Browsing by Author "Tharaka, VPV"

Now showing 1 - 2 of 2

item: Conference-Full-text
A conceptual overview: integration of bi-directional electric vehicle (ev) chargers for effective peak grid demand management in Sri Lanka
(IEEE, 2023-12-09) Induranga, DKA; Tharaka, VPV; Perera, WMKG; Priyadarshana, HVV; Koswattage, KR; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
This paper presents an energy analysis of the integration of bi-directional electric vehicle (EV) chargers for managing peak grid demand in Sri Lanka. This study addresses the challenges posed by peak demand and the way to address these issues with EV technology. The concept of bi-directional EV chargers is introduced, allowing EVs to both consume and feed energy back into the grid. The researchers calculated the benefit of using vehicle-to-grid (V2G) feeding systems for the years 2030 and 2040 assuming that the number of EVs is 10% of the total number of motor cars in the country. This method can provide 25% of the energy requirement of the current peak demand in Sri Lanka. Furthermore, this paper provides valuable insights that can guide further research and development in this area, contributing to sustainable grid utilization and EV adoption.
item: Conference-Full-text
IoT based building energy management system
(Institute of Electrical and Electronics Engineers, Inc., 2021-09) Hettiarachchi, DG; Jaward, GMA; Tharaka, VPV; Jeewandara, JMDS; Hemapala, KTMU; Abeykoon, AMHS; Velmanickam, L
The ever-growing demand for energy and uncertainty of supply lead towards a major crisis in the energy sector, especially in building energy management. In case of power outages it is crucial to utilize the scarce power sources for the most vulnerable cause of demand. Furthermore, it is evident that due to the lack of monitoring and automation present in building energy management systems, a considerable percentage of energy wastage gets reported. Thus the need for a proper load forecasting methodology has arisen in the recent past. Researchers have formulated statistical methods and machine learning based models to facilitate energy forecasting for future periods. This paper addresses the load forecasting challenge by proposing an IoT (Internet of Things) based energy management system that incorporates an XGBoost (Extreme Gradient Boost) machine learning model to forecast energy consumption. The energy management system consists of a user-friendly central dashboard that acts as a mediator between a NodeMCU device and a cloud-hosted database with the aforementioned machine learning model. The paper concludes with a summarized discussion on the research.