Yazar "Isik, Gurkan" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Deep learning based electricity demand forecasting to minimize the cost of energy imbalance: A real case application with some fortune 500 companies in Turkiye
    (Pergamon-Elsevier Science Ltd, 2023) Isik, Gurkan; Ogut, Hulisi; Mutlu, Mustafa
    In this study, the electricity demands of some Fortune 500 companies in Turkiye have been forecasted by using deep learning techniques. This is a quite harder problem than the forecasting of the aggregated electricity demand in which the negative and positive fluctuations are absorbed on paper. Forecasting of firm-level electricity demand is an important problem since it can help automating firms' routine forecasting operations, reducing the electricity supply costs of the firms by improving the quality of the forecasts, and improving the quality of the electricity on the transmission network. Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) techniques have been preferred concerning the successful results in the literature. As the originality of this paper, the Multiple Seasonal-Trend Decomposition using Loess (MSTL) technique is used for the electricity demand forecasting problem for the first time. The obtained results showed that although it is simple to implement, MSTL outperforms MLP and LSTM for most of the firms operating in mass production form. It is seen that the complexity of the model does not always guarantee good results and simple methods sometimes can work well. Load balancing studies are also very important for the economic sustainability of the industry since the electricity price and imbalance penalty have extremely increased (i.e., 8 times in Turkiye) during the post-pandemic period. Therefore, the energy cost reduction potential of the companies has also been assessed. This study resulted in cost savings of approximately 378 minimum wages for the pilot company.
  • Küçük Resim Yok
    Öğe
    Evaluation of Potential Locations for Hydropower Plants by Using a Fuzzy Based Methodology Consists of Two-Dimensional Uncertain Linguistic Variables
    (Inst Information Science, 2022) Kaya, Ihsan; Isik, Gurkan; Karasan, Ali; Gundogdu, Fatma Kutlu; Baracli, Hayri
    Hydropower is one of the most efficient renewable energy sources for the sustaina-bility of the environment if the plant location is well decided. The plant location should satisfy different criteria emerged by a wide range of criteria, consisting of law, environ-ment, and the expectations of the investors and residents. Some of these criteria can be conflicting. Some of them may also be in a relationship with each other. Moreover, they may be evaluated in a system that contains uncertainty consisting of a lack of information, impreciseness in the data, and human hesitancy. These aspects can be a powerful effect on the location selection of the hydropower plants and are considered in mathematical formu-lations. So, the problem can be considered as a multi-criteria decision-making (MCDM) problem under uncertainty. In this study, by considering the types of uncertainties, impre-ciseness of the available data, and hesitancy of the experts, an integrated MCDM method-ology consisting of DEMATEL, cognitive mapping, and TOPSIS methods has been ex-tended based on hesitant fuzzy z-numbers. Then the proposed methodology has been ap-plied for the evaluation of potential locations for hydropower plants in Turkey. For this aim, a hierarchical structure consisting of twenty-nine criteria and four alternative loca-tions has been determined for the assessment by combining literature analysis and expert knowledge. In the first stage, the criteria Availability of Water, Annual flow, Tech-nology, Capacity, and Annual energy production have been demonstrated as the most influential criteria for location selection. Then, based on the z-number fuzzy TOPSIS method, the most appropriate alternative for the construction location has been determined in Turkey. The findings have been checked in terms of validation and flexibility of the given decisions by applying sensitivity and comparative analyses.
  • Küçük Resim Yok
    Öğe
    Identifying Key Factors of Reputational Risk in Finance Sector Using a Linguistic Fuzzy Modeling Approach
    (Mdpi, 2024) Hanay, Ugur; Ince, Huseyin; Isik, Gurkan
    Management of reputational risk is crucial for financial institutions to establish a solid foundation for strategic decisions, gain customer trust, and enhance resilience against environmental adversities, as they largely operate on digital platforms. Since this becomes even more significant as online transactions and digital interactions amplify the visibility and potential impact of reputational issues in the context of electronic commerce, it is essential to thoroughly investigate environmental factors to achieve a comprehensive understanding of reputational risk. However, measuring and evaluating their influence on reputational risk is challenging due to their inherent connection to human perception. This study aims to explore the factors influencing reputational risk of financial organizations to mitigate potential reputational losses by addressing uncertainties associated with concepts such as vagueness. The employed methodology integrates the Decision-Making Trial and Evaluation Laboratory and Fuzzy Cognitive Map techniques using linguistic fuzzy terms. This approach focuses on both the direct effects of factors on reputational risk and the indirect effects arising from interdependencies between factors. Linguistic fuzzy variables enable us to consider the hesitation of the experts and the vagueness of human judgment. To validate the results, factors are also weighted using the fuzzy Stepwise Weight Assessment Ratio Analysis (SWARA) method. The most influential factors identified by both methods are market value, revenue, risk culture, shareholder value, firm performance, reputation awareness, and return on equity. Additionally, factors affecting other factors include firm performance, revenue, and growth opportunities.