hydrogen-based storage facilities for energy produced from a wind turbine. This research focuses on the USA's potential to meet all its industrial and other hydrogen application requirements through green hydrogen.