Publications

The demand for the energy has been significantly increased over years led by the growth of global population. By the signing of the Paris Agreement in 2015, countries pledged to reduce the greenhouse gas effect including gas emissions to prevent and mitigate the global warming. The emissions control from power generation has then become a serious concern for countries to achieve their target in reducing gas emissions. Besides, the emitted gas such as Nitrogen oxides (NOx) or Carbon Monoxide (CO) that are resulted from the combustion process of fossil fuels in power plants is harmful pollutants to the living organism. The presence of those gas emissions can be predicted using Predictive Emissions Monitoring System (PEMS) or Continues Emissions Monitoring System (CEMS) methods. Continuous Emissions Monitoring System is a system that was designed to monitor the effluent gas streams resulted from the combustion processes. However, this empirical method still has several constraints in predicting the gas emissions where in some cases, it produces significant errors that caused by some uncontrollable aspects such as ambient temperature, pressure and humidity that can lead to miscalculation of operational risks and costs. Solving this problem, we conduct a PEMS with data-driven approach. In this study, we used the 2011-2015 open data from gas-turbine-based power plants in Turkey to train and test several supervised methods as a practical application to predict gas concentration. Predictive Emissions Monitoring System (PEMS) offers more advantages than Continuous Emissions Monitoring System (CEMS) especially in economic aspects. The system will monitor and predict the actual emissions from gas-turbine-based power plants operation. The results of this study indicate that the data-driven approach produces a good RMSE value. By having the gas emissions predicted, a mitigation plan can be set and the operational costs in the following years can be optimized by the company