Yazar "Deepanraj, B." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Intelligent wild geese algorithm with deep learning driven short term load forecasting for sustainable energy management in microgrids
    (Elsevier, 2022) Deepanraj, B.; Senthilkumar, N.; Jarin, T.; Gürel, Ali Etem; Sundar, L. Syam; Anand, A. Vivek
    Energy management in power grids becomes essential to reduce the cost for the consumer and improve the power supply reliability. The microgrid is a vital part of the smart grid and it requires intelligent power management approach for effective functioning. Presently, delivering demand load and sustaining energy are two major challenges that exist in the power system. To resolve these problems, short-term load forecasting (STLF) models have been presented as an effective management and energy supply mode in power systems. The recently developed deep learning (DL) and machine learning (ML) models can be employed for accurate STLF in microgrids. In this view, this study presents an intelligent wild geese algorithm with deep learning driven short term load forecasting (IWGADL-STLF) model for sustainable energy management in microgrids. The proposed IWGADL-STLF model intends to accurately and rapidly predict the STLF in the microgrids. To accomplish this, the IWGADL-STLF model uses attention based Bi-directional long short term memory (ABiLSTM) model which involves the input parameters as formation of household and commercial load profiles with commercial load profile of the microgrid as output. The proposed IWGADL-STLF model identifies the behavioural patterns of parameters and models the behaviour in short time period for effective prediction process. Since hyper -parameters play a vital role in the DL models, in this study, WGA is applied as a hyperparameter optimizer of the ABiLSTM model. The IWGADL-STLF approach has shown effective results with low MAE, MAPE, and R2 values. A comprehensive experimental analysis reported the enhanced performance of the presented model over the other existing approaches under several aspects.
  • Küçük Resim Yok
    Öğe
    Investigations on a novel fuel water hyacinth biodiesel and Hydrogen-Powered engine in Dual-Fuel Model: Optimization with I-optimal design and desirability
    (Elsevier Sci Ltd, 2023) Bora, Bhaskor Jyoti; Sharma, Prabhakar; Deepanraj, B.; Agbulut, Umit
    Hydrogen is one of the most promising green fuels. The present study explores the potential of novel water hyacinth biodiesel as pilot fuel as well as investigates the influence of the injection pressure of pilot fuel on the performance of hydrogen running a dual-fuel diesel engine. For experimentation, a 4.8 kW research test engine was considered. Three fuel injection pressure (FIP) of the pilot fuel, namely 220 bar, 240 bar, and 260 bar were considered at a ratio of compression as 17.5 and standard injection timing of 23 degrees before Top Dead Centre (bTDC) for different loading conditions were considered. The peak brake thermal efficiency (BTE) under dual fuel mode (DFM) was observed as 26.77%, 28.11%, and 27.21% for FIP of the pilot fuel of 220 bar, 240 bar, and 260 bar, respectively in comparison to 25.11% for biodiesel mode at 100% load. The maximum drop in carbon monoxide (CO) and hydrocarbon (HC) emissions was found to be 15.48%, and 35.7%, respectively for the FIP of the pilot fuel of 240 bar under DFM in comparison to biodiesel mode. The fall in Oxides of Nitrogen (NOX) emission under DFM was found to be 23.66% for the FIP of the pilot fuel of 220 bar under DFM compared to biodiesel mode. Based on the performance and emission analysis, the optimum FIP of the pilot fuel is found to be 240 bar. For the same FIP, the maximum liquid fuel replacement of 85% was obtained. The experimental study's data were evaluated using analysis of variance (ANOVA) to create models in the form of mathematical expressions for each outcome. The desirability approach was employed to optimize the operating settings for maximum performance while emitting the least amount of emission. According to the desirability-based optimization research, ideal operating conditions were 83.61% engine load and 242 bar FIP, resulting in engine performance of 26.5% of BTE, 80.47% of LFR, and 51.82 bar peak cylinder pressure. The emission levels were 191.19 ppm of NOX, 106.41 ppm of HC, and 130.95 ppm of CO at this setting. A model validation test found that the model-predicted values were within 6% of the observed values.