Systems and methods for balancing energy usage
Presented herein are techniques for balancing energy usage. A method can include obtaining energy consumption patterns of a plurality of devices that consume energy in an environment from a plurality of data sources. The method can further include analyzing operational patterns of the plurality of devices that are dynamically controllable and associated with the environment to generate device data. The method can further include building and maintaining multiple domain ontologies for sustainability profiles. The method can further include developing a profile for energy consumption for at least one device of the plurality of devices, wherein the profile is based on the energy consumption patterns, the device data, and at least one sustainability profile of the multiple domain ontologies.
1 . A computer-implemented method for balancing energy usage, comprising:
obtaining energy consumption patterns of a plurality of devices that consume energy in an environment from a plurality of data sources, wherein the energy consumption patterns include heterogeneous types of data in different formats obtained using different protocols, and wherein the data representing amounts of energy consumed by the plurality of devices includes one or more of: maximum power, power profiles, workload power, current power usage, device power specifications, environmental data, energy mix and quality, and power usage metrics;
homogenizing the energy consumption patterns to a same format in real-time;
analyzing operational patterns of the plurality of devices that are dynamically controllable and associated with the environment to generate device data;
building multiple domain ontologies for sustainability profiles;
generating a profile for energy consumption for at least one device of the plurality of devices, wherein the profile is based on the energy consumption patterns, the device data, and at least one sustainability profile of the multiple domain ontologies; and
instantiating, based on the profile for energy consumption, a configuration change to the at least one device of the plurality of devices.
2 . The computer-implemented method of claim 1 , wherein analyzing the operational patterns of the plurality of devices includes applying machine learning algorithms to data from the plurality of data sources to extract the device data and to identify one or more risks associated with the plurality of devices.
3 . The computer-implemented method of claim 1 , wherein generating the profile for energy consumption employs a single artificial intelligence model to analyze the energy consumption patterns and the device data to generate the profile for energy consumption that is optimized based on the at least one sustainability profile.
4 . The computer-implemented method of claim 1 , wherein obtaining the energy consumption patterns includes obtaining data from data sources representing current energy consumption of the plurality of devices representing actual energy usage gathered in real time.
5 . The computer-implemented method of claim 1 , wherein the obtaining the energy consumption patterns from the plurality of data sources includes obtaining power consumption data gathered from signaling in fault managed powered techniques associated with power supplied to the plurality of devices from one or more power transmitters.
6 . The computer-implemented method of claim 1 , wherein obtaining the energy consumption patterns from the plurality of data sources includes obtaining data gathered using Power over Ethernet (POE) signaling.
7 . The computer-implemented method of claim 1 , wherein the plurality of data sources include Heating, Ventilation, and Air Conditioning (HVAC) controllers, presence sensors, video devices, phones, PoE switches, servers, network switches, environmental sensors, energy systems, electric vehicle chargers, routers, monitors, network controllers, calendar data, and/or weather data.
8 . The computer-implemented method of claim 1 , further comprising:
sending commands based on the profile for energy consumption to the at least one device.
9 . The computer-implemented method of claim 8 , wherein the commands are sent via fault managed power signaling techniques.
10 . One or more non-transitory computer readable storage media encoded with software comprising computer executable instructions that, when executed by a processor, cause the processor to perform a method for balancing energy usage, comprising:
obtaining energy consumption patterns of a plurality of devices that consume energy in an environment from a plurality of data sources, wherein the energy consumption patterns include heterogeneous types of data in different formats obtained using different protocols, and wherein the data representing amounts of energy consumed by the plurality of devices includes one or more of: maximum power, power profiles, workload power, current power usage, device power specifications, environmental data, energy mix and quality, and power usage metrics;
homogenizing the energy consumption patterns to a same format in real-time;
analyzing operational patterns of the plurality of devices that are dynamically controllable and associated with the environment to generate device data;
building multiple domain ontologies for sustainability profiles;
generating a profile for energy consumption for at least one device of the plurality of devices, wherein the profile is based on the energy consumption patterns, the device data, and at least one sustainability profile of the multiple domain ontologies; and
instantiating, based on the profile for energy consumption, a configuration change to the at least one device of the plurality of devices.
11 . The one or more non-transitory computer readable storage media of claim 10 , wherein analyzing the operational patterns of the plurality of devices includes applying machine learning algorithms to data from the plurality of data sources to extract the device data and to identify one or more risks associated with the plurality of devices.
12 . The one or more non-transitory computer readable storage media of claim 10 , wherein generating the profile for energy consumption employs a single artificial intelligence model to analyze the energy consumption patterns and the device data to generate the profile for energy consumption that is optimized based on the at least one sustainability profile.
13 . The one or more non-transitory computer readable storage media of claim 10 , wherein obtaining the energy consumption patterns includes obtaining data from data sources representing current energy consumption of the plurality of devices representing actual energy usage gathered in real time.
14 . The one or more non-transitory computer readable storage media of claim 10 , wherein the obtaining the energy consumption patterns from the plurality of data sources includes obtaining power consumption data gathered from signaling in fault managed powered techniques associated with power supplied to the plurality of devices from one or more power transmitters.
15 . The one or more non-transitory computer readable storage media of claim 10 , further comprising:
sending commands based on the profile for energy consumption to the at least one device.
16 . An apparatus for balancing energy usage, comprising:
a memory;
a network interface configured to enable network communications; and
a processor, wherein the processor is configured to perform a method comprising:
obtaining energy consumption patterns of a plurality of devices that consume energy in an environment from a plurality of data sources, wherein the energy consumption patterns include heterogeneous types of data in different formats obtained using different protocols, and wherein the data representing amounts of energy consumed by the plurality of devices includes one or more of: maximum power, power profiles, workload power, current power usage, device power specifications, environmental data, energy mix and quality, and power usage metrics;
homogenizing the energy consumption patterns to a same format in real-time;
analyzing operational patterns of the plurality of devices that are dynamically controllable and associated with the environment to generate device data;
building multiple domain ontologies for sustainability profiles;
generating a profile for energy consumption for at least one device of the plurality of devices, wherein the profile is based on the energy consumption patterns, the device data, and at least one sustainability profile of the multiple domain ontologies; and
instantiating, based on the profile for energy consumption, a configuration change to the at least one device of the plurality of devices.
17 . The apparatus of claim 16 , further comprising:
sending commands based on the profile for energy consumption to the at least one device.
18 . The apparatus of claim 16 , wherein analyzing the operational patterns of the plurality of devices includes applying machine learning algorithms to data from the plurality of data sources to extract the device data and to identify one or more risks associated with the plurality of devices.
19 . The apparatus of claim 16 , wherein generating the profile for energy consumption employs a single artificial intelligence model to analyze the energy consumption patterns and the device data to generate the profile for energy consumption that is optimized based on the at least one sustainability profile.
20 . The apparatus of claim 16 , wherein obtaining the energy consumption patterns includes obtaining data from data sources representing current energy consumption of the plurality of devices representing actual energy usage gathered in real time.