Energy supply in rural and off-grid communities has traditionally relied on diesel-based microgrids, due to limited access. But global environmental concerns are pushing for the transformation of these systems into renewable-based microgrids. This transition to more complex systems with a mix of dispatchable and nondispatchable resources requires new planning tools that ensure the security of supply. This paper presents a novel mixed-integer linear optimization model that determines optimal technology mix, size, placement, and associated dispatch for a multi-energy microgrid. The model satisfies microgrid's electrical and heat transfer network limitations by integrating linear power flow and heat transfer equations. It captures the efficiency gains from waste heat recovery through combined heat and power technologies, by modeling the interplay between electrical and heat sources. To ensure a secure design against generator outages, the optimization maintains sufficient reserve capacity in the system, which is dynamically allocated based on system operating conditions. Several case studies on an isolated microgrid model, developed based on a real microgrid in Alaska, illustrate how the proposed model works. The results show the effectiveness of the model and are used to discuss various aspects of the optimization solution.

Over the past century the electric power industry has evolved to support the delivery of power over long distances with highly interconnected transmission systems. Despite this evolution, some remote communities are not connected to these systems. These communities rely on small, disconnected distribution systems, i.e., microgrids to deliver power. However, as microgrids often are not held to the same reliability standards as transmission grids, remote communities can be at risk for extended blackouts. To address this issue, we develop an optimization model and an algorithm for capacity planning and operations of microgrids that include N -1 security and other practical modeling features like ac power flow physics, component efficiencies, and thermal limits. We demonstrate the computational effectiveness of our approach on two test systems; a modified version of the IEEE 13 node test feeder and a model of a distribution system in a remote community in Alaska.

Cancelled surgeries cause insufficient use of operating rooms, surgeons, nurses, equipment and other hospital resources. Operating rooms are one of the most expensive resources in any healthcare system. The average amount of cost for any operating room for a less complex procedure is around $29/min, while the more complex procedures cost up to $80/min. Many studies have been conducted to analyze and understand the reasons behind surgery cancellation; however, a handful of studies aimed to predict which patients have a large risk of cancellation. We used four different traditional data mining techniques—Conditional Inference Tree, C5.0, logistic regression, and Radial Basis Function Kernel Support Vector Machine—to predict surgical cancellations to create efficient surgical patients’ schedules. Then, a stacking generalization ensemble machine was developed and compared to the traditional methods. Three different scheduling scenarios were developed and tested using discrete event simulation (DES). The stacking generalization ensemble machine outperformed all traditional data mining techniques and the benchmark algorithm with an accuracy of 95% and area under the curve (AUC) of 96%. The proposed simulation-based optimization scheduling technique increased the operating room use by 13%. Surgeries cancellation prediction leads to efficient scheduling that ultimately leads to reductions in expenditure.