50 results on '"Başaran Filik, Ümmühan"'
Search Results
2. A Stackelberg game approach for energy sharing management of a microgrid providing flexibility to entities
- Author
-
Erol, Özge and Başaran Filik, Ümmühan
- Published
- 2022
- Full Text
- View/download PDF
3. Multi-Defender Strategic Filtering Against Multi Agent Cyber Epidemics on Multi-Environment Model for Smart Grid Protection
- Author
-
Bitirgen Kübra and Başaran Filik Ümmühan
- Subjects
Environmental sciences ,GE1-350 - Abstract
The growing cyber space with the developments in cyber network technologies in smart grid (SG) systems has necessitated questioning the reliability of networks and taking precautions against possible cyber threats. For this reason, defensive strategies and approaches against cyber attacks must be improved to sustain secure information flow of the network connections used in electricity generation, transmission, distribution, and consumption. This paper proposes a multi-agent multi environment deep reinforcement learning (MM-DRL) based defender response against cyber epidemics consisting coordinated cyber-attacks (multi-CAs) in the same time frame scheme to sustain security for SG networks. In this regard, the PMU-connected 123-bus system is integrated as a Markov game. MM-DRL approach is implemented for subenvironments of a typical SG system. Multi-CAs game aims to coordinate PMU signals across intersections to improve the network efficiency of a SG. DRL has been applied to data control recently and demonstrated promising performance where each data signal is regarded as an agent. Conversely, multi-CAs are self-renewing emerging causative agent of electricity theft, network disturbances, and data manipulation in SG systems characterized with wide characteristic diversity and rapid evolution. The game results show that the presented request response algorithm is able to minimize system attack damage and maintain protection duties when compared to a benchmark without request response. In addition, the performance of the MM-DRL approach compared to other developed methods is examined.
- Published
- 2023
- Full Text
- View/download PDF
4. A Markov Game Approach Based on Multiagent Reinforcement Learning Solution for Cyber-Physical Attacks in Smart Grid
- Author
-
Bitirgen, Kübra, primary and Başaran Filik, Ümmühan, additional
- Published
- 2023
- Full Text
- View/download PDF
5. Performance Analysis of PCA Based Machine Learning Approaches on FDIA Detection
- Author
-
BİTİRGEN, Kübra and BAŞARAN FİLİK, Ümmühan
- Subjects
Computer Science, Interdisciplinary Application ,Bilgisayar Bilimleri, Disiplinler Arası Uygulamalar ,False data injection attack (FDIA) ,Phasor measurement unit (PMU) ,Principle component analysis (PCA) ,Smart grid (SG) - Abstract
Smart grid (SG) and its specific structures are widely taken notice of by many researchers studying power systems. This paper compares and analyzes the performance of five machine learning approaches combined with principal component analysis (PCA) to do the task of false data injection attack (FDIA) detection of an SG. For this purpose, PCA method combinations are presented and tested by using labeled data. Phasor measurement unit (PMU) data is a critical source of monitoring of progress and performance of an SG system. PMUs are perniciously influenced by FDIAs trying to manipulate the measurements without being noticed by the bad data detector (BDD) of the SG system. In one sense, the selected PMU data consisting of various features which play an important role in the control system of SG is used to analyze the characteristics of the SG system. The results show that FDIA detection is effectively accomplished. The efficiency of the proposed hybrid PCA-based various machine learning approaches is illustrated on a real measured PMU dataset. As empirical results show, Random Forest (RF) with PCA achieves the entire accuracy of 95% in FDIA detection.
- Published
- 2022
6. Solar radiation – to – power generation models for one-axis tracking PV system with on-site measurements from Eskisehir, Turkey
- Author
-
Filik Tansu, Başaran Filik Ümmühan, and Gerek Ömer Nezih
- Subjects
Environmental sciences ,GE1-350 - Abstract
In this study, new analytic models are proposed for mapping on-site global solar radiation values to electrical power output values in solar photovoltaic (PV) panels. The model extraction is achieved by simultaneously recording solar radiation and generated power from fixed and tracking panels, each with capacity of 3 kW, in Eskisehir (Turkey) region. It is shown that the relation between the solar radiation and the corresponding electric power is not only nonlinear, but it also exhibits an interesting time-varying characteristic in the form of a hysteresis function. This observed radiation-to-power relation is, then, analytically modelled with three piece-wise function parts (corresponding to morning, noon and evening times), which is another novel contribution of this work. The model is determined for both fixed panels and panels with a tracking system. Especially the panel system with a dynamic tracker produces a harmonically richer (with higher values in general) characteristic, so higher order polynomial models are necessary for the construction of analytical solar radiation models. The presented models, characteristics of the hysteresis functions, and differences in the fixed versus solar-tracking panels are expected to provide valuable insight for further model based researches.
- Published
- 2017
- Full Text
- View/download PDF
7. Performance Investigation of On-Grid Solar Photovoltaic System in Eskişehir/Turkey
- Author
-
ADAN, Hussein Kerow, primary and BAŞARAN FİLİK, Ümmühan, additional
- Published
- 2021
- Full Text
- View/download PDF
8. Performance Investigation of On-Grid Solar Photovoltaic System in Eskişehir/Turkey
- Author
-
ADAN, Hussein Kerow and BAŞARAN FİLİK, Ümmühan
- Subjects
Engineering ,Mühendislik ,On Grid Photovoltaic System,Performance Analysis,Capacity factor,Performance Ratio,PVSYST Program,On Grid Photovoltaic System,Performance Analysis,Capacity factor,Performance Ratio,PVSYST Program ,Şebekeye bağlı fotovoltaik sistem,Performans analizi,Kapasite faktörü,PVSYST programı - Abstract
Bu çalışmada Eskişehir Teknik Üniversitesi’nde bulunan 3 kW’lık şebeke bağlantılı fotovoltaik sistemin performans analizi yapılmıştır. Sistem 12 tane 260 W_p PV modülüne sahiptir ve 3 kW eviriciye bağlıdır. PV panellerden elde edilen çıkış enerjisi, şebekeye beslenen enerji, kurulu güç başına düşen performans oranı ve verim değerleri sonuçlarda sunulmuştur. PV sistemin üretim miktarı 4839 kWh/yıl, elektrik şebekesine gönderilen enerji 4648 kWh/yıldır. Sistemin performans oranı %84,8 ve üretimi 4.08 kWh/kW/gün ’dür. Sistemin toplam verim değerleri, dünyadaki diğer bazı sistemlerle karşılaştırılmıştır. Yapılan çalışmanın sonuçlarına göre, Eskişehir bölgesinin Avrupa’daki çoğu yerden daha iyi bir güneş enerjisi potansiyeline sahip olduğu, ancak Afrika veya Asya’daki güneş PV sistemleri kadar iyi olmadığı sonucuna varılmıştır., The paper presents a performance investigation of a 3-kW grid interactive photovoltaic system located at Eskişehir Technical University using PVSYST program. The system has 260 W_p, 12 PV modules and is connected to a 3-kW inverter. Parameters like the energy from PV panels, energy fed to the utility grid, performance ratio and final yield per installed 〖kW〗_p is presented. The system produces 4839 kWh/year and injects 4648 kWh/year into the utility grid. It has a performance ratio of 84.8% and the specific production of 4.08 kWh/〖kW〗_p/day. The specific production is compared to other systems in the literature review around the world. The paper concludes that Eskişehir region has a better solar energy potential than most places in Europe but not as good as the solar PV systems located in Africa or Asia.
- Published
- 2020
9. A comprehensive study on modeling of photovoltaic arrays and calculation of photovoltaic potential using digital elevation model
- Author
-
Bitirgen, Kübra, primary and Başaran Filik, Ümmühan, additional
- Published
- 2020
- Full Text
- View/download PDF
10. HOURLY GLOBAL SOLAR RADIATION ESTIMATION BASED ON MACHINE LEARNING METHODS IN ESKISEHIR
- Author
-
ALSAFADI, Massa, primary and BAŞARAN FİLİK, Ümmühan, additional
- Published
- 2020
- Full Text
- View/download PDF
11. OPTIMAL RESIDENTIAL LOAD CONTROL COMPARISON USING LINEAR PROGRAMMING AND SIMULATED ANNEALING FOR ENERGY SCHEDULING
- Author
-
GÜLER, Emre, primary and BAŞARAN FİLİK, Ümmühan, additional
- Published
- 2020
- Full Text
- View/download PDF
12. A comprehensive study on modeling of photovoltaic arrays and calculation of photovoltaic potential using digital elevation model.
