Systems and methods for data analytics for virtual energy audits and value capture assessment of buildings

Abstract

A system may provide virtual energy audits of one or more target buildings. The system may retrieve weather data and energy usage data specific to a given target building from a weather server and a utility server, respectively. The system may store predefined building characteristics corresponding to the given target building in local memory. Based on the weather data, energy usage data, and/or predefined building characteristics, the system may generate one or more building markers that characterize the energy usage and efficiency of the given target building. Building efficiency diagnostics and energy conservation prognostics may be generated based on the building markers and may be sent by the system to be displayed via a user interface of a client device. The energy conservation prognostics may include one or more energy conservation measure recommendations and corresponding predicted cost/energy savings.

1 - 27 . (canceled) 
     
     
         28 . A system for providing virtual energy audits comprising:
 a processor; and   at least one memory coupled with the processor, the at least one memory having software stored thereon which, when executed by the processor, causes the processor to:
 retrieve input data corresponding to a target building, the input data comprising time-series energy usage data and building characteristic data, the time-series energy usage data comprising total power usage of the target building; 
 generate a plurality of building markers for the target building based on the input data, 
 automatically generate building efficiency diagnostics based on the plurality of building markers, wherein the building efficiency diagnostics include estimated on/off cycles of an HVAC system of the target building, the estimated on/off cycles of the HVAC system determined based on the time-series energy usage data; and 
 automatically send the building efficiency diagnostics to be displayed on a user interface. 
   
     
     
         29 . The system of  claim 28 , wherein to retrieve input data, the software causes the processor to:
 periodically retrieve new energy usage data corresponding to the target building from at least one of: a utility providing energy or a power sensor disposed at the target building;   add the new energy usage data to the time-series energy usage data in the at least one memory;   retrieve the time-series energy usage data corresponding to the target building; and   retrieve the building characteristic data corresponding to the target building.   
     
     
         30 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate an effective building R-value marker by:
 disaggregating the time-series energy usage data into a heating/cooling dataset and a load dataset;   determining an interior heating load for a selected time period based on the load dataset, wherein the selected time period corresponds to a time period during which an interior temperature of the target building is substantially unchanging;   determining an amount of energy being removed from an air-conditioned space of the target building based on the heating/cooling dataset for the selected time period;   determining an exterior temperature of the target building for the selected time period based on weather data;   estimating the interior temperature of the target building for the selected time period within a predetermined range; and   generating the effective R-value building marker corresponding to a thermal insulation quality of the target building based on the amount of energy being removed, the interior heating load, the exterior temperature, and the interior temperature.   
     
     
         31 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a heating/cooling system turn on time building marker, a heating/cooling system turn off time building marker, and a heating/cooling system turn on wattage building marker by:
 calculating a derivative of the time-series energy usage data to produce a derivative dataset defining changes in energy usage between timestamps of the time-series energy usage data;   identifying heating/cooling system turn on times from the derivative dataset;   identifying heating/cooling system turn off times from the derivative dataset;   identifying a first mode of the identified heating/cooling system turn on times;   identifying a second mode of the identified heating/cooling system turn off times;   generating the heating/cooling system turn on wattage building marker based on observed energy usage changes occurring at the heating/cooling system turn on times;   generating the heating/cooling system turn on time building marker equal to the first mode; and   generating the heating/cooling system turn off times equal to the second mode.   
     
     
         32 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a diurnal pattern building marker by:
 applying a chi-squared periodogram test to the time-series energy usage data to generate the diurnal pattern building marker.   
     
     
         33 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a rescheduling savings opportunity building marker by:
 applying an analytical method to the time-series energy usage data to identify when the target building is unoccupied, wherein the analytical method is selected from at least one of: wavelet transform, two sample t-test, or paired t-test;   determining that the HVAC system is active when the target building is unoccupied based on the time-series energy usage data;   generating a recommendation to adjust a temperature setpoint of the HVAC system of the target building; and   generating an estimated cost savings associated with adjusting the temperature setpoint according to the recommendation.   
     
     
         34 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate an energy usage change building marker by:
 separating the time-series energy usage data into a plurality of single-year subsets;   for each year represented in the plurality of single-year subsets, identifying significant change-points of the time-series energy usage data that occurred during a respective year;   determining that a correlation between first and second significant change points is lower than a predetermined threshold; and   flagging the first and second significant change points as corresponding to a retrofit time for the target building.   
     
     
         35 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a heating type building marker and a cooling type building marker by:
 removing datapoints from the time-series energy usage data and weather data corresponding to holidays and weekends to produce modified energy usage data and modified weather data;   applying a piecewise linear regression model to the modified energy usage data and time-series exterior temperature data of the modified weather data to produce a heating season trendline and a cooling season trendline;   determining a first slope of the heating season trendline;   determining a second slope of the cooling season trendline;   comparing the first slope to a first predetermined threshold to determine a heating type of the target building;   comparing the second slope to a second predetermined threshold to determine a cooling type of the target building;   setting the heating type building marker equal to the determined heating type; and   setting the cooling type building marker equal to the determined cooling type.   
     
