Article Title

Karakaya HES’de verim ve üretim parametrelerinin yapay sinir ağı ile tahmini


Due to an increase in conventional energy prices and environmental effects, such as air pollution, global heating, depletion of the ozone layer, greenhouse effects; the use of renewable energy has increased, following the energy crisis in 1970. The continuous depletion of conventional energy resources and its adverse environmental impacts have revived the interest on renewable energy sources. Among the renewable energy sources, hydropower is considered to be economical, readily available and non-polluting source. Turkey, as one of the countries recently being affected by energy shortage, is in search for various solutions to close this gap. Out of several solution ideas, increasing the proportion of hydroelectric power, which is at %18,7 as of 2007 out of the whole energy production, has become one of the most applied. This, in turn, resulted in ever-increasing projects of building many large dams and run-of-river type hydroelectric power plants. It is known that the hydroelectric potential in our country exists in Fırat Basin. In this area Keban, Karakaya, Atatürk, Birecik and Karakamis, hydroelectric power plants provide significant contributions to country’s economy. As the amount of water in a dam is very important factor for producing energy, the usage of this water efficient is also very important. Production and efficiency forecasting plays an important role for the power system operational planners and also most of the participants in the nowadays electricity markets. With the importance of the production and efficiency in power system operation and electricity markets, many methods for arriving careful results, are represented. Artificial neural networks have been successfully used in solving complicated problems in different areas of application including pattern recognition, identification, classification, speech, vision and control systems. Artificial neural networks, originally developed to mimic basic biological neural systems – the human brain particularly, are composed of a number of interconnected simple processing elements called neurons or nodes. Each node receives an input signal which is the total “information” from other nodes or external stimuli, processes it locally through an activation or transfer function and produces a transformed output signal to other nodes or external outputs. Although each individual neuron implements its function rather slowly and imperfectly, collectively a network can perform a surprising number of tasks quite efficiently. In this study, it has been predicted the efficiency and production of Karakaya Hydroelectric Power Plant in Diyarbakir province using the ANN. In this analysis, in the basin lake province humidity, from the meteorological data such as amount of rainfall, amount of vaporization in free surface and average pressure and temperature and from hydroelectric power plant data such as the rate of water, hydraulic head, the amount of vaporized water and specific water consumption for the last five years some modeling have been conducted taking three-days averages of the data. Taking entries as meteorological data and hydroelectric power plant data, production and efficiency of hydroelectric power plant have been output conducting a study of Artificial Neural Networks model. The obtained equations from theoritical analysis have been solved using Matlab and Excel and have presented graphically. The efficiency and production of Karakaya hydroelectric power plant have been predicted with a high sensitivity with developed ANN model. Thus, it will be helpful for studies to be done in the future years to meet demands.