- Author
-
Bitirgen, Kübra and Başaran Filik, Ümmühan
- Subjects
- *
DIGITAL elevation models , *SOLAR radiation , *GEOGRAPHIC information systems , *SOLAR energy , *AIR pressure , *SOLAR technology , *SPACE-based radar - Abstract
In solar energy applications, a complete knowledge and detailed analysis of the solar radiation potential is a prerequisite. In this paper, two different photovoltaic (PV) potential analysis approaches are compared. The first approach is based on a simulation of PV array and six different solar radiation estimation models. The outputs of these models are compared with hourly ground measured data by using statistical error methods. The most suitable solar radiation model which gives more accurate results is used to calculate the PV potential of Engineering Faculty of Eskişehir Technical University. The PV panel simulation is implemented in Matlab/Simulink besides that a suitable algorithm is selected to calculate the possible amount of PV panel energy generation based on the hourly measured wind speed (WS), air pressure, global solar radiation (GSR), and temperature values. In the second approach, building roof surface PV potential of the selected area is calculated and the available roof area for PV installation is determined by using Aeronautical Geographical Information System (ArcGIS) software. When the performances of the methods are compared, these methods obtained satisfactory results. Furthermore, it is clear that the algorithms and effective factors of the two methods are different. The results of ArcGIS outperform the PV array simulation based on Badescu model by the reason of its suitability of selecting optimal site for PV installation. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
13. Solar Electricity Potential Based on ArcGIS Maps and Consumption of Energy for Engineering Faculty Buildings in Anadolu University
- Author
-
Bitirgen, Kübra, Başaran Filik, Ümmühan, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Abstract
10th International Conference on Electrical and Electronics Engineering (ELECO) -- NOV 30-DEC 02, 2017 -- Bursa, TURKEY, WOS: 000426978800024, It is very significant to predict the solar energy potential correctly while solar panel applications arc being carried out. This study describes a model for prediction of solar energy potential and compares the prediction and energy consumption values in Engineering Faculty building roofs of Iki Eyltil Campus in Anadolu University. In order to evaluate this potential, a digital surface model (DSM) and high-resolution orthoimage are modeled and annual solar radiation maps included direct and diffuse solar radiations are generated at Solar Analyst platform of ArcGIS. Then, optimal tilt angle, aspect and site latitude factors are considered in selection of panel location. When total consumption and prediction values are compared the results show that estimated energy are compensated a substantial amount of energy consumption of the selected area., Chamber Elect Engineers Bursa Branch, Uludag Univ, Fac Engn, Dept Elect & Elect Engn, Istanbul Tech Univ, Fac Elect & Elect Engn, Sci & Technolog Res Council Turkey, IEEE Turkey Sect, Anadolu University [1705F291, 1505F512], Thanks to Earth and Space Sciences Institute of Anadolu University that provided us Digital Elevation Data and Aerial Image of the Campus. This work is funded by Anadolu University Scientific Research Project with project number: 1505F512 and 1705F291.
- Published
- 2017
14. Power Output Forecasting of a Solar House by Considering Different Cell Temperature Methods
- Author
-
Ayvazoğlüyüksel, Özge, Başaran Filik, Ümmühan, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Abstract
10th International Conference on Electrical and Electronics Engineering (ELECO) -- NOV 30-DEC 02, 2017 -- Bursa, TURKEY, WOS: 000426978800222, Forecasting of power generation is needed for accurate design and performance evaluation of solar energy systems to associate demand and source side dynamics efficiently. Since the power output values of solar energy systems are significantly affected by the cell temperature, estimation of cell temperature has gathered wide interest in recent years. In this study, cell temperature values of the on-grid photovoltaic panels of a solar house placed in Anadolu University. Iki Eylul Campus are estimated by using six different models. In addition, power output values of the system are forecasted with three different models by using the estimated cell temperature values, measured outdoor parameters and panel specifications. Therefore, the most accurate models for cell temperature estimation and power forecasting are determined according to the results of statistical test analysis methods., Chamber Elect Engineers Bursa Sect Branch, Uludag Univ, Fac Engn, Dept Elect & Elect Engn, Istanbul Tech Univ, Fac Elect & Elect Engn, Sci & Technolog Res Council Turkey, IEEE Turkey Sect, Scientific Research Projects Commission of Anadolu University [1705F291, 1505F512], This study is supported in part by the Scientific Research Projects Commission of Anadolu University under the grants of 1505F512 and 1705F291.
- Published
- 2017
15. Technical and economic evaluation of a standalone and on grid hybrid renewable energy: A case study at Eskişehir Technical University.
- Author
-
ADAN, Hussein Kerow and BAŞARAN FİLİK, Ümmühan
- Subjects
- *
HYBRID systems , *GRIDS (Cartography) , *PROBLEM solving , *FOSSIL fuels , *POWER resources - Abstract
Because of high-energy demand, population increase and exhaustion of fossil fuels, renewable energy is being utilized around the world especially for hybrid systems. The hybrid system should be optimally sized hence the aim of the study is to determine the technical and economic evaluation of a standalone and on grid hybrid system to supply power to the Department of Electrical and Electronics Engineering in Eskişehir Technical University. Hybrid optimization model for multiple energy resources (HOMER) program is used to achieve the optimal configuration of the standalone and on grid hybrid system and these systems are compared to each other to see the most economical one according to the net present cost (NPC) and cost of energy (COE). The result revealed that the most optimal configuration of the two systems is PV/Grid hybrid system with 198kW PV panel and the grid. It has NPC and COE of $1.68M and 0.176$/kWh but is not environmentally friendly as a standalone system due to low renewable fraction (RF). Overall, by using hybrid renewable energy systems (HES), the study is trying to solve the problem of reliability, cost and environmental concerns of the conventional energy sources. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
16. Solar radiation forecasting by using deep neural networks in Eskişehir.
- Author
-
QASEM, Mohammed and BAŞARAN FİLİK, Ümmühan
- Subjects
- *
SOLAR radiation , *STANDARD deviations , *SOLAR energy conversion , *ARTIFICIAL neural networks , *SOLAR energy , *ELECTRIC power consumption , *CLEAN energy - Abstract
According to the World Economic Outlook (WEO), the global demand for energy is presumably going to be increased due to growing the world's population up during the upcoming two decades. As a result of that, apprehensions about environmental effects, which appear as a result of greenhouse gases are grown and cleaner energy technologies are developed. This clearly shows that extended growth of the worldwide market share of clean energy. Solar energy is considered as one of the fundamental types of renewable energy. For this reason, the need for a predictive model that effectively observes solar energy conversion with high performance becomes urgent. In this paper, classic empirical, artificial neural network (ANN), deep neural network (DNN), and time series models are applied, and their results are compared to each other to find the most accurate model for daily global solar radiation (DGSR) estimation. In addition, four regression models have been developed and applied for DGSR estimation. The obtained results are evaluated and compared by the root mean square error (RMSE), relative root mean square error (rRMSE), mean absolute error (MAE), mean bias error (MBE), t-statistic, and coefficient of determination (R2). Finally, simulation results provided that the best result is found by the DNN model. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
17. A Hysteresis Model for Fixed and Sun Tracking Solar PV Power Generation Systems
- Author
-
Başaran Filik, Ümmühan, primary, Filik, Tansu, additional, and Gerek, Ömer, additional
- Published
- 2018
- Full Text
- View/download PDF
18. EFFICIENCY ANALYSIS OF THE SOLAR TRACKING PV SYSTEMS IN ESKISEHIR REGION
- Author
-
Filik, Tansu, primary and Başaran Filik, Ümmühan, additional
- Published
- 2017
- Full Text
- View/download PDF
19. Comparative Solution of Unit Commitment Problem Using Three Different Methods
- Author
-
Kurban, Mehmet, Başaran Filik, Ümmühan, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Unit Commitment ,Lagrange Relaxation ,Dynamic Programming ,Power System Optimization ,Simulated Annealing - Abstract
WOS: 000273608400005, In this paper, unit commitment problem which is an important subject in power system optimization, is solved by using dynamic programming, Lagrange relaxation, and simulated annealing methods. Dynamic programming method evaluates possible unit commitment schedules associated with decision made in the proceeding step by considering all constraints before searching for a schedule that yields the minimum cost. Lagrangian relaxation method, which is based on mathematical optimization, presents a solution for unit commitment problem. Simulated annealing is a method which refers to the process of heating up a solid to a high temperature followed by slow cooling achieved by decreasing the temperature of the environment in steps and gives feasible solutions for optimization problems. In the simulations made by using MATLAB (R), the operation conditions and total costs of the units are found by using three different solving methods. The solutions are given in the tables and methods used are compared. Four-unit in Tuncbilek thermal plant which is in Kutahya region, Turkey, are used as an example for the unit commitment problem. The data used in this paper is taken from (TEPC) Turkish Electric Power Company and (EGC) Electricity Generation Company.
- Published
- 2009
20. Next Day Load Forecasting Using Artificial Neural Network Models With Autoregression and Weighted Frequency Bin Blocks
- Author
-
Kurban, Mehmet, Başaran Filik, Ümmühan, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Artificial Neural Network ,Load Forecasting ,Autoregressive ,Weighted Frequency Bin Blocks - Abstract
WOS: 000265260800007, In this study, two different hybrid approaches based on Artificial Neural Network (ANN) models with Autoregressive (AR) method and Weighted Frequency Bin Blocks (WFBB), are used for next day load forecasting. To compare with the hybrid approaches and conventional models, the next day load forecasting is also performed by using AR and ANN models, separately. In the first hybrid approach, ANN model with AR method, the results of the AR method applied to all data taken from Turkish Electric Power Company and Electricity Generation Company, is used as an only additional input for ANN model. In this approach, the ANN structure has two layers composed of 49 and 24 neurons for input and output layers, respectively. In the second hybrid approach, ANN model with WFBB, the results obtained from WFBB are used for all inputs in the ANN. model. In this approach, input and output layers in the ANN structure are composed of 48 and 24 neurons, respectively. Feed Forward Back Propagation (FFBP) is chosen for all neural network models in this study. The forecasting results obtained from AR, ANN and the two hybrid models are compared to each other in the sense of root mean square error (RMSE). It is observed that the RMSE values for the hybrid approaches are smaller titan the conventional models. Then, the hybrid models forecast better than the conventional models.
