An asset manager is configured to control distribution of power within an aggregated distributed energy resources system. The asset manager is configured to solve a given asset model that models a real asset. The asset controller is configured to optimize a setpoint of the asset by determining a first trajectory over the course of a first prediction horizon and a second trajectory over the course of a second prediction horizon that is temporally shorter than the first prediction horizon. The trajectories are determined by minimizing a cost function associated with the DER model or a DERs system model. The first prediction horizon has a first temporal length and a first plurality of set points. The second prediction horizon has a second temporal length and a second plurality of set points. The asset controller is configured to constrain the second trajectory based on the first plurality of set points.

An occupancy tracking device configured to establish a network connection with an access point and to capture wireless signal distortion information for the network connection. The device is further configured to generate statistical metadata for the wireless signal distortion information. The device is further configured to input the wireless signal distortion information and the statistical metadata for the wireless signal distortion information into a machine learning model. The machine learning model is configured to determine a predicted occupancy level based on the wireless signal distortion information and the statistical metadata for the wireless signal distortion information. The predicted occupancy level indicates a number of people that are present within with the space. The device is further configured to obtain the predicted occupancy level from the machine learning model and to control a Heating, Ventilation, and Air Conditioning (HVAC) system based on the predicted occupancy level.

Methods for assessing energy efficiency of a building are provided including receiving data related to the plurality of buildings from at one or more of the plurality of MRACs. The data related to the plurality of buildings is associated with properties of the building. The data related to the plurality of buildings is organized by defining categories of relevant data related to the plurality of buildings. The categories of relevant data are defined by one or more properties and/or operational characteristics of the building. The defined categories of relevant data are associated with a corresponding one or more of the plurality of MRACs. Each MRAC receives data that satisfy data in the defined categories associated therewith. A hierarchy is created among the plurality of MRACs such that each increasing level of the hierarchy provides a more detailed assessment of energy efficiency for buildings in the defined category of relevant data.

A non-transitory computer-readable recording medium stores a model generation program for causing a computer to execute a process including: obtaining a plurality of pieces of data; inputting the plurality of pieces of data to a first model and obtaining a plurality of prediction results; determining importance of each of the plurality of pieces of data based on the plurality of prediction results; and generating a second model based on the determined importance and the plurality of pieces of data.

Embodiments are directed towards controlling uncontrolled release of ammonia from an engine of a vehicle. An estimated status of the engine is determined prior to an event, such as an estimated load on the engine prior to the vehicle going up a hill. A predictive model of uncontrolled ammonia release is generated for the estimated status. At least one engine-related countermeasure is selected based on the predictive model. If the predictive model of uncontrolled ammonia release with the selected countermeasures satisfies a threshold condition, then the selected engine-related countermeasure is employed.

A system and method of improving facility performance and reliability includes the integrated use of feedstock property management, condition-based monitoring (CBM), neural network augmented predictions of the impacts of feedstock properties, and feedstock properties/plant operation databases used for machine learning applications. Sensors are used to identify feedstock properties and operating parameters throughout the facility. Understanding how feedstock properties impact facility performance over time allows the system to predict how feedstock properties will impact processing outputs so that adjustments to operating parameters may be made to improve facility performance.

A non-transitory computer-readable recording medium stores a control program causing a computer to execute a processing including: acquiring an actual result of a target that fluctuates according to a control by a system; calculating a weight for a control values to be input to the system according to a comparison between the actual result and a specific range; calculating the control value based on the actual result and the weight; and controlling the target by inputting the calculated control value to the system.

A system includes a first facility element having a sensor and configured to generate recent performance data associated with a system of a facility, and a monitoring and control element in communication with the first facility element, where the monitoring and control element is configured to identify one or more analogous facility elements analogous to the first facility element, receive the recent performance data for the first facility element, generate projected performance data for the facility element according to historical performance data associated with the facility element and the one or more analogous facility elements, compare the projected performance data to a performance threshold, and override a setting or operating parameter of the first facility element according to a relationship of the projected performance data to the performance threshold and by sending one or more operational adjustment commands to at least one second facility element.

Aspects of the disclosure provide for controlling an autonomous vehicle. For instance, a first probability distribution may be generated for the vehicle at a first future point in time using a generative model for predicting expected behaviors of objects and a set of characteristics for the vehicle at an initial time expected to be perceived by an observer. Planning system software of the vehicle may be used to generate a trajectory for the vehicle to follow. A second probability distribution may be generated for a second future point in time using the generative model based on the trajectory and a set of characteristics for the vehicle at the first future point expected to be perceived by the observer. A surprise assessment may be generated by comparing the first probability distribution to the second probability distribution. The vehicle may be controlled based on the surprise assessment.

The technology relates to controlling a vehicle in an autonomous driving mode in accordance with behavior predictions for other road users in the vehicle's vicinity. In particular, the vehicle's onboard computing system may predict whether another road user will perform a “continuing” lane driving operation, such as going straight in a turn-only lane. Sensor data from detected/observed objects in the vehicle's nearby environment may be evaluated in view of one or more possible behaviors for different types of objects. In addition, roadway features, in particular whether lane segments are connected in a roadgraph, are also evaluated to determine probabilities of whether other road users may make an improper continuing lane driving operation. This is used to generate more accurate behavior predictions, which the vehicle can use to take alternative (e.g., corrective) driving actions.