Yazar "Zor, Kasim" seçeneğine göre listele

Listeleniyor 1 - 11 / 11
  • [ X ]
    Öğe
    A benchmark of GRU and LSTM networks for short-term electric load forecasting
    (Institute of Electrical and Electronics Engineers Inc., 2021) Zor, Kasim; Bulus, Kurtulus
    Recently, electric power systems have been modernised to be integrated with distributed energy systems having intermittent characteristics. Herein, short-term electric load forecasting (STLF), which covers hour, day, or week-ahead predictions of electric loads, is a crucial piece of the modern power system puzzle whose level of complexity has become more and more sophisticated owing to incorporating microgrids and smart grids. Due to the nonlinear feature of electric loads and the uncertainties in the modern power systems, deep learning algorithms are frequently applied to STLF problem which can be described as an arduous challenge because of being affected by several impacts. In this paper, gated recurrent unit (GRU) and long short-term memory (LSTM) networks are implemented in forecasting an hour-ahead electric loads of a large hospital complex located in Adana, Turkey. Overall results belonging to the benchmark of GRU and LSTM networks for STLF revealed that employing GRU networks performed better in terms of mean absolute percentage error (MAPE) by 7.8% and computational time by 15.5% in comparison with utilising LSTM networks. © 2021 IEEE.
  • [ X ]
    Öğe
    A hybrid deep learning algorithm for short-term electric load forecasting
    (IEEE, 2021) Bulus, Kurtulus; Zor, Kasim
    Over the last two decades, electric load forecasting has strengthened its significant role in electric power systems due to equalising the vital balance between generation and consumption of electrical energy for all actors of deregulated electricity markets. Artificial intelligence-based techniques are frequently used for short-term electric load forecasting owing to the abstruse nature of electric loads that can be influenced by a variety of factors. In this paper, a novel hybrid deep learning algorithm that combines GMDH and GRU networks is meticulously applied for one hour-ahead load forecasting of a large hospital complex. In the proposed algorithm, GMDH and GRU networks are employed for feature selection and prediction respectively. Consequently, the obtained results have demonstrated that the proposed algorithm is capable of reducing mean absolute percentage error by 12% and computational time by 5%.
  • [ X ]
    Öğe
    A novel gene expression programming-based MPPT technique for PV micro-inverter applications under fast-changing atmospheric conditions
    (Pergamon-Elsevier Science Ltd, 2022) Celik, Ozgur; Zor, Kasim; Tan, Adnan; Teke, Ahmet
    The erratic behavior of the atmospheric conditions adversely affects efficient energy harvesting and the stable operation of photovoltaic systems. It is therefore critical to draw maximum power from photovoltaic modules regardless of atmospheric conditions. The maximum power point tracking techniques have crucial impacts on both efficient and stable operation of photovoltaic systems as being the controller part of the power converters. In this paper, a novel gene expression programming-based maximum power point tracking technique is proposed for micro-inverter applications under fast-changing atmospheric conditions. In this context, the main objective of this study is to improve the significant performance indices of maximum power point tracking technique including convergence speed during transients, tracking accuracy, steady-state oscillations, and rate of overshoots for ensuring the stable and efficient operation of the photovoltaic micro-inverter system. The proposed maximum power point tracking technique is integrated to a two-stage grid-connected micro-inverter system and tested in terms of the aforementioned performance parameters. The performance analyses of the developed technique are performed under various scenarios by utilizing the PSCAD/EMTDC platform. The obtained results reveal that the rate of overshoots is decreased by 0.6 A while the convergence speed is accelerated by 1.4 s. In comparison with traditional MPPT techniques, tracking accuracy, steady-state stability, and robustness of the whole system are remarkably improved along with increasing overall system efficiency by 4%. It is also worth pointing out that the complexity level of the control technique is significantly reduced by the equation obtained through the symbolic regression analysis.
  • [ X ]
    Öğe
    A state-of-the-art review of artificial intelligence techniques for short-term electric load forecasting
    (Institute of Electrical and Electronics Engineers Inc., 2017) Zor, Kasim; Timur, O?uzhan; Teke, Ahmet
    According to privatization and deregulation of power system, accurate electric load forecasting has come into prominence recently. The new energy market and the smart grid paradigm ask for both better demand side management policies and for more reliable forecasts from single end-users, up to system scale. However, it is complex to predict the electric demand owing to the influencing factors such as climate factors, social activities, and seasonal factors. The methods developed for load forecasting are broadly analyzed in two categories, namely analytical techniques and artificial intelligence techniques. In the literature, commonly used analytical methods are linear regression method, Box-Jenkins method, and nonparametric regression method. The analytical methods work well under normal daily circumstances, but they can't give contenting results while dealing with meteorological, sociological or economical changes, hence they are not updated depending on time. Therefore, artificial intelligence techniques have gained importance in reducing estimation errors. Artificial neural network, support vector machine, and adaptive neuro-fuzzy inference system are among these artificial intelligence techniques. In this paper, a state-of-the-art review of three artificial intelligence techniques for short-term electric load forecasting is comprehensively presented. © 2017 IEEE.
