# US 10,770,898 B2 · Methods and systems for energy use normalization and forecasting

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,770,898 B2
- Document ID: US10770898B2
- Status: Granted
- Kind: B2
- Application number: 15/444,456
- Filed: 2017-02-28
- Published: 2018-08-30
- Granted: 2020-09-08
- Earliest claimed: 2017-02-28
- Assignees: Screaming Power Inc.
- Applicants: Screaming Power Inc.
- Inventors: Soosan Beheshti; Assadallah Sahebalam; Edward W. Nidoy; Francis Palma
- Web page: https://patentgrep.com/patent/US10770898B2

## CPC

- H02J 3/003: {Load forecast, e.g. methods or systems for forecasting future load demand}
- G05B 13/041: {in which a variable is automatically adjusted to optimise the performance}
- G05B 15/02: electric
- G06Q 10/06: Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q 50/06: Energy or water supply
- H02J 3/14: by switching loads on to, or off from, the networks, e.g. progressively balanced loading
- G05B 2219/2642: Domotique, domestic, home control, automation, smart house
- H02J 2103/30: Simulating, planning, modelling, reliability check or computer assisted design [CAD] of electric power networks
- H02J 2105/42: Home appliances
- Y02B 70/30: Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
- Y02B 70/3225: Demand response systems, e.g. load shedding, peak shaving
- Y02B 90/20: Smart grids as enabling technology in buildings sector (smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00)
- Y02P 90/82: Energy audits or management systems therefor
- Y04S 20/00: Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S 20/222: Demand response systems, e.g. load shedding, peak shaving
- Y04S 20/242: Home appliances
- H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y04S: SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS

## Abstract

Disclosed herein are methods and systems for normalizing an energy use intensity value to compensate for variations in energy usage due to environment. Also disclosed are methods and systems for forecasting energy use intensity values.

## Claims

### Claim 1

A computer-implemented method of generating a temperature-normalized energy use intensity (EUI-T) value for a structure, the method comprising:
receiving, by a processor: raw energy use data by the structure; weather information for a geographic location containing the structure, the weather information comprising a plurality of weather parameters related to weather data; and building occupancy information of the structure, the building occupancy information comprising one or more occupancy parameters related to occupancy data;
pre-processing, validating and remediating, by the processor, the raw energy use data;
generating, by the processor, an energy use intensity (EUI) value representing energy use by the structure over a time period;
generating, by the processor, a heating load of the structure, a cooling load of the structure and a baseload value of the structure, the baseload value comprising a passive baseload and an active baseload, the passive baseload determined from either a historic minimum energy use or from a combination of the heating load and the cooling load;
generating, by the processor, an energy use intensity baseload (EUIbl) value corresponding to the baseload value over the time period;
training, by the processor, a neural network on data related to the weather information and the building occupancy information to generate a non-linear Structure Dependent Energy Usage/Loss (SDE U/L) of the structure, with each of the weather parameters and each of the one or more occupancy parameters assigned to a node at an input layer of the neural network, the neural network comprising one or more hidden layers and the neural network using back propagation to generate the SDE U/L; and
generating, by the processor, the temperature-normalized energy use intensity value at a set point temperature of the structure, based on the EUIbl and the SDE U/L at the set-point temperature of the structure.

### Claim 2 (depends on 1)

The method of claim 1, wherein the weather information comprises one or more solar radiation values, one or more outside temperature values, one or more humidity values and one or more wind speed values.

### Claim 3 (depends on 1)

The method of claim 1, further comprising: using the temperature normalized energy use intensity value of the structure to determine, by the processor, at least one of: a volume of greenhouse gas emissions by the structure and a cost of energy use of the structure.

### Claim 4 (depends on 1)

The method of claim 1, wherein:
the weather information comprises: a recorded temperature (T), a wind speed (W), a humidity (H), and a solar radiation (R);
the building occupancy information comprises a building occupancy parameter (P); and
each of the T, H, W, R and P is assigned to a node at the input layer of the neural network.

