GCRIS

Now showing 1 - 2 of 2

Görüntü Tanıma Tabanlı Gökyüzü Kamerası Entegrasyonunu Kullanarak Sezgisel Vektörize Öğrenme Yöntemine Dayalı PV Tahmini
(Abdullah Gül Üniversitesi, Fen Bilimleri Enstitüsü, 2023) Yavuz, Levent; Önen, Ahmet
In order to ensure the continuity of demand and production balance, the use of renewable energy resources (RES) by countries will increase in the near future. Solar power generation is important for the integration of renewable energy into the power grid, but it can cause problems in power systems due to the uncertain and intermittent nature of solar power. Deep learning methods provide promising results in solar energy prediction, but the performance of these models depends on the initial weights assigned to the network. In this thesis, a novel weight initialization method, the Heuristic Vectorised Learning method, which takes into account certain characteristics of solar generation data has been proposed. This method aims to achieve better accuracy in solar forecasting by combining a statistical approach with a method based on deep learning. The method was compared with other commonly used methods such as Xavier, LeCun, He and Random, and it was seen that the proposed method performed better. Overall, the proposed weight initialization method provides significant benefits for solar forecasting applications in the context of renewable energy integration into the power grid. So, to reach higher accuracy, monitoring the sky is the best option for intra-day forecasts. Therefore, a hybrid model was created for photovoltaic generation prediction by using it together with environmental sensor data. The proposed method and panel shading model achieve higher accuracy values at the Abdullah Gül University campus in Kayseri. The proposed system provides a reliable PV energy forecast for the intraday energy markets.
Akıllı Mikro-Şebekelerde Kontrol Stratejilerinin Geliştirilmesi
(Abdullah Gül Üniversitesi Fen Bilimleri Enstitüsü, 2021) Yoldaş, Yeliz; Yoldaş, Yeliz; Önen, Ahmet
This thesis concerns the transformation of aged power systems to modern power systems that include microgrids with renewable energy sources and energy storage systems. The integration of renewable energy sources brings excellent opportunities to provide better reliability and efficiency. However, the uncertainty and intermittent nature of renewable energy sources may potentially degrade the stability and quality of the electrical grid. Therefore, the aim of this dissertation is to maintain the supply-demand balance in microgrids while minimizing the cost in real time operation. A microgrid energy management system that can optimize the dispatch of the controllable distributed energy resources in grid-connected mode of a pilot microgrid on a university campus in Malta was developed to achieve this goal. Three different methods were used in this study: mixed integer linear programming (MILP), MILP based rolling horizon control and Q-learning, Designing intelligent method for the real-time energy management of the stochastic and dynamic microgrid is the primary goal of this research. Moreover, the detailed mathematical models of the network model and of the technical model are considered for the economic and environmental operation of the microgrid system to solve the optimization problem under more real-world conditions. The objective is to minimize the total daily operation costs, which include the degradation cost of batteries, the cost of energy bought from the main grid, the fuel cost of the diesel generator, and the emission cost. The optimization problem is modeled as a finite Markov decision process (MDP) by combining network and technical constraints, and a Q-learning algorithm is adopted to solve the sequential decision subproblems. The proposed algorithm decomposes a multi-stage mixed-integer nonlinear programming (MINLP) problem into a series of single-stage problems so that each subproblem can be solved using Bellman's equation. To prove the effectiveness of the proposed algorithm, three different case studies are taken into consideration. A predictive control framework is also proposed to provide optimal operation with minimum cost. This method allows the consideration of operational cost values, demand with uncertainty, generation units' profiles with uncertainty, and constraints related to the network model and technical model. The stochastic and deterministic cases are conducted to validate the efficiency of the approach.

Doktora Tezleri

Browse

Filters

Settings

Sort By

Results per page

Search Results