Abstract: An apparatus, system, and method are disclosed for calibrating algorithms for determining electrical load and lifestyle characteristics. A model creation module creates an electrical usage model that includes an electrical device usage model for each electrical load assumed to be at simulated premises (an assumed load set). The simulated premises include characteristics from actual premises within an area serviced by an electric utility. A simulation module simulates a number of simulated electrical usages for a number of assumed load sets at the simulated premises. A load prediction module determines if a particular type of load is present within each simulated premises using a load prediction algorithm that includes algorithm parameters. An accuracy module determines an accuracy of the load prediction algorithm and an adjustment module adjusts the algorithm parameters of the load prediction algorithm in response to the determined accuracy.

Abstract: An apparatus, system, and method are disclosed for determining electrical load and lifestyle characteristics. A record receiving module receives an electrical energy usage record for premises for a predefined time period (“record period”), and receives property characteristics for the premises. The property characteristics include physical characteristics for the premises, environmental characteristics for the premises for the record period, and/or lifestyle characteristics of users of the premises. A load identification module selects a load prediction algorithm to determine if a particular type of electrical load is present at the premises. A comparison module applies the load prediction algorithm to the electrical energy usage record for the premises for at least a portion of the record period (“comparison period”) to determine if the particular type of electrical load is present at the premises. The load prediction algorithm uses the property characteristics of the premises during the comparison period.

Abstract: An apparatus, system, and method are disclosed for determining a partial class membership of a data record in a class. The apparatus includes a record set acquisition module that receives a set of reference records having the same independent variables and belonging to a known class within a group of classes. An unknown-class record receiving module receives an unknown-class record having same independent variables as reference records. A class identification module creates a class vector for each reference record identifying whether the record is in a class. A weighting module calculates a set of unknown-class record weights for the unknown-class record. A classification module determines a partial class membership for the unknown-class record for each class in the group of classes using the set of unknown-class record weights. Each partial class membership identifies a probability that the unknown-class record belongs to a corresponding class in the group of classes.