- Published
- 2009
21. Neural and mathematical modeling approaches for hourly long term loadforecasting
- Author
-
Başaran Filik, Ümmühan, Gerek, Ömer Nezih, Kurban, Mehmet, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Başaran Filik, Ümmühan, and Gerek, Ömer Nezih
- Subjects
Artificial Neural Network ,Mathematical Modeling ,Load Forecasting - Abstract
In this work, a mathematical model and an Artificial Neural Network (ANN)approach are constructed for the hourly forecasting of long term electric energydemand. Unlike former studies, these methods produce long term load forecastingresults at an accuracy level of hourly precision. The proposed mathematicalmodel of the load is compared with a feed-forward ANN model output in the senseof Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Themathematical model provides a simple, intuitive and more generalized form,whereas the ANN model provides a specified model fine-tuned for the availabledata. The suitability of these methods is illustrated and verified using4-year-long real-life hourly load data taken from Turkish Electric PowerCompany. ICIC International © 2009.
- Published
- 2009
22. Unit Commitment Scheduling by Using the Autoregressive and Artificial Neural Network Models Based Short-Term Load Forecasting
- Author
-
Kurban, Mehmet, Başaran Filik, Ümmühan, Anadolu Üniversitesi, and Başaran Filik, Ümmühan
- Subjects
Unit Commitment ,Lagrange Relaxation ,Load Forecasting ,Ar ,Ann Model - Abstract
10th International Conference on Probabilistic Methods Applied to Power Systems -- MAY 25-29, 2008 -- Rincon, PR, WOS: 000271680900023, In this study, unit commitment (UC) problem is solved for an optimum schedule of generating units based on the load data forecasted by using Artificial Neural Network (ANN) model and ANN model with Autoregressive (AR). Low-cost generation is important in power system analysis. Under forecasting or over forecasting will result in the requirement of purchasing power from spot market or an unnecessary commitment of generating units. Accurate load forecasting is the first step to enhance the UC solution. Lagrange Relaxation (LR) method is used for solving the UC problem. Total costs calculated for the actual load and two different forecasting load data are compared. Four-unit Tuncbilek thermal plant which is in Kutahya region, Turkey, is used for this analysis. The data used in this analysis is taken from Turkish Electric Power Company and Electricity Generation Company. All the analyses are implemented using MATLAB (R)., Georgia Power, BC Transmiss Corp, Amer Elect Power, Recinto Univ Mayaguez, IEEE, AES, IEEE PES, EcoElectrica, Windmar
- Published
- 2008
23. Unit commitment scheduling by using the neural network-weighted frequency bin blocks based next day load forecasting
- Author
-
Başaran Filik, Ümmühan, Kurban, Mehmet, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Artificial Neural Network And Unit Commitment ,Power Economics ,Load Forecasting ,Power System Planning - Abstract
10th IASTED International Conference on Power and Energy Systems, PES 2008 -- 16 April 2008 through 18 April 2008 -- Baltimore, MD -- 75518, Unit commitment (UC) and load forecasting analyses are important because low-cost generation is one of the most significant points in power systems. Since UC solves for an optimum schedule of generating units based on load forecasting data, an accurate load forecasting is also very important in power system optimal planning and operation. Scheduling improperly the generating units due to under forecasting or over forecasting will result in the requirement of purchasing power from spot market or an unnecessary commitment of generating units. Therefore, the load forecasting is made as the first step to enhance the UC solution. Artificial Neural Network (ANN) and ANN model withWeighted Frequency Bin Blocks (WFBB) are used for the load forecasting. Then UC problem is solved by using the SA method and simulation results of these methods are compared. Comparing to these total costs show that load forecasting is important for unit commitment. Fourunit Tuncbilek thermal plant which is in Kutahya region in Turkey, is used for this analysis. The data used in the analysis is taken from Turkish Electric Power Company and Electricity Generation Company. All the analyses are implemented using MATLAB.
- Published
- 2008
24. Parameters and power flow analysis of the 380-kV interconnected power system in Turkey
- Author
-
Kurban, Mehmet, Başaran Filik, Ümmühan, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
380 Kv ,Line Parameters ,Transmission Line ,Power Flow - Abstract
1st International Power and Energy Conference (PECon 2006) -- NOV 28-29, 2006 -- Putrajaya, MALAYSIA, WOS: 000245900400046, This paper presents all the general overview of the interconnected power system in Turkey which consists of 30 generation and 35 load buses, totaling 65 buses connected each other with 380-kV power transmission lines. Also the. power flow analysis implemented using MATLAB (R) is made to find optimal operating points of the system and to make power systems generation planning. AD data used. in this analysis is taken from TEIAS (Transmission System Operator of Turkey) and EUAS (Electricity. Generation Co. Inc.), IEEE Power Engn Soc Chapter, Malaysia, PELS, IAS, IES Chapter, Malaysia
- Published
- 2006
25. New Electric Transmission Systems: Experiences from Turkey
- Author
-
Başaran Filik, Ümmühan, primary, Filik, Tansu, additional, and Nezih Gerek, Ömer, additional
- Published
- 2015
- Full Text
- View/download PDF
26. Birim Yüklenme Probleminin İki Farklı Ekonomik Dağıtım Yaklaşımlı
- Author
-
KURBAN, Mehmet and BAŞARAN FİLİK, Ümmühan
- Subjects
lcsh:Agriculture ,lcsh:Technology (General) ,lcsh:S ,lcsh:T1-995 ,lcsh:Agriculture (General) ,lcsh:S1-972 - Abstract
Bu çalışmada, güç sistemi optimizasyonunda önemli bir konu olan birim yüklenme problemi, iki farklı ekonomik dağıtım yaklaşımına dayalı benzetimli tavlama yöntemi ile çözülmüştür. Kullanılan ekonomik dağıtım yaklaşımları ikinci derece gradient ve lamda-öteleme yöntemleridir. MATLAB kullanılarak yapılan simülasyonlarda iki farklı yaklaşım için birimlerin çalışma durumları ve toplam maliyet değerleri bulunmuştur. Birim yüklenme problemi için Türkiye'de Kütahya bölgesinde bulunan dört birimli Tunçbilek termik santrali ele alınmış ve çözümler çizelgeler halinde verilmiştir. Bu çalışmada kullanılan veriler, TEİAŞ (Türkiye Elektrik İletim Anonim Şirketi) ve EÜAŞ (Elektrik Üretim Anonim Şirketi) 'tan alınmıştır.
