Still with FIG. 29, the power analytics server 116 can be configured to host one or more analytic engines that allow the Energy Management System to perform its various functions. For example, as depicted herein FIG. 29, the power analytics server 116 can host a machine learning engine 2908, a virtual system modeling engine 2922 and/or a utility power pricing engine 2914. The machine learning engine 2908 can be configured to work in conjunction with the virtual system modeling engine 2922 and a virtual system model of the electrical system to make real-time predictions (i.e., forecasts) about the various operational aspects of the electrical system. The machine learning engine 2908 work by processing and storing patterns observed during the normal operation of the electrical system over time. These observations are provided in the form of real-time data captured using a multitude of sensors that are imbedded within the electrical system.
The utility pricing engine 2914 can be configured to access a utility power pricing data source 2916 (that includes energy cost tables and other power billing data) to generate real-time energy cost and usage data 2910 that is reflective of the operational efficiency and performance of the electrical system. Examples of real-time energy cost and usage data 2910 can include, but are not limited to: 1. the real-time cost of energy utilized by the electrical system (energy cost), 2. the real-time cost of intrinsic power losses within the electrical system (cost of losses), and/or 3. the real-time cost of power losses due to the electrical system running at poor power factors (cost due to poor power factor).
