Yazar "Cakil, Fatih" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    A novel probabilistic load shifting approach for demand side management of residential users
    (Elsevier Science Sa, 2024) Cakil, Fatih; Tekdemir, Ibrahim Gursu
    Demand side management is a beneficial set of techniques which leads improving consumption profile of residential users. Practice of dynamic pricing and appropriate shifting of electrical appliances at home are important tasks at that point. In this study, a novel probabilistic load shifting strategy is proposed and its beneficial effects on economic and technical parameters are demonstrated. For that purpose, a survey on energy consumption is applied for residential users and its results are used for creating a probabilistic model. 300 virtual residents are created in this way and a probabilistic simulation technique is developed. Next, the developed simulation technique is applied for creation of the monthly consumption data. Finally, it is demonstrated that electricity bills are decreased significantly when the proposed approach is applied. Besides that, peak-to-average ratio which is calculated by considering all residential users is also decreased as a result. In conclusion, when the results are compared with the ones of conventional constant tariff, time-of-use tariff with three time zones and a deterministic load shifting strategy, it is observed that the best results of economic and technical parameters in question are achieved by using the proposed probabilistic load shifting strategy together with dynamic pricing mechanism involved.
  • Küçük Resim Yok
    Öğe
    An optimal load shifting strategy for residential energy consumers considering economic, technical and environmental impacts
    (Elsevier Science Sa, 2025) Cakil, Fatih; Tekdemir, Ibrahim Gursu
    Residential consumers have a significant share in total global energy demand. By adjusting operating hours of electrical appliances at residences has a potential to get economic, technical and environmental benefits. In this study, an optimal load shifting strategy that is based on particle swarm optimization algorithm is developed considering this potential. It is applied both in a single-objective and in a multi-objective form. The multi-objective optimization approach is realized by using weight factors and effects of different weight values are also demonstrated. Rooftop photovoltaic panels are integrated into 300 virtual residences, which are formed by using statistical models. Also, energy buying, selling and dynamic pricing mechanisms are involved in the analyses. Having photovoltaic panels and energy selling mechanism, optimization process has also realized a consideration of energy market. After analyses obtained for revealed optimization problems in the study, electricity bills, peak-to-average ratio and utilization of solar panels in residential power demand is calculated for a single month. It is seen that a significant improvement is reached when compared to the case without any load shifting approach and to the one with a novel load shifting strategy: electricity bills are reduced by up to 37.61 %, and carbon dioxide emission is reduced by 32.05 kg per residence when the proposed method is used, which are far better than the others. Although the technical parameter that is relevant to the system operation cannot be improved, it can be prevented from reaching undesirable extreme values by using the proposed participation in load shifting index.
  • Küçük Resim Yok
    Öğe
    Optimizing Battery Cooling with Reinforcement Learning: A Dynamic Control Strategy for Energy Storage Systems
    (Ieee, 2025) Aksoy, Necati; Cakil, Fatih; Ozden, Mustafa
    The growing reliance on energy storage systems (ESS) in residential, vehicular, and industrial applications necessitates efficient thermal management solutions to enhance performance and longevity. This study proposes a reinforcement learning (RL)-based cooling control system for optimizing the temperature regulation of battery banks. Unlike traditional rule-based or static cooling strategies, the proposed method dynamically adjusts coolant flow rates using an Expected SARSA agent, which learns an optimal control policy through interactions with a custom-designed environment model. The model accurately simulates thermal absorption and coolant flow dynamics, allowing for precise and adaptive cooling regulation. The performance of the RL agent was evaluated across different training durations, demonstrating that extended training significantly improves stability, reward consistency, and energy efficiency. Compared to conventional cooling strategies, the RL-based system ensures more adaptive, efficient, and reliable thermal management, making it a promising solution for next-generation energy storage applications.
  • Küçük Resim Yok
    Öğe
    Reinforcement learning-based multi-objective smart energy management for electric vehicle charging stations with priority scheduling
    (Pergamon-Elsevier Science Ltd, 2025) Cakil, Fatih; Aksoy, Necati
    Reinforcement learning (RL)-based control structures represent a transformative approach to optimizing energy management in electric vehicle (EV) charging stations, offering unparalleled adaptability and efficiency. This paper introduces a novel RL-based intelligent control strategy, designed to address multi-objective challenges in EV charging, such as energy efficiency, cost-effectiveness, and user prioritization. Central to this study is the development of a unique environment model, which incorporates dynamic variables including vehicle priority, arrival times, and real-time pricing data, ensuring realistic and practical applications. Additionally, a custom reward strategy is proposed, enabling the RL agents to effectively learn and adapt to complex operational demands. The study evaluates the performance of three RL algorithms-Q-Learning, SARSA, and Expected SARSA-within the proposed environment model, demonstrating their capabilities in reducing charging costs and improving profitability. Experimental results indicate that the Q-Learning agent achieved an average cost reduction of up to 66.4% compared to conventional charging strategies, with energy costs dropping from 11.78 to 3.96 per unit in high-priority cases. Expected SARSA exhibited a competitive performance, yielding up to 44.3% cost savings, whereas SARSA consistently resulted in the lowest cost efficiency, with reductions of only 46.6% in comparable scenarios. Furthermore, the RL-based scheduling framework successfully shortened peak-hour waiting times by 40%, while ensuring equitable prioritization of charging requests. Through a comprehensive set of realistic case studies and scenarios, the effectiveness of these algorithms is analyzed, focusing on their capacity to manage energy costs, enhance profitability, and adapt to fluctuating pricing conditions.