### Claim 5 (depends on 1)

The method of claim 1, wherein:
the neural network is a multi-layer perceptron feed forward neural network with two hidden layers and five input nodes;
the data related to the weather information comprises: a recorded temperature (T), a wind speed (W), a humidity (H), and a solar radiation (R);
the data related to the building occupancy information comprises a building occupancy parameter (P); and
each of T, H, W, R and P is assigned to one of the five input nodes of a first layer of the neural network.

### Claim 6 (depends on 1)

The method of claim 1, wherein the one or more occupancy parameters is at least one of: a number of occupants of the structure, time spent by the occupants in the structure and a difference between the set point temperature and an occupant-selected set point temperature.

### Claim 7 (depends on 1)

The method of claim 1, wherein the neural network uses gradient descent back propagation, variable learning rate back propagation, conjugate gradient back propagation or quasi-Newton back propagation.

### Claim 8

A system for generating a temperature-normalized energy use intensity (EUI-T) value of a structure, the system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the system to:
receive, by the processor: raw energy use data by the structure; weather information for a geographic location containing the structure, the weather information comprising a plurality of weather parameters related to weather data; and building occupancy information of the structure, the building occupancy information comprising one or more occupancy parameters related to occupancy data;
pre-process, validate and remediate, by the processor, the raw energy use data;
generate, by the processor, an energy use intensity (EUI) value representing energy use by the structure over a time period;
generate, by the processor, a heating load of the structure, a cooling load of the structure and a baseload value of the structure, the baseload value comprising a passive baseload and an active baseload, the passive baseload determined from either a historic minimum energy use or from a combination of the heating load and the cooling load;
generate, by the processor, an energy use intensity baseload (EUIbl) value corresponding to the baseload value over the time period;
train, by the processor, a neural network on data related to the weather information and the building occupancy information to generate a non-linear Structure Dependent Energy Usage/Loss (SDE U/L) of the structure, with each of the weather parameters and each of the one or more occupancy parameters assigned to a node at an input layer of the neural network, the neural network comprising one or more hidden layers and the neural network using back propagation to generate the SDE U/L; and
generate, by the processor, the temperature-normalized energy use intensity value based on the EUIbl and the SDE U/L at a set-point temperature of the structure.

### Claim 9 (depends on 8)

The system of claim 8, wherein the weather information comprises one or more solar radiation values, one or more outside temperature values, one or more humidity values and one or more wind speed values.

### Claim 10 (depends on 8)

The system of claim 8, wherein the instructions further configure the system to:
use the temperature normalized energy use intensity value of the structure to determine, by the processor, at least one of: a volume of greenhouse gas emissions by the structure and a cost of energy use of the structure.

### Claim 11 (depends on 8)

The system of claim 8, wherein:
the weather information comprises: a recorded temperature (T), a wind speed (W), a humidity (H), and a solar radiation (R);
the building occupancy information comprises a building occupancy parameter (P); and
each of the T, H, W, R and P is assigned to a node at the input layer of the neural network.

### Claim 12 (depends on 8)

The system of claim 8, wherein:
the neural network is a multi-layer perceptron feed forward neural network with two hidden layers and five input nodes;
the data related to the weather information comprises: a recorded temperature (T), a wind speed (W), a humidity (H), and a solar radiation (R);
the data related to the building occupancy information comprises a building occupancy parameter (P); and
each of T, H, W, R and P is assigned to one of the five input nodes of a first layer of the neural network.

### Claim 13 (depends on 8)

The system of claim 8, wherein the one or more occupancy parameters is at least one of: a number of occupants of the structure, time spent by the occupants in the structure and a difference between the set point temperature and an occupant-selected set point temperature.

### Claim 14 (depends on 8)

The system of claim 8, wherein the neural network uses gradient descent back propagation, variable learning rate back propagation, conjugate gradient back propagation or quasi-Newton back propagation.