Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
2 results
Search Results
Item Control of Zeta Converter and Hybrid Energy Storage System (HESS) using Small Signal Analysis with State Feedback(Institute of Electrical and Electronics Engineers Inc., 2021) Ajeya, K.; Smiee, V.U.Renewable energy system at a low power level is of utmost significance since the area of the distributed power system is growing rapidly. DC-DC converters which can step up and step down voltage levels are extensively researched for the control and regulation of power and voltage of these types of system. Zeta converter, one of the promising DC-DC converter topology has advantages of low ripple output current over the conventional buck-boost converters and hence is considered in this paper. Zeta converter can operate in both excessive and deficit power modes while providing better load voltage regulation. This makes it a good candidate for PV based applications whose output power is intermittent in nature. Hybrid Energy Storage System (HESS) are increasingly becoming popular as energy storage devices since it inherits the quality of reducing fast and slow transients. Integration of zeta converter and such an energy storage system will provide optimal power transfer between the load and storage along with the load side regulation. State Space averaging technique is one of the modeling approach where in the parasitic resistances can be included so that the small signal behavior is captured and analyzed. For the control of small signal response, state feedback is implemented so that the optimal current flows in the energy storage system along with the HESS component voltage compensation. In the work presented in this paper, state space modeling is used to analyze the converter properties and feedback is appropriately ensued such that there is a seamless transfer of power to the load and HESS while keeping the steady state voltage error at the minimum. © 2021 IEEE.Item InFLuCs: Irradiance Forecasting Through Reinforcement Learning Tuned Cascaded Regressors(IEEE Computer Society, 2024) Chandrasekar, A.; Ajeya, K.; Vinatha Urundady, U.Accurate prediction of solar irradiance is essential for optimizing renewable energy sources in distributed generation systems due to its significant impact on solar power generation. Despite notable advancements, the inherent variability of irradiance presents challenges for existing models. In this article, we introduce a novel approach for irradiance forecasting using a cascaded combination of regressors applied to transformed process variables. Our method utilizes a gradient-boosted decision tree as the primary regressor to generate initial predictions, which are subsequently refined by a support vector regressor acting as an error correction module. Notably, the secondary regressor's kernel, alongside other hyperparameters, is dynamically learned through reinforcement learning with an RNN-based controller. Evaluation results demonstrate that our prediction-correction framework achieves superior performance compared to state-of-the-art approaches, as indicated by RMSE, MAE, and text{R}^{2} score metrics. Thorough comparative analysis highlights the model's enhanced accuracy and its potential for precise irradiance forecasting. © 2005-2012 IEEE.