Browsing by Author "Yucekaya, A."

Now showing 1 - 4 of 4

Citation - Scopus: 0
A Framework To Forecast Electricity Consumption of Meters Using Automated Ranking and Data Preprocessing
(Econjournals, 2023) Guzel, T.; Hekimoğlu, Mustafa; Çınar, H.; Çenet, M.N.; Oguz, K.D.; Yucekaya, A.; Hekimoglu, M.
Forecasting electricity consumption is crucial for the operation planning of distribution companies and suppliers and for the success of deregulated electricity markets as a whole. Distribution companies often need consumption forecasting for meters to better plan operations and demand fulfillment. Although it is easier to forecast the aggregated demand for a region, meter based demand forecasting brings challenging issues such as non-uniform usage and uncertain customer consumption patterns. The stochastic nature of the demand for electricity, along with parameters such as temperature, humidity, and work habits, eventually causes deviations from the expected demand. In this paper, real meter data from a regional distribution company is used to cluster the customer using their non-uniform usage and automated ranking mechanism is proposed to select the best method to forecast the consumption. The proposed end-to-end methodology includes data processing, missing value detection and filling, abnormal value detection, and mass reading for meters and is applied to regional data for the period 2017-2018 and provides a powerful tool to forecasts the demand in hourly and daily horizons using only the past demand data. Besides proposing effective methodologies for data preprocessing, 10 different regression methods, 7 regressors, 5 machine learning methods that include LSTM and Ar-net models are used to forecast the meter based consumption. The hourly forecasting errors in the demand, in the Mean Absolute Percentage Error (MAPE) norm, are <4% for most customer groups. The meter based forecast is then aggregated to reach a final demand which is then used for operation and demand planning. The proposed framework can be considered reliable and practical in the circumstances needed to make demand and operation decisions. © 2023, Econjournals. All rights reserved.
Citation - WoS: 0
A Hesitant Fuzzy Linguistic Terms Set-Based Ahp and Topsis Methodology for Fuel Coal Type Selection Problem of Industrial Facilities
(Old City Publishing, 2024) Yucekaya, A.; Ayağ, Zeki; Ayağ, Z.
Coal is still used widely by both industrial facilities and coal fired power plants. Lignite, hard coal, coke, and imported coal are some alternatives. The coal has ash content, moisture content, heat rate, volatile matter, carbon content, sulphur content, and size that need to be considered as well as price. The suppliers provide coal products for each coal type, and the most appropriate coal product needs to be selected considering different parameters. Therefore, in this paper, a hesitant fuzzy linguistic term sets-based AHP (HFLTS-AHP) and TOPSIS method are used to select the best coal type alternative for industrial facilities. As the HFLTS-AHP is used to weight the evaluation criteria, TOPSIS is utilized to rank the fuel coal type alternatives. The proposed methodology offers an innovative and novel approach to help industrial facilities select the appropriate coal product while balancing the outputs, such as carbon, sulphur, ash content, and so on. In another point of view, the motivation of this research is to help industrial firms find out the ultimate fuel coal alternative based on their needs. This objective is realized using the proposed approach that integrates the HFLTS-AHP and TOPSIS approaches for the related problem, also utilizing group decision making. Moreover, this approach is concreted by an Excel template that provides an effective tool for firms to realize the evaluation process without many tiresome fuzzy comparisons and complex calculations. Furthermore, in the paper, a real-life case study in Turkish industrial facilities is presented to demonstrate the effectiveness and applicability of the proposed approach to readers and practitioners. In this case, seven coal type options are evaluated in terms of eight criteria by three decision makers, and the best coal type alternative is determined. © 2024 Old City Publishing, Inc.
Citation - WoS: 11
Citation - Scopus: 17
The impact of the COVID-19 pandemic and behavioral restrictions on electricity consumption and the daily demand curve in Turkey
(Elsevier Sci Ltd, 2022) Bilge, Ayşe Hümeyra; Hekimoğlu, Mustafa; Yucekaya, A.; Bilge, A.; Aktunc, E. Agca; Hekimoglu, M.
The rapid spread of COVID-19 has severely impacted many sectors, including the electricity sector. The reliability of the electricity sector is critical to the economy, health, and welfare of society; therefore, supply and demand need to be balanced in real-time, and the impact of unexpected factors should be analyzed. During the pandemic, behavioral restrictions such as lockdowns, closure of factories, schools, and shopping malls, and changing habits, such as shifted work and leisure hours at home, significantly affected the demand structure. In this research, the restrictions and their corresponding timing are classified and mapped with the Turkish electricity demand data to analyze the estimated impact of the restrictions on total demand and daily demand profile. A modulated Fourier Series Expansion evaluates deviations from normal conditions in the aggregate demand and the daily consumption profile. The aggregate demand shows a significant decrease in the early phase of the pandemic, during the period March-June 2020. The shape of the daily demand curve is analyzed to estimate how much demand shifted from daytime to night-time. A population-based restriction index is proposed to analyze the relationship between the strength and coverage of the restrictions and the total demand. The persistency of the changes in the daily demand curve in the post-contingency period is analyzed. These findings imply that new scheduling approaches for daily and weekly loads are required to avoid supply-demand mismatches in the future. The longterm policy implications for the energy transition and lessons learned from the COVID-19 pandemic experience are also presented.
Citation - Scopus: 0
Segregation of Hourly Electricity Consumption: Quantification of Demand Types Using Fourier Transform
(Econjournals, 2025) Yucekaya, A.; Bilge, A.H.; Yukseltan, E.; Aktunc, E.A.
Although aggregate electricity consumption provides valuable information for market analysis, it does not provide demand composition, including industrial, residential, illumination, and other uses. The information for subconsumptions is required for the reliable and cost-effective operation of the power system. As a first step towards the segregation of hourly total electricity consumption into its components, we use spectral analysis (Fast Fourier Transform) to determine relative strengths of the harmonics of annual, weekly and daily variations, to quantify the share of electricity consumption for heating, cooling, illumination and industrial activities. The method is applied to the data of France, Sweden, Finland, Norway, Turkiye, Italy, Spain, Greece, Germany, Great Britain, Poland and the Netherlands. Quantitative results obtained via spectral analysis are supplemented by qualitative features observed via time-domain analysis. The consumption ratios for each demand type are calculated using daily, weekly and annual harmonics and the results are presented. © 2025, Econjournals. All rights reserved.