- Published
- 2009
27. Solving Unit Commitment Problem Using Modified Subgradient Method Combined with Simulated Annealing Algorithm
- Author
-
Başaran Filik, Ümmühan, primary and Kurban, Mehmet, additional
- Published
- 2010
- Full Text
- View/download PDF
28. A Comparative Study of Three Different Mathematical Methods for Solving the Unit Commitment Problem
- Author
-
Kurban, Mehmet, primary and Başaran Filik, Ümmühan, additional
- Published
- 2009
- Full Text
- View/download PDF
29. Short Term Wind Speed Prediction Based on Autoregressive and Artifical Neural Networks as a New Hybrid Approach
- Author
-
Başaran Filik, Ümmühan, Filik, Tansu, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Başaran Filik, Ümmühan, and Filik, Tansu
- Subjects
Elektrik ve Elektronik ,Mühendislik ,Ekoloji ,Fizik ,Jeoloji ,İmalat Mühendisliği ,İnşaat Mühendisliği ,Kimya ,Yerbilimleri ,Otoregresif model,Rüzgâr enerjisi,Rüzgâr hızı,Yapay sinir ağları ,Okyanus ,Nanobilim ve Nanoteknoloji ,Uygulamalı ,Makine ,Robotik ,İstatistik ve Olasılık ,Tıbbi ,Ortak Disiplinler ,Telekomünikasyon ,Rüzgâr enerjisi,rüzgâr hızı,otoregresif model,yapay sinir ağları ,Partiküller ve Alanlar ,Matematik ,İnşaat ve Yapı Teknolojisi ,Uzaktan Algılama ,Zooloji ,Entomoloji ,Nükleer ,Organik ,Savunma Bilimleri ,Deniz ,Akışkanlar ve Plazma ,Çevre Bilimleri ,Çevre Mühendisliği ,Termodinamik ,Biyoliji Çeşitliliğinin Korunuması ,Polimer Bilimi ,Hava ve Uzay ,Analitik ,Atomik ve Moleküler Kimya ,Katı Hal ,Biyoloji - Abstract
Rüzgâr enerjisinin elektrik şebekesine entegrasyonu, ekonomik dağıtımı için ayrıca rüzgâr türbinlerinin güvenli işletilebilmesi kontrolü için kısa-dönem rüzgâr hızı tahmini önemli bir konudur. Rüzgâr hızının anlık değişkenliği problemi zorlaştırmaktadır. Bu çalışmada, kısa-dönem rüzgâr hızı tahmini için doğrusal otoregresif, AR ve doğrusal olmayan yapay sinir ağları, YSA modelleri aynı anda kullanan yeni hibrit bir model önerilmektedir. AR modeller yaygın olarak tahmin problemlerinde kullanılan istatiksel yöntemlerdir. YSA yaklaşımı başlıca modelleme, tahmin ve sınıflandırma problemlerinde kullanılan insan beynindeki sinir ağlarına benzer şekilde çalışan bir yaklaşımdır. Bu çalışmada tahmin problemlerinde kullanılan iki güçlü yöntem birleştirilerek kısa dönem rüzgâr hızının belirlenmesinde yeni bir hibrit yaklaşım olarak sunulmuştur. Bu yaklaşım ile sadece AR yöntemin kullanıldığı ya da sadece YSA yönteminin kullanıldığı yöntemlere göre rüzgâr hızı tahmininde daha başarılı sonuçlar elde edilmiştir. Çalışmanın doğruluğunu göstermek amacıyla meteoroloji istasyonundan alınan Eskişehir bölgesine ait sekiz yıllık gerçek saatlik ortalama rüzgâr hızı değerleri kullanılmıştır. Yedi yıllık rüzgâr hızı değerleri eğitim verileri olarak kullanılmış, kalan bir yıllık değerler test amacıyla kullanılmıştır. Farklı durumlar için önerilen hibrit yaklaşımın kök ortalama kare hata değerleri RMSE ve ortalama mutlak hata MAE değerleri AR ve YSA yöntemlerinin doğrudan kullanılmasına göre daha düşük sonuçlara ulaştığı gösterilmiştir, Rüzgâr enerjisinin elektrik şebekesine entegrasyonu, ekonomik dağıtımı için ayrıca rüzgâr türbinlerinin güvenli işletilebilmesi kontrolü için kısa-dönem rüzgâr hızı tahmini önemli bir konudur. Rüzgâr hızının anlık değişkenliği problemi zorlaştırmaktadır. Bu çalışmada, kısa-dönem rüzgâr hızı tahmini için doğrusal otoregresif, AR ve doğrusal olmayan yapay sinir ağları, YSA modelleri aynı anda kullanan yeni hibrit bir model önerilmektedir. AR modeller yaygın olarak tahmin problemlerinde kullanılan istatiksel yöntemlerdir. YSA yaklaşımı başlıca modelleme, tahmin ve sınıflandırma problemlerinde kullanılan insan beynindeki sinir ağlarına benzer şekilde çalışan bir yaklaşımdır. Bu çalışmada tahmin problemlerinde kullanılan iki güçlü yöntem birleştirilerek kısa dönem rüzgâr hızının belirlenmesinde yeni bir hibrit yaklaşım olarak sunulmuştur. Bu yaklaşım ile sadece AR yöntemin kullanıldığı ya da sadece YSA yönteminin kullanıldığı yöntemlere göre rüzgâr hızı tahmininde daha başarılı sonuçlar elde edilmiştir. Çalışmanın doğruluğunu göstermek amacıyla meteoroloji istasyonundan alınan Eskişehir bölgesine ait sekiz yıllık gerçek saatlik ortalama rüzgâr hızı değerleri kullanılmıştır. Yedi yıllık rüzgâr hızı değerleri eğitim verileri olarak kullanılmış, kalan bir yıllık değerler test amacıyla kullanılmıştır. Farklı durumlar için önerilen hibrit yaklaşımın kök ortalama kare hata değerleri RMSE ve ortalama mutlak hata MAE değerleri AR ve YSA yöntemlerinin doğrudan kullanılmasına göre daha düşük sonuçlara ulaştığı gösterilmiştir.
30. Solar energy analysis of a home by considering outdoor parameters
- Author
-
Ayvazoğluyüksel, Özge, Başaran Filik, Ümmühan, Elektrik-Elektronik Mühendisliği Ana Bilim Dalı, Başaran-Filik, Ümmühan, and Fen Bilimleri Enstitüsü
- Subjects
Elektrik ve Elektronik Mühendisliği ,Güneş enerjisi ,Solar radiation ,Enerji depolama ,Electrical and Electronics Engineering - Abstract
Tez (yüksek lisans) - Anadolu Üniversitesi, Anadolu Üniversitesi, Fen Bilimleri Enstitüsü, Elektrik-Elektronik Mühendisliği Anabilim Dalı, Kayıt no: 433717, Bu tezde, Anadolu Üniversitesi İki Eylül Kampüsü'ne konumlandırılan bir ev için dış ortam parametreleri gözetilerek güneş enerjisi analizi gerçekleştirilmiştir. Bu analiz kapsamında, yatay yüzeyde saatlik küresel güneş ışınım değerleri, ölçülen günlük küresel güneş ışınım değerlerinden on bir farklı model kullanılarak tahmin edilmiştir. Ölçülen ve tahmin edilen saatlik küresel güneş ışınım değerleri karşılaştırılmıştır ve modellerin doğruluğu istatistiksel analiz yöntemleri kullanılarak değerlendirilmiştir. Elde edilen sonuçlar, Gueymard tarafından modifiye edilen Collares - Pereira ve Rabl (CPRG) modelinin göz önünde bulundurulan tüm modeller arasında genel olarak en yüksek doğruluğa sahip olduğunu göstermektedir. Olmo et al. modeli kullanılarak, CPRG modeli ile yatay yüzey için tahmin edilen saatlik küresel güneş ışınım değerleri eğimli yüzey değerlerine dönüştürülmüştür. Ayrıca, fotovoltaik modüllerin hücre sıcaklığı, dış ortam koşullarını ve üreticiler tarafından tanımlanan panel teknik özelliklerini göz önünde bulunduran yedi farklı model ile tahmin edilmiştir. Böylece, tahmin edilen hücre sıcaklığı ve eğimli yüzeydeki küresel güneş ışınım değerleri esas alınarak, şebeke-bağlantılı ve şebekeden-bağımsız sistemlerin güç üretim değerleri MATLAB ortamında bir model ile tahmin edilmiştir ve bu değerler gerçek güç üretim değerleri ile karşılaştırılmıştır. Standart yaklaşım ile tahmin edilen hücre sıcaklığı değerlerinin en iyi güç üretim tahmin değerlerini verdiği görülmüştür.
- Published
- 2016
31. Solar radiation forecasting by using deep neural networks in Eskişehir
- Author
-
Qasem, Mohammed Qasem Mohammed Saleh, Başaran Filik, Ümmühan, and İleri Teknolojiler Anabilim Dalı
- Subjects
Energy ,Enerji - Abstract
WEO'ya göre, küresel enerji talebinin önümüzdeki yirmi yılda dünya nüfusunun artması nedeniyle 2016'da% 30'dan 2040'ta% 40'a çıkacağı tahmin ediliyor. Bunun bir sonucu olarak, sera gazlarının neden olduğu çevre kirliliği ile ilgili endişeler artmakta ve daha temiz enerji teknolojileri geliştirilmektedir. Bu dünya çapında güneş enerjisi pazar payının genişlemiş büyümesini açıkça göstermektedir. Bu nedenle, güneş enerjisi dönüşümünü etkili bir şekilde gözlemleyen ve performansını gözlemleyen neredeyse gerçek zamanlı bir öngörü modeli, güneş enerjisi santrallerinin tasarımı için en iyi seçenek olarak kabul edilir.Bu çalışmada, güneş ışınımı tahmini için en uygun modeli bulma üzerinde çalışmalar yurütülmüştür. Bu kapsamda üç farklı yaklaşm temel alnarak problem matematiksel modeller, yapay sinir ağları ve derin öğrenme kullanılarak çözülmüştür. Ayırca, güneş ışınımı tahmini için dört yeni model oluşturulmuştur. Bütün bu yöntemlerin uygulamasında Eskişehir'deki meteroloji istasyondan alınan veriler kullanılmıştır. Elde edilen sonuçlar Kare Ortalamalarının Karekökü (RMSE), ortalama mutlak hata (MAE), ortalama önyargı hatası (MBE) ve test istatistiği (t-istatistiği) değerlerine kullanılarak detaylı bir şekilde karşılaştırılmıştır. Yapılan analiz sonucunda ele alan bölge için en iyi sonucu derin öğrenme yöntemi vermiştir.Anahtar Sözcükler: Güneş radyasyonu tahmini, ANN'ler, DNN'ler, Yapay zeka, Hibrit modeller According to the WEO, the global demand for energy is presumably going to increase, due to growing up the world's population during the upcoming two decades. As a result of that, apprehensions about environmental effects, which appear as a result of greenhouse gases, are grown and cleaner energy technologies are developed. This clearly shows that extended growth of the worldwide market share of solar energy. For this reason, a predictive model that effectively observes solar energy conversion and its performance is considered as the best choice for design solar energy plants.In this thesis, to find the most accurate model for solar radiation forecasting, many studies have been conducted. In this work, based on three different approaches, the problem was solved by using classic mathematical models, artificial neural network (ANN), and deep neural network (DNN) methods. Besides, four new models have been developed for solar radiation prediction. The data are obtained from the Turkish State Meteorological of Service. The obtained results are compared and evaluated by the root mean square error (RMSE), mean absolute error (MAE), mean bias error (MBE) and test statistics (t-statistic). As a result of the analysis, the best result was given by the deep learning (DL) method.Keywords: Solar radiation forecasting, ANN, DNN, Artificial intelligence, Hybrid models 76
