Method and system for AI-powered smart homes and offices

An Internet of Things (IoT) system comprising a computing device configured with one or more processors and one or more non-transitory computer-readable memories coupled to the one or more processors and configured with instructions executable by the one or more processors to cause the system to perform operations comprising:

• receiving, by the computing device from each of a plurality of power receptacles, power usage information of an electrical device attached to the power receptacle;
• generating, by the computing device for each of the plurality of power receptacles, a plurality of power usage metrics of the power receptacle based on the power usage information, wherein the plurality of power usage metrics comprise a power-switch frequency of the electrical device attached to the power receptacle and power consumption of the electrical device;
• feeding, by the computing device, the plurality of power usage metrics into a machine learning model to obtain a priority of the electrical device attached to the power receptacle, wherein the priority is one of a plurality of pre-configured priorities;
• crawling, by the computing device using a webpage crawler, a website associated with an electricity grid to obtain an electricity rate schedule, wherein the electricity rate schedule comprises a plurality of rate tiers at different time windows;
• generating, by the computing device, a power management signal to enter a power-saving mode or a power-efficient mode at a point of time when an electricity rate changes to a higher rate tier;
• and
• generating and transmitting, by the computing device, a plurality of control signals to the plurality of power receptacles based on the power management signal and respective priorities of the plurality of electrical devices attached to the plurality of power receptacles.

A non-transitory computer-readable storage medium configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

• receiving, from each of a plurality of power receptacles, power usage information of an electrical device attached to the power receptacle;
• generating, for each of the plurality of power receptacles, a plurality of power usage metrics of the power receptacle based on the power usage information, wherein the plurality of power usage metrics comprise a power-switch frequency of the electrical device attached to the power receptacle and power consumption of the electrical device;
• feeding the plurality of power usage metrics into a machine learning model to obtain a priority of the electrical device attached to the power receptacle, wherein the priority is one of a plurality of pre-configured priorities;
• receiving a power management signal from an electrical grid, wherein the power management signal comprises a broadcasted message for entering or exiting a power-saving mode;
• and
• generating and transmitting a plurality of control signals to the plurality of power receptacles based on the power management signal, wherein the generating and transmitting comprise:
• identifying a type of the electrical device;
• in response to the electrical device being a light, generating the corresponding control signal as dimming or turning off the light;
• and
• in response to the electrical device being a smart device, determining whether the smart device is installed with a driver program associated with the plurality of power receptacles, and sending a shutdown signal to the power receptacle corresponding to the electrical device for the power receptacle to initiate a shutdown process through the driver program.