Search

In this study, it is aimed to determine the most suitable method for electricity price forecasting in the Turkish day ahead electricity market and to test the selected method using real data. In order to forecast the electricity price, forecasting models were created in Python programming language with four different forecasting methods: linear regression, polynomial regression, artificial neural networks, XGBoost analysis method It is aimed that models can make predictions with low deviations, react quickly to short-term changes in price, and have short running times. Models were trained and tested with real data obtained from the Energy Markets Operations (EPİAŞ) Transparency Platform. The data used for analysis is hourly Market Clearing Price (MCP) data and hourly energy production data for each electricity generation source. The data used is hourly data covering the years 2015-2020 and is a large dataset consisting of approximately 40,000 rows. The test data used in the methods were randomly selected from five years of data to ensure a homogeneous distribution. Considering the dynamic structure of the Turkish electricity energy market, actual values and estimated values are compared both graphically and with the mean square error rates (RMSE) metric for four forecasting methods. In addition, the four forecasting methods were compared in terms of running times. When both estimation error rates and running times are evaluated together, XGBoost model was found to be the most appropriate estimation model. Making consistent price estimations will enable both electricity producers and large-capacity consumers to provide accurate supply offers and demand bids and to determine electricity prices precisely within the electricity market structure. [ABSTRACT FROM AUTHOR]

In recent years, hybrid models, using more than one models together, are presented in the field of time series analysis. One of the most important hybrid model classes is ARIMA-Artificial Neural Networks (ANN) hybrids. ARIMA is a linear model according to its structure, whereas ANN models are quite successful on modeling nonlinear time series. Time series encountered in real life usually carry linear and nonlinear characteristics together, which causes high forecasting performance of ARIMA-ANN hybrid models. In this study, a novel optimization based ARIMA-ANN hybrid model is presented. Proposed Optimized ARIMAANN (OptAA) hybrid model assumes time series is the sum of linear and nonlinear two series. In the first stage of the two staged model, ARIMA and ANN models with real time series pass through a least squares optimization process to obtain linear and nonlinear components. In the second stage, error values of the linear component are transferred to nonlinear component, nonlinear component is revised and remodeled with ANN. To determine the forecasting performance, Wolf's sunspot, Canadian lynx and GBP/USD exchange rate data sets, which are applied often in the literature, are used. Results obtained from the application show that OptAA hybrid model has higher performance than other models especially in relatively short term forecasting and is a very powerful methodology in time series analysis field. [ABSTRACT FROM AUTHOR]

This study presents a design and development of hybrid forecasting model by using ARIMA and artificial neural networks for short-term energy forecasting processes in energy management systems. Proposed model is applied into a company operating in the tobacco products manufacturing industry and reliability of the model is tested by using real-life data set in illustrative cases. In line with the results obtained from ARIMA method, some of the factors affecting electricity consumption are taken into consideration as input data for artificial neural network model. After considering the correlation between solar energy generation, working hours, production quantities and past electricity consumption data, various number of neurons and different training algorithms are tested to design the optimal system for the company. The proposed hybrid model provides around 39.9% improvement compared to forecast data obtained by using only ARIMA model. [ABSTRACT FROM AUTHOR]

Turkey's economic development in terms of urbanization, consumption of electricity is a significant pressure on the natural environment. In order to reduce the effects of this pressure in parallel with economic growth, it is necessary to reduce the dependence on foreign sources in energy while reducing the amount of carbon emissions that cause environmental pollution. Therefore, Turkey's economic growth of urbanization in order to continue in a healthy way, the relationship between the amount of energy consumption and carbon emissions need to be better understood. The target to reduce the economic and environmental impacts of economic growth and urbanization with increasing energy needs to the minimum should be to use renewable energy sources efficiently. The aim of this study urbanization in Turkey, the relationship between electricity consumption and carbon emissions is to examine the amount of time series analysis. The increase in the amount of carbon emission, the increase in population and the increase in electricity demand in comparison with years and sectoral basis were compared. discussing the results obtained from the graph are interpreted in how it has changed that and more weight which results results obtained from the graphic industry where the bet is causing the increase of electricity demand with urbanization between 1990-2017 years in Turkey. Graphic shows the results obtained from the last 27 years the amount of carbon emissions in Turkey, the population and electricity demand is increasing in parallel with each other. Especially the rise in demand for electricity and carbon emissions, but not appear as a result of this parallel Turkey's recent emphasis on renewable energy sources. [ABSTRACT FROM AUTHOR]