- Published
- 2020
32. Makine öğrenme ve ampirik modeller kullanılarak Eskişehir'de saatlik küresel güneş radyasyonunun tahmini
- Author
-
Alsafadi, Massa, Başaran Filik, Ümmühan, and Elektrik-Elektronik Mühendisliği Ana Bilim Dalı
- Subjects
Engineering Sciences ,Mühendislik Bilimleri - Abstract
Güneş panellerine etki eden kısa dönem küresel güneş radyasyonu miktarını bilmenin önemi arttığı için, saatlik küresel güneş radyasyonu (HGSR) daha doğru ve güvenilir enerji üretim tahmini için gereklidir. Günümüzde, makine öğrenimi (ML) yöntemleri veri tahmini için büyük bir trend haline geliyor. Bu çalışmada, ML yöntemlerinin HGSR'yi tahmin etmede güvenilirliği göstermek için beş ampirik modelin ML yöntemini ile Eskişehir şehri için karşılaştırması yapılmıştır. ML yöntemlerinden, yapay sinir ağı (YSA), regresyon ağacı (RT) ve destek vektör regresyonu (SVR), HGSR'yi tahmin etmek için bu çalışmada kullanılan yöntemlerdir. Bu çalışmalar, Türkiye Devlet Meteoroloji İşleri Genel Müdürlüğü'nden elde edilen bir yıllık veri seti üzerinde gerçekleştirilmiştir. Bu yöntemlerin karşılaştırılması MATLAB yazılımı kullanılarak yapılmıştır. Bununla birlikte, bu çalışma Collares-Pereira ve Rabl (CPRG) modelinin diğer ampirik modeller arasında en doğru sonucu verdiğini kanıtlamıştır. Buna ragmen, ML yöntemleri, CPRG ampirik modelinden daha iyi performans göstermiştir. Hemen hemen tüm ML modelleri neredeyse benzer sonuçlar vermesine rağmen, SVR aralarında en iyisidir. Özetle, ML'nin güneş enerji tahmini alanında, gelecekte HGSR'yi mükemmel bir şekilde tahmin etmek için dikkate alınması gereken başarılı yöntemler olduğu gözlemlenmiştir.Anahtar Sözcükler: Saatlik Küresel Güneş Radyasyonu, Makine Öğrenmesi, Yapay Sinir Ağı, Regresyon Ağacı, Destek Vektör Regresyonu Due to the increasing importance of knowing short term data of global solar radiation amount incident on solar panels, hourly global solar radiation (HGSR), is essentially required to obtain more accurate and reliable power generation prediction. Nowadays, Machine Learning (ML) methods are becoming a huge trend for data forecasting. In this study, to ensure that ML methods are reliable to estimate HGSR, a comparison between five existing empirical models and ML methods for HGSR estimation in Eskişehir city, Turkey is conducted. Artificial Neural Network (ANN), Regression Tree (RT) and Support Vector Regression (SVR) are popular ML methods that are used to predict HGSR in this study. In addition, this study is carried out on one year data set which is obtained from Turkish State Meteorological Service. The comparisons are implemented using MATLAB software to demonstrate these techniques. However, this study proved that Collares-Pereira & Rabl (CPRG) model gives the most accurate result among other empirical models. Nevertheless, ML methods also outperform CPRG empirical model. Despite the fact that almost all ML models gave almost similar results, SVR was the best among them. In a nutshell, it has been observed that ML methods are one of the successful methods that should be taken into consideration to perfectly estimate HGSR in the future in the field of solar energy estimation.Keywords: Hourly Global Solar Radiation, Machine Learning, Artificial Neural Network, Regression Tree, Support Vector Regression 71
- Published
- 2020
33. Estimation methods of global solar radiation, cell temperature and solar power forecasting: A review and case study in Eskişehir
- Author
-
Özge Ayvazoğluyüksel, Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Meteorology ,Renewable Energy, Sustainability and the Environment ,business.industry ,020209 energy ,Photovoltaic system ,Cell Temperature ,Power Generation ,02 engineering and technology ,Solar energy ,Solar power forecasting ,Power (physics) ,Global solar radiation ,Electricity generation ,0202 electrical engineering, electronic engineering, information engineering ,Astrophysics::Solar and Stellar Astrophysics ,Environmental science ,Solar Radiation ,Astrophysics::Earth and Planetary Astrophysics ,business ,Solar power ,Energy (signal processing) - Abstract
WOS: 000434919600044, Solar energy is the most important energy resource that has become an efficient solution to the world's energy challenges. Accurate knowledge of global solar radiation and cell temperature are required for solar photovoltaic power forecasting. In this paper, a comprehensive literature review of methods used for estimation of global solar radiation, cell temperature and solar power generation forecasting are presented. In addition, a comparative analysis is presented using the actual data, which is collected from a home placed in Anadolu University Iki Eylul Campus in Eskisehir as a comprehensive case study. Within the scope of this analysis, hourly global solar radiation values on horizontal surface are estimated from the measured daily global solar radiation values by using eleven different models. By using the selected model, estimated hourly global solar radiation values for horizontal surface are converted to values for inclined surface. Cell temperature of the photovoltaic modules is estimated with various known models in the literature. Based on the estimated cell temperature and global solar radiation values on inclined surface, power generation values of the on-grid and off-grid systems are forecasted. Therefore, based on the statistical analysis, the most accurate models are recommended to be carried out in any location that has similar climatic conditions with the considered city., Scientific Research Projects Commission of Anadolu University [1604F170, 1505F512], This study is supported in part by the Scientific Research Projects Commission of Anadolu University under the master thesis grant 1604F170 and the general purpose grant 1505F512.
- Published
- 2018
34. EFFICIENCY ANALYSIS OF THE SOLAR TRACKING PV SYSTEMS IN ESKISEHIR REGION
- Author
-
Tansu Filik, Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Filik, Tansu, and Başaran Filik, Ümmühan
- Subjects
Meteorology ,020209 energy ,Mühendislik ,Solar energy,Sun tracking PV system,Photovoltaic ,02 engineering and technology ,Tracking (particle physics) ,Solar tracker ,Engineering ,Solar energy ,lcsh:Technology (General) ,0202 electrical engineering, electronic engineering, information engineering ,Yield ratio ,Ortak Disiplinler ,Solar power ,business.industry ,Photovoltaic system ,Tracking system ,General Medicine ,021001 nanoscience & nanotechnology ,Power (physics) ,Sun tracking PV system ,lcsh:TA1-2040 ,Environmental science ,lcsh:T1-995 ,0210 nano-technology ,business ,lcsh:Engineering (General). Civil engineering (General) ,Photovoltaic - Abstract
In this study, efficiency analysis of the solar tracking photovoltaic (PV) system in Eskişehir region is considered for onsite real solar power generation values. It is shown that the tracking system's power generations are always higher than fixed one, but increased yield ratio is changing according to weather conditions (sunny or cloudy times). In order to make a fair analysis/comparison, all the instantaneous real solar power generations between 1 July and 30 October 2016 are used to figure out the ratio of sunny and cloudy days of the whole year. The averaged total generation values are calculated and it is revealed that the tracking system provides approximately 33 % higher electricity generation than the same capacity fixed PV panels for Eskişehir region.
- Published
- 2017
35. Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir
- Author
-
Ümmühan Başaran Filik, Tansu Filik, Caetano, ND, Felgueiras, MC, Forment, MA, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Başaran Filik, Ümmühan, and Filik, Tansu
- Subjects
Artificial Neural Network ,Engineering ,Wind power ,Meteorology ,Artificial neural network ,Mean squared error ,business.industry ,020209 energy ,Local variable ,02 engineering and technology ,Interval (mathematics) ,Wind direction ,Wind speed ,Energy(all) ,0202 electrical engineering, electronic engineering, information engineering ,Benchmark (computing) ,Wind Energy ,Wind Speed Prediction ,020201 artificial intelligence & image processing ,business ,Physics::Atmospheric and Oceanic Physics - Abstract
3rd International Conference on Energy and Environment Research (ICEER) -- SEP 07-11, 2016 -- Barcelona, SPAIN, WOS: 000400640900040, In this study, artificial neural network (ANN) based models, which differently uses multiple local meteorological measurements together such as wind speed, temperature and pressure values, are proposed and it shown ANN based multivariable model's wind speed predictions can be improved for various cases. A data monitoring system are used which can sensitively measures in milliseconds time interval and records the values of weather temperature, wind speed, wind direction and weather pressure in this study. The proposed ANN based multivariable model's root mean square error (RMSE) and mean absolute error (MAE) performances are presented and compared for various cases. The effect of using multiple local variables instead of wind speed only are analyzed and compared with persistence method for benchmark., Univ Poltecnica Catalunya, BarcelonaTECH, Anadolu University Scientific Research Projects Fund [1505F512], This work was supported by Anadolu University Scientific Research Projects Fund with project number: 1505F512.
