Systems and methods for real-time DC microgrid power analytics for mission-critical power systems
摘要
說明書
Both the actual real-time sensory data 2307 feed and the predicted sensory data 2304 feed are communicated directly to an archive database trending historian element 2309 so that the data can be accessed by a pattern recognition machine learning engine 2311 to make various predictions regarding the health, stability and performance of the electrical power system. For example, in one embodiment, the machine learning engine 2311 can be used to make predictions about the operational reliability of an electrical power system (aspects) in response to contingency events such as a loss of power to the system, loss of distribution lines, damage to system infrastructure, changes in weather conditions, etc. Often, the machine learning engine 2311 includes a neocortical model that is encapsulated by a real-time sensory system layer, which is itself encapsulated by an associative memory model layer.