     
         36 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a heating/cooling system size building marker by:
 generating a heating/cooling system turn on time building marker;   defining a subset of the time-series energy usage data as a set of datapoints corresponding to the heating/cooling system turn on time building marker;   determining energy demand values for each of the set of datapoints;   determining a mode of the energy demand values; and   setting the heating/cooling system size building marker equal to the mode.   
     
     
         37 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a heating/cooling system oversized condition building marker by:
 identifying a first subset of the time-series energy usage data corresponding to a heating season;   identifying a second subset of the time-series energy usage data corresponding to a cooling season;   applying a low-pass filter to the first subset to generate a first signal;   applying the low-pass filter to the second subset to generate a second signal;   generating a first signal-to-noise ratio of the first signal to the first subset;   generating a second signal-to-noise ratio of the second signal to the second subset;   determining that the first signal-to-noise ratio is less than a first average signal-to-noise ratio corresponding to similar buildings in the heating season;   determining that the second signal-to-noise ratio is less than a second average signal-to-noise ratio corresponding to the similar buildings in the cooling season; and   setting the heating/cooling system oversized condition building marker to indicate that the HVAC system is oversized.   
     
     
         38 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate one or more building operation patterns building markers by:
 removing data points corresponding to holidays from the time-series energy usage data to produce filtered energy usage data;   dividing the filtered energy usage data into seven subsets, each corresponding to a different day of week;   determining a minimum length from among the seven subsets;   setting lengths of each of the seven subsets equal to the minimum length;   performing hierarchical cluster analysis on the seven subsets to produce a cluster dendrogram;   determining that a ratio of a maximum height of the cluster dendrogram to a minimum height of the cluster dendrogram is less than or equal to a predetermined threshold; and   setting the building operation patterns building marker to indicate a pattern corresponding to the predetermined threshold.   
     
     
         39 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a baseload building marker by:
 applying a low-pass filter to the time-series energy usage data to produce filtered energy usage data;   identifying daily minimum energy usage values from the filtered energy usage data;   sorting the daily minimum energy usage values by magnitude to produce sorted daily minimum energy usage values;   removing any anomalous and/or negative valued data points from the sorted daily minimum energy usage values to produce cleaned, sorted daily minimum energy usage values;   calculating an average of a predetermined number of lowest values of the cleaned, sorted daily minimum energy usage values; and   setting the baseload building marker equal to the average.   
     
     
         40 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate a building energy usage intensity building marker by:
 setting the building energy usage intensity building marker equal to an amount of energy used per square foot per year value based on the time-series energy usage data and the building characteristic data; and   comparing the building energy usage intensity building marker to an average energy usage intensity building marker corresponding to a set of buildings, wherein a first climate zone of the set of buildings is equal to a second climate zone of the target building, and wherein a first building type of the set of buildings is equal to a second building type of the target building.   
     
     
         41 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate an abnormal energy usage days building marker by:
 dividing the time-series energy usage data into subsets;   applying hierarchical clustering to the subsets to produce cluster data;   identifying abnormal days corresponding to outlier energy usage based on the cluster data; and   flagging the identified abnormal days.   
     
     
         42 . The system of  claim 28 , wherein to generate the plurality of building markers, the software causes the processor to generate an energy usage variability building marker by:
 generating a summer boxplot from first datapoints of the time-series energy usage data corresponding to a summer time period;   generating a winter boxplot from second datapoints of the time-series energy usage data corresponding to a winter time period;   generating a set of contiguous box plots for each hour represented in the summer boxplot and the winter boxplot; and   calculating a smooth mean of energy usage values for each hour in both summer and winter.   
     
     
         43 . The system of  claim 28 , wherein the software further causes the processor to:
 generate prognostics data based on the input data, the prognostics data comprising energy conservation measure recommendations and estimated impacts of implementing the energy conservation measure recommendations;   generate energy conservation prognostics based on the prognostics data and the plurality of building markers; and   send the energy conservation prognostics to be displayed on the user interface.   
     
     
         44 . The system of  claim 43 , wherein the prognostics data is generated by processing weather data and the time-series energy usage data using at least one predictive model, and
 wherein the at least one predictive model is selected from at least one of: a neural network model, a random forest model, a support-vector machine model, GBRT model, or a diffusion index model.   
     
     
         45 . The system of  claim 44 , wherein the software further causes the processor to:
 generate the energy conservation prognostics by:
 generating a recommendation for an energy conservation measure corresponding to an action that could be taken to improve energy efficiency of the building, identified based on at least one of the building markers; and 
 generating a prediction of an effect the energy conservation measure would have on the energy efficiency of the target building; and 
   send the recommendation and the prediction to be displayed at the user interface.   
     