- Published
- 2017
- Full Text
- View/download PDF
36. Comparison of linear programming and simulated annealing methods for optimal load control and energy scheduling in smart home
- Author
-
Güler, Emre, Başaran Filik, Ümmühan, and Elektrik-Elektronik Mühendisliği Anabilim Dalı
- Subjects
Elektrik ve Elektronik Mühendisliği ,Electrical and Electronics Engineering - Abstract
Elektrik fiyatlandırılması için birçok tarife kullanılmaktadır. Akıllı evlerde cihazlar için optimum çalışma saatleri ve uygun tarife seçilerek elektrik faturaları minimize edilebilir. Bunun için tezde, optimizasyon metotlarından Doğrusal Programlama ve Tavlama Benzetimi kullanılmıştır. Tezin amaçlarından biri bu metotların sonuçlarını karşılaştırmaktır. Tezde kullanılan çok zamanlı tarifelerde günün farklı saatlerinde farklı enerji birim fiyatları bulunur. Enerji yönetim sistemi, bazı cihazları ucuz enerji birim fiyatları olan zaman aralıklarına kaydırır. Cihazların çalışma saatlerini kaydırmaktan dolayı sistemde aşırı yük oluşabilir. Tezin ikinci amacı olarak aşırı yük oluşmasını engellemek için optimum yük kontrolü uygulanmıştır. Problemin matematiksel modeli oluşturulmuş ve GAMS uygulaması çözümde kullanılmıştır. Girdi olarak her saat aralığının enerji birim fiyatından oluşan maliyet tablosu kullanılmıştır. Ayrıca metasezgisel çözüm yöntemlerinden Tavlama Benzetimi teknikleri kullanılmış ve C# programı ile çözüme ulaşılmıştır. İki farklı çözüm yolu ile optimum elektrik maliyeti, cihazların çalışma saatleri ve pik-ortalama güç oranına ulaşılmış ve sonuçlar kıyaslanmıştır. Doğrusal Programlamanın daha iyi çözümler verdiği görülmüştür. Many tariffs are used for electricity pricing. Electricity bills can be minimized by choosing the optimal working hours of appliances and for appropriate tariffs in smart homes. For this reason, Linear Programming (LP) and Simulated Annealing (SA) optimization methods are used. One of the aims of the thesis is to compare the results of these methods. The multi-time tariffs which have different energy unit prices at different times of the day are used in the thesis. Energy Management System (EMS) shifts time slots of some appliances to cheap energy unit prices. There may be overload in system because of shifting of working hours of appliances. Optimal load control is applied to prevent high peak demand as the second aim of the thesis. Mathematical model of the problem is created and GAMS application is used in the solution. The cost table consisting of the energy unit prices of each time slot is used as input. Also, SA technique which is one of the metaheuristic solution methods is used and the solution has been reached using C# program. Optimum electricity cost, working hours of the appliances and peak to average ratio are achieved by two different solutions and the results are compared. The results of the LP are better than SA. 51
- Published
- 2019
37. A Hysteresis Model for Fixed and Sun Tracking Solar PV Power Generation Systems
- Author
-
Ümmühan Başaran Filik, Ömer Nezih Gerek, Tansu Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Başaran Filik, Ümmühan, Filik, Tansu, and Gerek, Ömer Nezih
- Subjects
Control and Optimization ,Computer science ,Sun tracking ,020209 energy ,solar radiation ,Energy Engineering and Power Technology ,02 engineering and technology ,photovoltaic ,output power ,temperature ,lcsh:Technology ,Control theory ,0202 electrical engineering, electronic engineering, information engineering ,Electrical and Electronic Engineering ,Engineering (miscellaneous) ,Rain and snow mixed ,Renewable Energy, Sustainability and the Environment ,business.industry ,lcsh:T ,Photovoltaic system ,Function (mathematics) ,021001 nanoscience & nanotechnology ,Power (physics) ,Renewable energy ,Hysteresis ,Electricity generation ,0210 nano-technology ,business ,Energy (miscellaneous) - Abstract
WOS: 000428304300131, In this study, a new solar photovoltaic (PV) panel output power model is proposed. The model is constructed as a function of ambient temperature and solar radiations for two types (fixed panel and sun tracking panel) of PV systems. The proposed models are tested and verified on the Renewable Energy Research Home (RERH) system that was installed at the Anadolu University campus in Eskisehir, Turkey. The model is deliberately constructed for the winter season, where cloudliness, rain and snow constitute more challenging conditions for modeling. The developed model outcomes are compared to the outputs of state of the art methods that use global solar radiation and temperature data. A total of eight algebraic models are constructed for the purpose of depicting the solar radiation-to-electric power behavior. It is observed that even the least successful one of these eight variants are performing better than the most accurate method in the literature. It is argued that mathematical incorporation of the proposed novel hysteresis functions to the solar radiation-to-power conversion curves results in a richer class of functions and causes a significant accuracy improvement on the mathematical power generation model, even for the most challenging season of winter., Anadolu University Research Fund [1705F291], This work was supported by Anadolu University Research Fund under contract no. 1705F291.
- Published
- 2018
38. Solar radiation estimation for modeling of PV arrays and calculation of solar energy potential based on ArcGIS
- Author
-
Bitirgen, Kübra, Başaran Filik, Ümmühan, Elektrik-Elektronik Mühendisliği Ana Bilim Dalı, Başaran, Ümmühan, and Fen Bilimleri Enstitüsü
- Subjects
Elektrik ve Elektronik Mühendisliği ,Güneş enerjisi ,Electrical and Electronics Engineering - Abstract
Tez (yüksek lisans) - Anadolu Üniversitesi, Anadolu Üniversitesi, Fen Bilimleri Enstitüsü, Elektrik-Elektronik Mühendisliği Anabilim Dalı, Kayıt no: 492451, Güneş enerjisi, en verimli alternatif enerji kaynaklarından biri olarak bilinir. Yeryüzüne ulaşan güneş ışınımı, güneş enerjisinin bir şeklidir. Güneş enerjisi uygulamaları, seçilen bölgenin güneş ışınımı potansiyeli hakkında tam bir bilgi ve ayrıntılı analiz gerektirir. Bu tezde, altı farklı güneş ışınımı hesaplama modeli kullanılarak Eskişehir için eğimli bir yüzey üzerinde saatlik küresel güneş ışınımı tahmin edilmiştir. Bu modellerin sonuçları, istatistiksel hata yöntemleri kullanılarak saatlik ölçüm verileri ile karşılaştırılmıştır. Tahmin sonuçları, modellerin performansını daha belirgin bir biçimde göstermek için aylık küresel güneş ışınımına dönüştürülmüştür. Uygun güneş ışınımı modeli seçildikten sonra, modeller karşılaştırıldığında, Eskişehir'in enerji potansiyelini hesaplamak için daha doğru sonuçlar veren model kullanılmıştır. MATLAB/Simulink programında ideal bir fotovoltaik panel simülasyonu uygulanmıştır, bunun yanı sıra, saatlik ölçülen rüzgar hızı, hava basıncı, küresel güneş ışınımı ve sıcaklık değerlerine dayalı olası PV panel enerji üretim miktarını hesaplamak için uygun bir algoritma seçilmiştir. PV potansiyelinin belirlenmesinden sonra, ideal PV simülasyonu ve tahmini PV potansiyeli sonuçları meteorolojik koşullar dikkate alınarak PV verimliliğini anlamak için karşılaştırılmıştır. Ayrıca, Anadolu Üniversitesi Mühendislik Fakültesi'nin bina çatı yüzeyinin PV potansiyeli hesaplanmış ve PV kurulumu için uygun çatı alanı ArcGIS yazılımı kullanılarak belirlenmiştir.
- Published
- 2018
39. Very Short Term Wind Speed Forecasting Using Multivariable Dense Data with WLS-MARMA Model
- Author
-
Ümmühan Başaran Filik, Tansu Filik, Caetano, ND, Felgueiras, MC, Forment, MA, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Filik, Tansu, and Başaran Filik, Ümmühan
- Subjects
010504 meteorology & atmospheric sciences ,Meteorology ,Computer science ,020209 energy ,02 engineering and technology ,01 natural sciences ,Wind speed ,Energy(all) ,0202 electrical engineering, electronic engineering, information engineering ,Astrophysics::Solar and Stellar Astrophysics ,Wind Energy ,Autoregressive–moving-average model ,Physics::Atmospheric and Oceanic Physics ,Weigted Least Squares ,0105 earth and related environmental sciences ,Wind power ,biology ,business.industry ,Autoregressive Moving Average ,Multivariable calculus ,Very Short-Term Wind Speed Forecasting ,Multivariable Data ,biology.organism_classification ,Term (time) ,Data set ,Physics::Space Physics ,Benchmark (computing) ,business ,Marma - Abstract
3rd International Conference on Energy and Environment Research (ICEER) -- SEP 07-11, 2016 -- Barcelona, SPAIN, WOS: 000400640900039, In this study, very short-term wind speed forecasting problem, which is quite important for the future's electricity market -wind forecasting control algorithms, is investigated. Recently, the multi-channel (spatial) methods which uses neighboring (from different locations) wind measurements are become popular. But it is not always possible to collect spatially distributed neighboring wind speed values around target location simultaneously. In this study, previously proposed multichannel autoregressive moving average (MARMA) model is applied to local multiple sensor measurements such as wind speed, direction, temperature, pressure, solar radiation etc. instead of neighboring (distributed) wind speed measurements. It is shown that weighted least squares solution based MARMA model (WLS-MARMA) can give more accurate wind speed estimation results according to other well-known benchmark methods (such as Persistence, AR, VAR) with real data set., Univ Poltecnica Catalunya, BarcelonaTECH, Anadolu University Scientific Research Projects fund [1505F512], This study is supported by Anadolu University Scientific Research Projects fund with project number 1505F512.
