Yazar "Cam E." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    Optimal Operation of Virtual Power Plant in a Day Ahead Market
    (Institute of Electrical and Electronics Engineers Inc., 2019) Akkas O.P.; Cam E.
    The necessity for Renewable Energy Resources (RES) has become a major issue due to the shortage of adequate fossil fuels recently. In addition to fossil fuel shortages, global warming is also an anxiety for a lot of countries and companies. These problems have led to the addition of a large number of renewable energy sources to modern distribution systems. However, due to the high integration of RES to these systems and the intermittent characteristic of sources such as wind and solar, it causes variable production and uncertainty in the power system. It is proposed as a solution to gather these resources together in order to solve the problems caused by the changeable outputs of these resources. Virtual Power Plant (VPP) is described as the management of distributed generation facilities, energy storage systems and controllable loads by an Energy Management System (EMS). In this study, the VPP model consists of renewable energy sources such as wind power plant (WPP), solar power plant (SPP), biogas power plant (BPP) and pumped hydro storage plant (PHSP) as an energy storage system (ESS). The aim of the VPP is to maximize the net daily profit in a 24 h time interval. The proposed mixed integer linear programming (MILP) optimization problem is modeled in GAMS software and solved using CPLEX. © 2019 IEEE.
  • [ X ]
    Öğe
    Optimizing of Speed Profile in Electrical Trains for Energy Saving with Dynamic Programming
    (Institute of Electrical and Electronics Engineers Inc., 2019) Arikan Y.; Cam E.
    Nowadays, the use of electric trains has been increasing in transportation and the rail networks has been expanding with the increasing needs. Therefore, energy efficiency in electric trains has become one of the notable issues. This study investigates the driving style of trains and the effects of driving styles on energy consumption and travel time and proposes a new speed profile to reduce energy consumption. Dynamic Programming and Bellman's Backward Approach have been applied to develop this speed profile and discretization of time, speed and distance parameters has been used for energy calculations. In the study, in order to test speed profiles, two different test lines with different characteristics such as slope, curve and speed limit have been formed. The comparison of the actual driving style and the proposed style has been examined in terms of operating time and energy consumption in these lines. In addition, the error of the distance and speed have been found and RMSE values have been calculated for these methods. The results of the study have been found to be successful because of the small error rates, the small increase in operating time and the significant reduction in energy consumption. © 2019 IEEE.
  • [ X ]
    Öğe
    Short-term fuzzy load forecasting model using genetic-fuzzy and ant colony-fuzzy knowledge base optimization
    (MDPI AG, 2018) Luy M.; Ates V.; Barisci N.; Polat H.; Cam E.
    The estimation of hourly electricity load consumption is highly important for planning short-term supply-demand equilibrium in sources and facilities. Studies of short-term load forecasting in the literature are categorized into two groups: classical conventional and artificial intelligence-based methods. Artificial intelligence-based models, especially when using fuzzy logic techniques, have more accurate load estimations when datasets include high uncertainty. However, as the knowledge base-which is defined by expert insights and decisions-gets larger, the load forecasting performance decreases. This study handles the problem that is caused by the growing knowledge base, and improves the load forecasting performance of fuzzy models through nature-inspired methods. The proposed models have been optimized by using ant colony optimization and genetic algorithm (GA) techniques. The training and testing processes of the proposed systems were performed on historical hourly load consumption and temperature data collected between 2011 and 2014. The results show that the proposed models can sufficiently improve the performance of hourly short-term load forecasting. The mean absolute percentage error (MAPE) of the monthly minimum in the forecasting model, in terms of the forecasting accuracy, is 3.9% (February 2014). The results show that the proposed methods make it possible to work with large-scale rule bases in a more flexible estimation environment. © 2018 by the authors.