     
         46 . A method for managing energy usage efficiency comprising:
 receiving a request to monitor energy usage for at least one target building;   obtaining building-specific characteristic data for the at least one target building, the building-specific characteristic data including at least location data;   retrieving time-series energy usage data for the at least one target building, wherein the time-series energy usage data reflects total electricity usage for the at least one target building;   identifying, from fluctuations in the total electricity usage, on/off cycles for at least one apparatus associated with the at least one target building;   periodically updating building efficiency diagnostics for the at least one target building using the time-series energy usage data; and   automatically sending instructions for changing settings associated with the at least one apparatus to change the on/off cycles of the at least one apparatus.   
     
     
         47 . The method of  claim 46 , wherein the at least one apparatus is an HVAC system for the at least one target building, and
 the method further comprising:
 determining an HVAC turn on time building marker and an HVAC turn off time building marker from the time-series energy usage data. 
   
     
     
         48 . The method of  claim 46 , wherein the building-specific characteristic data is automatically obtained from a database of real estate records. 
     
     
         49 . The method of  claim 46 , wherein the time-series data is retrieved from at least one sensor associated with the at least one target building, the sensor installed to capture time-series total energy usage data for the at least one target building. 
     
     
         50 . The method of  claim 46 , wherein the at least one target building comprises a group of target locations. 
     
     
         51 . The method of  claim 50 , wherein the group of target locations is an apartment. 
     
     
         52 . The method of  claim 50 , wherein the group of target locations is a complex of buildings. 
     
     
         53 . The method of  claim 46 , further comprising:
 updating thermostat settings based on the on/off cycles for the at least one apparatus.   
     
     
         54 . The method of  claim 46 , further comprising:
 displaying, via a client device, the building efficiency diagnostics on a user interface.   
     
     
         55 . The method of  claim 54 , further comprising:
 providing, via the user interface, a user an option to update and display the building efficiency diagnostics on demand.   
     
     
         56 . The method of  claim 54 , further comprising:
 receiving, via the user interface, unoccupied times for the at least one target building, to improve efficiency diagnostics.   
     
     
         57 . The method of  claim 46 , further comprising:
 determining an effective R-value for the at least one target building based on an interior heating load of the at least one target building, an amount of energy being removed from an air-conditioned space of the at least one target building, an interior temperature of the at least one target building, and an exterior temperature of the at least one target building.   
     
     
         58 . The method of  claim 46 , wherein the building efficiency diagnostics comprise: at least one of: a base load, a heating/cooling system load, a total heating time, a total cooling time, or a total water heater operation time. 
     
     
         59 . A system for managing energy usage efficiency comprising:
 a processor; and   at least one memory coupled with the processor, the at least one memory having software stored thereon which, when executed by the processor, causes the processor to:
 receive a request to monitor energy usage for at least one target building; 
 obtain building-specific characteristic data for the at least one target building, the building-specific characteristic data including at least location data; 
 retrieve time-series energy usage data for the at least one target building, wherein the time-series energy usage data reflects total electricity usage for the at least one target building; 
 identify, from fluctuations in the total electricity usage, on/off cycles for at least one apparatus associated with the at least one target building; 
 periodically update building efficiency diagnostics for the at least one target building using the time-series energy usage data; and 
 automatically send instructions for changing settings associated with the at least one apparatus to change the on/off cycles of the at least one apparatus. 
   
     
     
         60 . The system of  claim 59 , wherein the at least one apparatus is an HVAC system for the at least one target building, and
 wherein the software further causes the processor to:
 determine an HVAC turn on time building marker and an HVAC turn off time building marker from the time-series energy usage data. 
   
     
     
         61 . The system of  claim 59 , wherein the building-specific characteristic data is automatically obtained from a database of real estate records. 
     
     
         62 . The system of  claim 59 , wherein the time-series data is retrieved from at least one sensor associated with the at least one target building, the sensor installed to capture time-series total energy usage data for the at least one target building. 
     
     
         63 . The system of  claim 59 , wherein the at least one target building comprises a group of target locations. 
     
     
         64 . The system of  claim 63 , wherein the group of target locations is an apartment. 
     
     
         65 . The system of  claim 63 , wherein the group of target locations is a complex of buildings. 
     
     
         66 . The system of  claim 59 , wherein the software further causes the processor to:
 update thermostat settings based on the on/off cycles for the at least one apparatus.   
     
     
         67 . The system of  claim 59 , wherein the software further causes the processor to:
 display, via a client device, the building efficiency diagnostics on a user interface.   
     
     
         68 . The system of  claim 67 , wherein the software further causes the processor to:
 provide, via the user interface, a user an option to update and display the building efficiency diagnostics on demand.   
     
     
         69 . The system of  claim 67 , wherein the software further causes the processor to:
 receive, via the user interface, unoccupied times for the at least one target building, to improve efficiency diagnostics.   
     
     
         70 . The system of  claim 59 , wherein the software further causes the processor to:
 determine an effective R-value for the at least one target building based on an interior heating load of the at least one target building, an amount of energy being removed from an air-conditioned space of the at least one target building, an interior temperature of the at least one target building, and an exterior temperature of the at least one target building.   
     
     
         71 . The system of  claim 59 , wherein the building efficiency diagnostics comprise: at least one of: a base load, a heating/cooling system load, a total heating time, a total cooling time, or a total water heater operation time.