- Published
- 2017
40. Sizing procedures for sun-tracking PV system with batteries
- Author
-
Ömer Nezih Gerek, Tansu Filik, Ümmühan Başaran Filik, Kazmierczak, B, Kutylowska, M, Piekarska, K, Anadolu Üniversitesi, Mühendislik Fakültesi, Gerek, Ömer Nezih, Başaran Filik, Ümmühan, and Filik, Tansu
- Subjects
Engineering ,Wind power ,business.industry ,020209 energy ,Photovoltaic system ,02 engineering and technology ,Energy consumption ,010501 environmental sciences ,01 natural sciences ,Sizing ,Automotive engineering ,Wind speed ,Solar tracker ,Environmental sciences ,Electricity generation ,0202 electrical engineering, electronic engineering, information engineering ,GE1-350 ,business ,Solar power ,Simulation ,0105 earth and related environmental sciences - Abstract
International Conference on Advances in Energy Systems and Environmental Engineering (ASEE) -- JUL 02-05, 2017 -- Wroclaw, POLAND, WOS: 000417352100052, Deciding optimum number of PV panels, wind turbines and batteries (i.e. a complete renewable energy system) for minimum cost and complete energy balance is a challenging and interesting problem. In the literature, some rough data models or limited recorded data together with low resolution hourly averaged meteorological values are used to test the sizing strategies. In this study, active sun tracking and fixed PV solar power generation values of ready-to-serve commercial products are recorded throughout 2015-2016. Simultaneously several outdoor parameters (solar radiation, temperature, humidity, wind speed/direction, pressure) are recorded with high resolution. The hourly energy consumption values of a standard 4-person household, which is constructed in our campus in Eskisehir, Turkey, are also recorded for the same period. During sizing, novel parametric random process models for wind speed, temperature, solar radiation, energy demand and electricity generation curves are achieved and it is observed that these models provide sizing results with lower LLP through Monte Carlo experiments that consider average and minimum performance cases. Furthermore, another novel cost optimization strategy is adopted to show that solar tracking PV panels provide lower costs by enabling reduced number of installed batteries. Results are verified over real recorded data.
- Published
- 2017
41. A New Hybrid Approach for Wind Speed Prediction Using Fast Block Least Mean Square Algorithm and Artificial Neural Network
- Author
-
Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Engineering ,Mean squared error ,Article Subject ,020209 energy ,General Mathematics ,02 engineering and technology ,Machine learning ,computer.software_genre ,Wind speed ,Least mean squares filter ,0202 electrical engineering, electronic engineering, information engineering ,Block (data storage) ,Adaptive algorithm ,Artificial neural network ,business.industry ,lcsh:Mathematics ,General Engineering ,lcsh:QA1-939 ,Rate of convergence ,lcsh:TA1-2040 ,Artificial intelligence ,business ,lcsh:Engineering (General). Civil engineering (General) ,Algorithm ,computer ,Test data - Abstract
WOS: 000387376100001, A new hybrid wind speed prediction approach, which uses fast block least mean square (FBLMS) algorithm and artificial neural network (ANN) method, is proposed. FBLMS is an adaptive algorithm which has reduced complexity with a very fast convergence rate. A hybrid approach is proposed which uses two powerful methods: FBLMS and ANN method. In order to show the efficiency and accuracy of the proposed approach, seven-year real hourly collected wind speed data sets belonging to Turkish State Meteorological Service of Bozcaada and Eskisehir regions are used. Two different ANN structures are used to compare with this approach. The first six-year data is handled as a train set; the remaining one-year hourly data is handled as test data. Mean absolute error (MAE) and root mean square error (RMSE) are used for performance evaluations. It is shown for various cases that the performance of the new hybrid approach gives better results than the different conventional ANN structure., Anadolu University Scientific Research Projects Fund [1505F512], This work was supported by Anadolu University Scientific Research Projects Fund with Project no. 1505F512. The received fund covers the costs to publish in open access. And the author is grateful to the Turkish State Meteorological Service for providing the data.
- Published
- 2016
- Full Text
- View/download PDF
42. Short-Term Wind Speed Prediction Using Several Artificial Neural Network Approaches in Eskisehir
- Author
-
Mert Alper Duran, Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Wind power ,Meteorology ,business.industry ,Computer science ,Astrophysics::High Energy Astrophysical Phenomena ,Fossil fuel ,Back Propagation ,Feed forward ,Wind Speed ,Wind speed ,Renewable energy ,Electric power system ,Electricity generation ,Physics::Space Physics ,Alternative energy ,Wind Speed Prediction ,business ,Physics::Atmospheric and Oceanic Physics ,Simulation ,Artificial Neural Networks - Abstract
International Symposium on Innovations in Intelligent SysTems and Applications (INISTA 2015) -- SEP 02-04, 2015 -- Madrid, SPAIN, WOS: 000380428200026, Due to the negative environmental impact of using fossil energy sources and depletion of fossil fuels, the alternative energy sources are being searched all over the world. Since wind energy is clean and renewable, the penetration of wind energy for electricity generation is increasing day by day. Wind power plants require continuous and appropriate intensity winds. In terms of the reliability and power quality of the power system, the variability of wind energy has led to problems. To minimize these problems, highly accurate wind speed prediction method should be used. In this study, accurate short term wind speed prediction approach is aimed for increasing efficiency of wind energy production. The short term wind speed prediction approached is trained/tested with real three years hourly averaged wind speed values from Eskisehir region of Turkey. Feed forward backpropagation network and Levenberg-Marquardt algorithms are used for analyzing and the identified four network model are compared in terms of mean square error values., Univ Autonoma Madrid, Ai+da
- Published
- 2015
43. A novel modeling approach for hourly forecasting of long-term electric energy demand
- Author
-
Ümmühan Başaran Filik, Mehmet Kurban, Ömer Nezih Gerek, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Başaran Filik, Ümmühan, and Gerek, Ömer Nezih
- Subjects
Engineering ,Mathematical optimization ,Mean squared error ,Mathematical Modeling ,Renewable Energy, Sustainability and the Environment ,business.industry ,Energy Demand ,Energy Engineering and Power Technology ,Residual ,Term (time) ,Electric energy ,Fuel Technology ,Mean absolute percentage error ,Nuclear Energy and Engineering ,Probabilistic forecasting ,Electric power ,Representation (mathematics) ,business ,Surface Fitting ,Simulation ,Forecasting - Abstract
WOS: 000284746800023, In this study, a novel mathematical method is proposed for modeling and forecasting electric energy demand. The method is capable of making long-term forecasts. However, unlike other long-term forecasting models, the proposed method produces hourly results with improved accuracy. The model is constructed and verified using 26-year-long real-life load data (4 years with hourly resolution) obtained from the Turkish Electric Power Company. The overall method consists of a nested combination of three subsections for modeling. The first section is the coarse level for modeling variations of yearly average loads. The second section refines this structure by modeling weekly residual load variations within a year. The final section reaches to the hourly resolution by modeling variations within a week, using a novel 2-D mathematical representation at this resolution. The adoptions of such nested forecasting methodology together with the proposed 2-D representation for hourly load constitute the novelties of this work. The major advantage of the proposed approach is that it enables the possibility of making short-, medium-, and long-term hourly load forecasting within a single framework. Several mathematical functions are applied as models at each level of the nested system for achieving the minimal forecasting error. Proposed model functions with their corresponding forecasting accuracies are presented in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE)
- Published
- 2011
44. Solving Unit Commitment Problem Using Modified Subgradient Method Combined with Simulated Annealing Algorithm
- Author
-
Ümmühan Başaran Filik, Mehmet Kurban, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Mathematical optimization ,Schedule ,Duality gap ,Article Subject ,lcsh:Mathematics ,General Mathematics ,General Engineering ,lcsh:QA1-939 ,Convexity ,symbols.namesake ,lcsh:TA1-2040 ,Lagrangian relaxation ,Simulated annealing ,symbols ,Initial value problem ,Penalty method ,lcsh:Engineering (General). Civil engineering (General) ,Subgradient method ,Mathematics - Abstract
WOS: 000281094800001, This paper presents the solving unit commitment (UC) problem using Modified Subgradient Method (MSG) method combined with Simulated Annealing (SA) algorithm. UC problem is one of the important power system engineering hard-solving problems. The Lagrangian relaxation (LR) based methods are commonly used to solve the UC problem. The main disadvantage of this group of methods is the difference between the dual and the primal solution which gives some significant problems on the quality of the feasible solution. In this paper, MSG method which does not require any convexity and differentiability assumptions is used for solving the UC problem. MSG method depending on the initial value reaches zero duality gap. SA algorithm is used in order to assign the appropriate initial value for MSG method. The major advantage of the proposed approach is that it guarantees the zero duality gap independently from the size of the problem. In order to show the advantages of this proposed approach, the four-unit Tuncbilek thermal plant and ten-unit thermal plant which is usually used in literature are chosen as test systems. Penalty function (PF) method is also used to compare with our proposed method in terms of total cost and UC schedule., MSG, The support and guidance on MSG method by Professor Rafail N. Gasimov is gratefully acknowledged.
