Managing big data in coal-fired power plants: a business intelligence framework

Many power producers are looking for ways to develop smarter energy capabilities to tackle challenges in the sophisticated, non-linear dynamic processes due to the complicated operating conditions. One prominent strategy is to deploy advanced intelligence systems and analytics to monitor key performance indicators, capture insights about the behavior of the electricity generation processes, and identify factors affecting combustion efficiency. Thus, the purpose of this paper is to outline a way to incorporate a business intelligence framework into existing coal-fired power plant data to transform the data into insights and deliver analytical solutions to power producers.

The proposed ten-step business intelligence framework combines the architectures of database management, business analytics, business performance management, and data visualization to manage existing enterprise data in a coal-fired power plant.

The results of this study provide plant-wide signals of any unusual operational and coal-quality factors that impact the level of NO_x and consequently explain and predict the leading causes of variation in the emission of NO_x in the combustion process.

Once the framework is integrated into the power generation process, it is important to ensure that the top management and the data analysts at the plants have the same perceptions of the benefits of big data and analytics in the long run and continue to provide support and awareness of the use of business intelligence technology and infrastructure in operational decision making.

The key finding of this study helps the power plant prioritize the important factors associated with the emission of NO_x; closer attention to those factors can be promptly initiated in order to improve the performance of the plant.

The use of big data is not just about implementing new technologies to store and manage bigger databases but rather about extracting value and creating insights from large volumes of data. The challenge is to strategically and operationally reconsider the entire process not only to prepare, integrate, and manage big data but also to make proper decisions as to which data to select for the analysis and how to apply analytical techniques to create value from the data that is in line with the strategic direction of the enterprise. This study seeks to fill this gap by outlining how to implement the proposed business intelligence framework to provide plant-wide signals of any unusual operational and coal-quality factors that impact the level of NO_x and to explain and predict the leading causes of variation in the emission of NO_x in the combustion process.