A load management system including a number of sensors structured to sense characteristics of a managed area, a controller including a processor structured to estimate occupancy of the managed area based on outputs of the number of sensors and to implement a load management scheme, a number of circuit breakers, at least one of the number of circuit breakers being electrically connected to a corresponding load circuit and including a metering circuit structured to meter energy provided to the load circuit and a device control unit structured to control one or more load devices electrically connected to the load circuit based on the load management scheme. The processor is structured to implement the load management scheme based on outputs of the sensors and metering information of one or more of the circuit breakers.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for integrating a monitoring system with one or more air quality sensors. The method includes receiving data indicating a level of volatile organic compounds within an area, determining an increase in the level of volatile organic compounds within the area, receiving video data that shows the area, detecting, from the video data, a new item of furniture within the area, sending a notification that indicates an increase in the level of volatile organic compounds is likely caused by the new item of furniture.

The disclosure provides an energy management system that is based on a distributed architecture that includes networked energy management devices located at a plurality of sites and a collection of energy management program applications and modules implemented by a centralized energy management service unit. The energy management program applications and modules are responsible for facilitating customer access to the system, configuring energy management devices, and collecting, storing, and analyzing energy management data collected from the plurality of sites. The energy management system is adaptable to a wide variety of energy usage requirements and enables customers to configure energy management devices at customer sites using scheduling templates, to define and customize site groupings for device configuration and data analysis purposes, and to request and view various statistical views of collected energy usage data.

A method for monitoring or controlling equipment of a building includes receiving a first timeseries comprising first data samples of a first variable monitored or controlled by a system and a second timeseries comprising second data samples of a second variable monitored or controlled by the system. The first data samples are at least partially asynchronous with the second data samples. The method includes synchronizing the first timeseries with the second timeseries by aggregating both the first timeseries and the second timeseries using equivalent aggregation intervals. Aggregating the first timeseries generates a third timeseries comprising aggregated values of the first variable and aggregating the second timeseries generates a fourth timeseries comprising aggregated values of the second variable. The method includes performing an automated operation to monitor or control the equipment of the building using the synchronized data samples of the third timeseries and the fourth timeseries.

Aspects of the disclosure relate to using machine learning techniques for dynamic occupancy prediction. A computing platform may receive first data that is non-personalized and is associated with a first specific physical space, and may receive second data associated with a second specific physical space. The computing platform may normalize, for a common subspace of the first specific physical space and the second specific physical space, the first data and the second data. Using the normalized data, the computing platform may generate a predicted occupancy value for the common subspace. The computing platform may send commands directing a local HVAC control system, deployed at the common subspace, to perform a resource control action for the common subspace, which may cause the local HVAC control system to perform the resource control action for the common subspace.

Methods, systems, and apparatus for controlling an air flow are described. A monitor obtains an environmental parameter and an air deflector controls the air flow exiting an air duct. An air deflector actuator configures the air deflector, the configuration of the air deflector being based on the environmental parameter.

Systems and methods are provided for predicting inefficient HVAC operation, by obtaining first training data for HVACs in a training set of households during a first period of moderate weather; obtaining second training data for HVACs in the training set of households during a subsequent period of harsher weather; generating classification labels of the household locations of the training set according to the second training data; 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 harsher weather conditions; obtaining operational data pertaining to HVACs in an operational set of households during a second period of moderate weather; and applying the HVAC classification model to predict inefficiency of HVACs at individual households in the operational set during a second subsequent period of harsher weather.

A facility implementing systems and/or methods for achieving energy consumption/production and cost goals is described. The facility identifies various components of an energy system and assesses the environment in which those components operate. Based on the identified components and assessments, the facility generates a model to simulate different series/schedules of adjustments to the system and how those adjustments will effect energy consumption or production. Using the model, and based on identified patterns, preferences, and forecasted weather conditions, the facility can identify an optimal series or schedule of adjustments to achieve the user's goals and provide the schedule to the system for implementation. The model may be constructed using a time-series of energy consumption and thermostat states to estimate parameters and algorithms of the system. Using the model, the facility can simulate the behavior of the system and, by changing simulated inputs and measuring simulated output, optimize use of the system.

A flexible workspace system with real-time sensor feedback comprises workstations, presence sensors, environmental sensors, an upstream device, and a mobile device. The workstations are located within a predetermined area. A presence sensor is positioned at each workstation, in which the presence sensor detects a potential occupancy proximate the corresponding workstation. An environmental sensor is positioned at each workstation, in which the environmental sensor detects a workspace environment proximate the corresponding workstation. The upstream device communicates with the presence sensors and the environmental sensors. The upstream device associates a target workstation with a mobile device located within the predetermined area based on the potential occupancy and the workspace environment. The mobile device communicates with the upstream device and includes an output component presenting the target workstation.

A system and method of managing operation of environmental heating/cooling devices adjacent or designed to direct heated/cooled air adjacent a frequently opening/closing opening in a facility is provided. The system monitors various states and activities of the facility that result in the window/door opening/closing and employs strategic use of the additional heating/cooling device to maintain a comfortable environment adjacent the opening while avoiding un-necessary operation of the heating/cooling device.