- Published
- 2010
45. Feasible Modified Subgradient Method for Solving the Thermal Unit Commitment Problem as a New Approach
- Author
-
Mehmet Kurban, Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Mathematical optimization ,Duality gap ,Article Subject ,General Mathematics ,lcsh:Mathematics ,General Engineering ,Zero (complex analysis) ,Value (computer science) ,lcsh:QA1-939 ,Dual (category theory) ,symbols.namesake ,Electric power system ,Lagrangian relaxation ,lcsh:TA1-2040 ,Convergence (routing) ,symbols ,lcsh:Engineering (General). Civil engineering (General) ,Subgradient method ,Mathematics - Abstract
WOS: 000281093600001, The Lagrangian relaxation- (LR-) based methods are commonly used to solve the thermal unit commitment (UC) problem which is an important subject in power system engineering. The main drawback of this group of methods is the difference between the dual and the primal solutions which gives some significant problems on the quality of the feasible solutions. In this paper, a new approach, feasible modified subgradient (F-MSG) method which does not require finding an unconstrained global minimum of the Lagrangian function and knowing an optimal value of the problem under consideration in order to update dual variables at the each iteration, is firstly used for solving the thermal UC problem. The major advantage of the proposed approach is that it guarantees the zero duality gap and convergence independently from the size of the problem. In order to discuss the advantages of this method, the four-unit Tuncbilek thermal plant, which is located in Kutahya region in Turkey, is chosen as a small test system. The numerical results show that F-MSG gives better solutions as compared to the standard LR method.
- Published
- 2010
46. A Comparative Study of Three Different Mathematical Methods for Solving the Unit Commitment Problem
- Author
-
Mehmet Kurban, Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Mathematical optimization ,Duality gap ,Article Subject ,Augmented Lagrangian method ,General Mathematics ,lcsh:Mathematics ,General Engineering ,Duality (optimization) ,lcsh:QA1-939 ,Electric power system ,Nonlinear system ,Power system simulation ,lcsh:TA1-2040 ,Penalty method ,lcsh:Engineering (General). Civil engineering (General) ,Metaheuristic ,Mathematics - Abstract
WOS: 000267563000001, The unit commitment (UC) problem which is an important subject in power system engineering is solved by using Lagragian relaxation (LR), penalty function (PF), and augmented Lagrangian penalty function (ALPF) methods due to their higher solution quality and faster computational time than metaheuristic approaches. This problem is considered to be a nonlinear programming (NP-) hard problem because it is nonlinear, mixed-integer, and nonconvex. These three methods used for solving the problem are based on dual optimization techniques. ALPF method which combines the algorithmic aspects of both LR and PF methods is firstly used for solving the UC problem. These methods are compared to each other based on feasible schedule for each stage, feasible cost, dual cost, duality gap, duration time, and number of iterations. The numerical results show that the ALPF method gives the best duality gap, feasible and dual cost instead of worse duration time and the number of iterations. The four-unit Tuncbilek thermal plant which is located in Kutahya region in Turkey is chosen as a test system in this study. The programs used for all the analyses are coded and implemented using general algebraic modeling system (GAMS). Copyright (C) 2009 M. Kurban and U. Basaran Filik.
- Published
- 2009
- Full Text
- View/download PDF
47. A new approach for next day load forecasting integrating Artificial Neural Network model with Weighted Frequency Bin Blocks
- Author
-
U. Basaran Filik, Mehmet Kurban, Ishikawa, M, Doya, K, Miyamoto, H, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Artificial neural network ,Mean squared error ,Computer science ,business.industry ,Load forecasting ,Computer Science::Neural and Evolutionary Computation ,Artificial neural network model ,Artificial intelligence ,Electric power ,Sense (electronics) ,business ,Algorithm ,Bin - Abstract
14th International Conference on Neural Information Processing (ICONIP 2007) -- NOV 13-16, 2007 -- Kitakyushu, JAPAN, WOS: 000257315300073, In this study, a new method is developed for the next day load forecasting integrating Artificial Neural Network(ANN) model with Weighted Frequency Bin Blocks (WFBB). After the WFBB is applied to all data, the results obtained from this analysis are used as the inputs in the ANN structure. However, the conventional ANN structure is also used for the next day load forecasting. The forecasting results obtained from ANN structure and the hybrid model are compared in the sense of root mean square error (RMSE). It is observed that the performance and the RMSE values for the hybrid model,the ANN model with WFBB, are smaller than the values for the conventional ANN structure. Furthermore, the new hybrid model forecasts better than the conventional ANN structure. The suitability of the proposed approach is illustrated through an application to actual load data taken from the Turkish Electric Power Company in 2002., RIKEN Brain Sci Inst, Adv Telecommun Res Inst Int, Japan SOc Fuzzy Theory & Intelligent Informat, IEEE CIS Japan Chap, Fuzzy Log Syst Inst
- Published
- 2008
48. Parameters and power flow analysis of the 380 -kV interconnected power system in Turkey
- Author
-
Ümmühan Başaran Filik, Mehmet Kurban, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
380 Kv ,Engineering ,Line Parameters ,Transmission Line ,business.industry ,Electrical engineering ,Power flow ,Electric power system ,Electric power transmission ,Electricity generation ,Transmission line ,Power-flow study ,Transmission system operator ,Power Flow ,MATLAB ,business ,computer ,computer.programming_language - Abstract
1st International Power and Energy Conference, PECon 2006 -- 28 November 2006 through 29 November 2006 -- Putrajaya -- 72409, This paper presents all the general overview of the interconnected power system in Turkey which consists of 30 generation and 35 load buses, totaling 65 buses connected each other with 380-kV power transmission lines. Also the power flow analysis implemented using MATLAB® is made to find optimal operating points of the system and to make power systems generation planning. All data used in this analysis is taken from TEIAS (Transmission System Operator of Turkey) and EUAS (Electricity Generation Co. Inc.) © 2006 IEEE.
- Published
- 2006
49. Optimal power flow analysis of the 22-bus 380-kV interconnected power system in Turkey
- Author
-
Mehmet Kurban, Ümmühan Başaran Filik, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, and Başaran Filik, Ümmühan
- Subjects
Engineering ,Karush–Kuhn–Tucker conditions ,business.industry ,Cost Function ,Lagrange ,Kuhn-Tucker ,Electric power system ,Electricity generation ,Electric power transmission ,Newton-Based Opf ,Electronic engineering ,Load bus ,Power-flow study ,Transmission system operator ,business ,MATLAB ,computer ,computer.programming_language - Abstract
1st International Power and Energy Conference (PECon 2006) -- NOV 28-29, 2006 -- Putrajaya, MALAYSIA, WOS: 000245900400055, In this paper, the Newton based optimal power now analysis (OPF) implemented using MATLAB (R) is applied for the 22-bus interconnected power system in Turkey which consists of 8 generation and 14 load bus connected each other with 380-kV power transmission lines. The results are given in the tables. All data used this analysis is taken from TEIAS (Transmission System Operator of Turkey) and EIJAS (Electricity Generation Co. Inc.)., IEEE Power Engn Soc Chapter, Malaysia, PELS, IAS, IES Chapter, Malaysia
- Published
- 2006
50. HOURLY FORECASTING OF LONG TERM ELECTRIC ENERGY DEMAND USING NOVEL MATHEMATICAL MODELS AND NEURAL NETWORKS
- Author
-
Filik, Ummuhan Basaran, Omer Nezih Gerek, Kurban, Mehmet, Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Başaran Filik, Ümmühan, and Gerek, Ömer Nezih
- Subjects
Artificial Neural Network Structures ,Mathematical Models ,Energy Demand ,Hourly Forecasting - Abstract
WOS: 000291711600037, In this work, hourly forecasting of long term electric energy demand is achieved using mathematical models and Artificial Neural Network (ANN) approaches. Previous works regarding energy demand forecasting either treated the problem of long term prediction over yearly averages, or considered hourly prediction using a very short term time lag, such as a few hours. The methods proposed in this work produce predictions with hourly accuracy despite the time lag of "years", making the model suitable for long term prediction. Several functions for mathematical modeling and different ANN structures are applied and tested for achieving small forecasting errors. The proposed mathematical models of the load are compared with different ANN model outputs in the sense of Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The mathematical models are observed to provide a simple, intuitive and more generalized form, whereas the ANN models provided specified models that are better fine-tuned for the available data. The suitability of these methods is illustrated and verified using 4-year-long real-life hourly load data taken from the Turkish Electric Power Company.
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.