  • [ X ]
    Öğe
    A State-of-the-Art Review of Artificial Intelligence Techniques for Short-Term Electric Load Forecasting
    (IEEE, 2017) Zor, Kasim; Timur, Oguzhan; Teke, Ahmet
    According to privatization and deregulation of power system, accurate electric load forecasting has come into prominence recently. The new energy market and the smart grid paradigm ask for both better demand side management policies and for more reliable forecasts from single end-users, up to system scale. However, it is complex to predict the electric demand owing to the influencing factors such as climate factors, social activities, and seasonal factors. The methods developed for load forecasting are broadly analyzed in two categories, namely analytical techniques and artificial intelligence techniques. In the literature, commonly used analytical methods are linear regression method, Box-Jenkins method, and nonparametric regression method. The analytical methods work well under normal daily circumstances, but they can't give contenting results while dealing with meteorological, sociological or economical changes, hence they are not updated depending on time. Therefore, artificial intelligence techniques have gained importance in reducing estimation errors. Artificial neural network, support vector machine, and adaptive neuro-fuzzy inference system are among these artificial intelligence techniques. In this paper, a state-of-the-art review of three artificial intelligence techniques for short-term electric load forecasting is comprehensively presented.
  • [ X ]
    Öğe
    An application of different approaches to missing data for electric load forecasting by using an advanced gene expression programming algorithm
    (Nova Science Publishers, Inc., 2021) Zor, Kasim; Çelik, Özgür
    More recently, electric load forecasting has become a crucial tool in planning and management of modern electric power systems owing to the fact that it provides insights acquired by employing data analytics along with artificial intelligence for the forthcoming internet of energy era. The ubiquity of missing data is frequently encountered in the load forecasting applications and several imputation approaches have been carried out in the literature. Meanwhile, the use of artificial intelligence-based techniques is required to deal with the nonlinear nature of electric loads which is originated from seasonal and other effects. Furthermore, gene expression programming is one of the proven artificial intelligence-based techniques which produces simple equations between explanatory variables and target variable. In this study, an application of different approaches to missing data for short-term electric load forecasting by using an advanced gene expression programming algorithm is comprehensively introduced through a case study. Consequently, impacts of each imputation approach and the advanced gene expression programming algorithm on forecasting process are discussed, and the results of the study are presented in details. © 2021 by Nova Science Publishers, Inc. All rights reserved.
  • [ X ]
    Öğe
    Application of Statistical and Artificial Intelligence Techniques for Medium-Term Electrical Energy Forecasting: A Case Study for a Regional Hospital
    (Int Centre Sustainable Dev Energy Water & Env Systems-Sdewes, 2020) Timur, Oguzhan; Zor, Kasim; Celik, Ozgur; Teke, Ahmet; Ibrikci, Turgay
    Electrical energy forecasting is crucial for efficient, reliable, and economic operations of hospitals due to serving 365 days a year, 24/7, and they require round-the-clock energy. An accurate prediction of energy consumption is particularly required for energy management, maintenance scheduling, and future renewable investment planning of large facilities. The main objective of this study is to forecast electrical energy demand by performing and comparing well-known techniques, which are frequently applied to short-term electrical energy forecasting problem in the literature, such as multiple linear regression as a statistical technique and artificial intelligence techniques including artificial neural networks containing multilayer perceptron neural networks and radial basis function networks, and support vector machines through a case study of a regional hospital in the medium-term horizon. In this study, a state-of-the-art literature review of medium-term electrical energy forecasting, data set information, fundamentals of statistical and artificial intelligence techniques, analyses for aforementioned methodologies, and the obtained results are described meticulously. Consequently, support vector machines model with a Gaussian kernel has the best validation performance, and the study revealed that seasonality has a dominant influence on forecasting performance. Hence heating, ventilation, and air-conditioning systems cover the major part of electrical energy consumption of the regional hospital. Besides historical electrical energy consumption, outdoor mean temperature and calendar variables play a significant role in achieving accurate results. Furthermore, the study also unveiled that the number of patients is steady over the years with only small deviations and have no significant influence on medium-term electrical energy forecasting.
