Decision support system for the management of energy use, contracting and capital investments for facilities

Abstract

Disclosed herein is an energy management decision support system and methods for asset managers of buildings and facilities that can utilize energy usage data captured from meters, such as smart meters, and weather data to provide a systems-based cost reduction and optimization solution for end users. Building system components may be highly inter-dependent and changes to one system element can have substantial effects (positive and negative) upon other system elements. As described in further detail herein, system and method embodiments according to the present disclosure may apply predefined criteria to such building energy usage data to identify energy usage variances, and may graphically present to a user the identified energy usage variances. As a result, facility administrators are provided with more easily interpretable energy usage information. Such information may be applied by the administrators for adjusting operations, upgrading building equipment, or retrofitting building equipment to improve building energy usage and reduce costs.

1 - 22 . (canceled) 
     
     
         23 . A system for projecting future energy and demand use associated with a building to allow for improved management of operations, maintenance and commodity hedging strategies:
 at least a processor and memory configured to:   generate derived polynomial equations using time-based historical energy and weather data grouped by clustering techniques for meeting a fit and minimal variance criteria, wherein the time-based historical energy and weather data is received at least two times per day for a set of days, weeks, months or years;   receive multi-day forecasted weather data from one or more sources;   apply received forecasted weather data to the generated polynomial equations;   generate future predictions for energy and demand over the period of the received forecasted weather data with defined levels of statistical confidence;   update future energy and demand predictions based on changing multi-day forecasted weather data;   utilize energy and demand predictions to plan maintenance and operational schedules that account for weather and day of week effects on the building so as to reduce costs associated with the utility tariffs; and   manage near term energy purchase requirements for buildings through the forward purchase of energy based on forecasted energy and demand requirements.