(61s) Applications of Data-Driven Approaches in Chemical Process and Energy System Optimization

These days, the availability, and the ease access to enormous volumes of data derives different industrial and technological fields to utilize data-driven solutions. As optimization has always been constructed based on exchanging information between models and data, multi-level optimization tasks such as long-term planning, scheduling and control will tremendously benefit from information mined from massive data. Big data-driven tools (i.e., machine learning) has proven superiority over traditional data tools in dealing with substantial amounts of data and data different structure. Hence, in this work, big data tools are applied to address the challenges associated with planning models of energy systems and process optimization of operating chemical engineering processes.

A Data-driven stochastic optimization framework that leverages big data in design and operation of power generation planning is proposed. The proposed approach is applied to different power planning models that include unit commitment (UC) characteristics where the size of uncertainty scenarios is reduced. Results show that the proposed approach is an effective tool to generate reduced size stochastic scenarios.

The design and operation of energy hub problem involves the integration of decision levels with different time scales that usually lead to multiscale models which are computationally costly. A mathematical programming-based general clustering approach is applied to reduce the size of multiple attributes input data and tackle the computational complexity of multiscale energy hub problems. Different case studies are considered under different environmental and technical consideration. Assessments conclude that the clustering approach is an efficient tool to decrease the size of the original model while maintaining good results.

Modern improvements in supervised machine learning tools have demonstrated their ability to achieve accurate and efficient prediction results. Therefore, these tools are employed as alternative approaches to model a specific application in the gas industry. Results obtained from this study showcase the ability of the developed models to offer reliable and accurate predictions. A data-driven surrogate-based optimization framework is developed, where the developed machine learning models can be used as a suitable replacement for detailed first principal models, to find the optimal conditions at maximum cost-saving. The proposed approach can help the gas industry to simultaneously achieve process efficiency, profitability, and safety.