  • [ X ]
    Öğe
    Day-ahead electricity price forecasting using artificial intelligence-based algorithms
    (Institute of Electrical and Electronics Engineers Inc., 2023) Yorat, Emre; Ozbek, Necdet Sinan; Zor, Kasim; Saribulut, Lutfu
    Deregulation and privatization of electricity markets has brought greater attention to electricity price forecasting (EPF) problem in day-ahead and intraday markets since a reliable forecast ensures market participants develop bidding strategies that aim to maximize their profit. Nonlinear and non-stationary characteristics of electricity prices ensemble a barrier in front of an accurate forecast and have required researchers to analyze the effects of exogenous variables such as economic metrics and neighboring countries' prices. In this paper, three different artificial intelligence-based algorithms namely multiple linear regression (MLR), autoregressive integrated moving average (ARIMA) with exogenous variables, and extreme gradient boosting decision trees (XGBoost) are applied to forecast day-ahead electricity prices of the Turkish electricity market by considering the aforementioned exogenous variables. Test results have shown that the XGBoost model has superior results in the error metrics than the other employed methods. Substantial error decrease in symmetric mean absolute percentage error, normalized root mean square error, normalized mean absolute error, and mean absolute scaled error metrics by 19.256%, 19.834%, 23.060%, and 23.016% is observed with respect to the closest performing MLR method on the test set. © 2023 IEEE.
  • [ X ]
    Öğe
    Medium- to long-term nickel price forecasting using LSTM and GRU networks
    (Elsevier Sci Ltd, 2022) Ozdemir, Ali Can; Bulus, Kurtulus; Zor, Kasim
    Recently, nickel is a critical metal for manufacturing stainless steel, rechargeable electric vehicle batteries, and alloys utilized in the state-of-the-art technologies. The use of more environmentally friendly electric vehicles has become widespread and brought tackling climate change to forefront, especially for reducing greenhouse gas emissions. Therefore, the demand for rechargeable batteries that power electric vehicles and the need for the nickel in the production of these batteries will increase as well. In addition to those, nickel prices significantly impact mine investment decisions, mine planning, economic development of nickel companies, and countries that depend on nickel resources. However, there is uncertainty about how the nickel price will trend in the future, and the solution to this problem attracts the attention of researchers. For forecasting nickel price, this paper proposes recurrent neural networks-based on long short-term memory (LSTM) and gated recurrent unit (GRU) networks, classified as deep learning algorithms. Mean absolute percentage error (MAPE) was used as the performance measure to compute the accuracy of the proposed techniques. As a result, it has been determined that the LSTM and GRU networks are very useful and successful in forecasting the nickel price variations owing to having average MAPE values of 7.060% and 6.986%, respectively. Furthermore, it has been observed that GRU networks surpassed the LSTM networks by 33% in terms of average computational time.
  • [ X ]
    Öğe
    Short-Term Building Electrical Energy Consumption Forecasting by Employing Gene Expression Programming and GMDH Networks
    (Mdpi, 2020) Zor, Kasim; Celik, Ozgur; Timur, Oguzhan; Teke, Ahmet
    Over the past decade, energy forecasting applications not only on the grid side of electric power systems but also on the customer side for load and demand prediction purposes have become ubiquitous after the advancements in the smart grid technologies. Within this context, short-term electrical energy consumption forecasting is a requisite for energy management and planning of all buildings from households and residences in the small-scale to huge building complexes in the large-scale. Today's popular machine learning algorithms in the literature are commonly used to forecast short-term building electrical energy consumption by generating an abstruse analytical expression between explanatory variables and response variables. In this study, gene expression programming (GEP) and group method of data handling (GMDH) networks are meticulously employed for creating genuine and easily understandable mathematical models among predictor variables and target variables and forecasting short-term electrical energy consumption, belonging to a large hospital complex situated in the Eastern Mediterranean. Consequently, acquired results yielded mean absolute percentage errors of 0.620% for GMDH networks and 0.641% for GEP models, which reveal that the forecasting process can be accomplished and formulated simultaneously via proposed algorithms without the need of applying feature selection methods.
  • [ X ]
    Öğe
    Very Short-Term Prosumer Electric Load Forecasting Using Deep Learning-Based Techniques
    (IEEE, 2024) Aydin, Bari; Zor, Kasim; Disken, Gokay
    In recent years, owing to the increasing penetration of renewable energy sources into the modern electric distribution networks within the age of smart grid, the concept of consumer in the electricity markets has been evolved into the concept of prosumer which can be referred to as an individual who consumes and produces electricity. In order to maintain the crucial balance between the generation and consumption of electricity, prosumer electric load forecasting (PELF) has become a requisite for energy management and planning in today's microgrids. Deep learning (DL)-based techniques are frequently employed for forecasting the electric load that is nonstationary and affected by several factors such as seasonal effects, climatological conditions, and random effects. The aim of this paper is to present a benchmark regarding PELF of a household residing in the state of California, USA via using DL-based techniques, namely convolutional neural networks (CNN) and gated recurrent unit networks (GRU) within the very short-term horizon. In addition, hourly meteorological data belonging to the residential area has been obtained from Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) database of NASA. Consequently, the results of the paper unveiled that utilizing CNN achieved better performance for PELF in terms of mean absolute error (MAE) and root mean squared error (RMSE) by 13% and 8%, respectively. Furthermore, it is considered that there is a gap in the literature for PELF and this paper will bridge this gap along with guiding the potential researchers in the field.