ENERGIA
Permanent URI for this community
Browse
Browsing ENERGIA by Field of Science and Technology (FOS) "Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Analysis of Techno-Economic and Social Impacts of Electric Vehicle Charging Ecosystem in the Distribution Network Integrated with Solar DG and DSTATCOMPublication . Bonela, Ramesh; Ghatak, Sriparna Roy; Swain, Sarat Chandra; Lopes, Fernando; Nandi, Sharmistha; Sannigrahi, Surajit; Acharjee, ParimalABSTRACT: In this work, a comprehensive planning framework for an electric vehicle charging ecosystem (EVCE) is developed, incorporating solar distributed generation (DG) and a distribution static compensator (DSTATCOM), to assess their long-term techno-economic and environmental impacts. The optimal locations and capacities of the EVCE, solar DG, and DSTATCOM are determined using an improved particle swarm optimization algorithm based on the success rate technique. The study aims to maximize the technical, financial, and social benefits while ensuring that all security constraints are met. To assess the financial viability of the proposed model over a 10-year horizon, a detailed economic analysis comprising installation cost, operation, and maintenance cost is conducted. To make the model more realistic, various practical parameters, such as the inflation rate and interest rate, are incorporated during the financial analysis. Additionally, to highlight the societal benefits of the approach, the study quantifies the long-term carbon emissions and the corresponding cost of emissions. The proposed framework is tested on both a 33-bus distribution network and a 108-bus Indian distribution network. Various planning scenarios are explored, with different configurations of the EVCE, solar-based DG, and DSTATCOM, to assist power system planners in selecting the most suitable strategy.
- A Machine Learning Model for Procurement of Secondary Reserve Capacity in Power Systems with Significant vRES PenetrationsPublication . dos Santos, Joao; Algarvio, HugoABSTRACT: The growing investment in variable renewable energy sources is changing how electricity markets operate. In Europe, players rely on forecasts to participate in day-ahead markets closing between 12 and 37 h ahead of real-time operation. Usually, transmission system operators use a symmetrical procurement of up and down secondary power reserves based on the expected demand. This work uses machine learning techniques that dynamically compute it using the day-ahead programmed and expected dispatches of variable renewable energy sources, demand, and other technologies. Specifically, the methodology incorporates neural networks, such as Long Short-Term Memory (LSTM) or Convolutional neural network (CNN) models, to improve forecasting accuracy by capturing temporal dependencies and nonlinear patterns in the data. This study uses operational open data from the Spanish operator from 2014 to 2023 for training. Benchmark and test data are from the year 2024. Different machine learning architectures have been tested, but a Fully Connected Neural Network (FCNN) has the best results. The proposed methodology improves the usage of the up and down secondary reserved power by almost 22% and 11%, respectively.