Method and system for HVAC inefficiency prediction using household electrical smart meter data

A system for monitoring a plurality of heating, ventilation, and air conditioning (HVAC) systems and predicting inefficient HVAC operation, said system comprising a non-transitory storage device and one or more processing devices operatively coupled to the storage device on which are stored modules of instruction code executable by the one or more processors, said systems comprising:

• data Accumulation Module for obtaining first training data for HVACs in a training set of households during a first period of spring weather and obtaining second training data for the HVACs in the training set of households during a period of summer weather, wherein the first and second training data are acquired using smart meters by acquiring regular readings of overall household power consumption, and wherein the first and second training data include indoor temperature and thermostat setting temperature, wherein this first and second training data is used only in a training phase as training data for the supervised machine learning algorithms;
• preprocessing module for analyzing the training data to identify repeating patterns of HVAC consumption;
• training module for determining a “Household Efficiency Score” by detecting HVAC efficiency by calculating the amount of energy required to change house temperature by defined number of degrees in relation to house size based on measured power consumption in relation to temperature, HVAC efficiency being calculated based on measured household power consumption in relation to outside temperature, and for applying the first training data and the classification labels to train a supervised machine learning algorithm, to generate an HVAC classification model predictive of inefficiency during periods of summer weather conditions based on said Household Efficiency Score and identified repeating patterns of HVAC consumption;
• prediction module for obtaining operational data pertaining to HVACs in an operational set of households during a second period of spring weather;
• and applying the HVAC classification model to predict inefficiency of the HVACs at individual households in the operational set during periods of summer weather using only overall household power consumption, wherein the period of spring weather has different weather conditions than the periods of summer weather.