Some content of this application is unavailable at the moment.
If this situation persists, please contact us atFeedback&Contact
1. (WO2019063079) SYSTEM, DEVICE AND METHOD FOR ENERGY AND COMFORT OPTIMIZATION IN A BUILDING AUTOMATION ENVIRONMENT
Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

Claims

1. A method (100) of energy and comfort optimization in a building automation environment (302, 802, 1002), the method (100) comprising:

receiving environment data associated with the building automation environment (302, 802, 1002);

generating a building model for the building automation environment (302, 802, 1002), wherein the building model is represented by a set of states comprising energy profiles and comfort profiles;

determining reward vectors for the set of states with the energy profiles and the set of states with the comfort pro-files, wherein the reward vectors are determined based on probabilities of transition from a current state to remaining states of the set of states;

determining an optimization policy for energy and comfort based on the reward vectors;

performing an action based on the optimization policy whereby the building automation environment (302, 802, 1002) transitions to a new state in the set of states; and

optimizing the energy and comfort by iteratively determining the reward vectors and the optimization policy for the new state.

2. The method (100) as claimed in claim 1, wherein generating a building model for the building automation environment (302, 802, 1002), comprises:

generating the building model for the building automation environment (302, 802, 1002) based on one of a historical environment data and a predicted environment data.

3. The method (100) as claimed in claim 1, further compris- ing:

determining the current state from the set of states based on the environment data, wherein the current state comprises one of at least one energy profile and at least one comfort profile .

4. The method (100) as claimed in claim 3, wherein determin-ing the current state of the building automation environment

(302, 802, 1002) based on the environment data comprises: identifying emotion and behaviour pattern of at least one occupant in of the building automation environment (302, 802, 1002), wherein the at least one occupant comprise living and non-living entities.

5. The method (100) as claimed in claim 4, wherein identifying emotion and behaviour pattern of at least one occupant in the building automation environment (302, 802, 1002) com-prises:

capturing emotion and behavior of the at least one occupant in form of audio data, video data and image data; and auto-correlating the audio data, video data and image data in a chronological sequence using at least one neural network, wherein the at least one neural network comprises one of a recurrent neural network and convolution neural network.

6. The method (100) as claimed in claim 4, comprising:

monitoring an energy data comprising plug load and energy sources associated with the building automation environment (302, 802, 1002);

monitoring an occupant data comprising occupant metabolic rate, occupant energy consumption, occupant clothing; and

determining an ambient data comprising weather, air qual-ity, air temperature, radiant temperature, air velocity, relative humidity, time, day.

7. The method (100) as claimed in claim 1, comprising:

generating a state matrix with the probabilities of tran-sition from the current state to remaining states, wherein the probabilities of transition comprises probabilities of achieving an effective goal associated with optimizing energy and comfort in the building automation environment (302, 802, 1002) .

8. The method (100) as claimed in claim 1, wherein determin-ing reward vectors for the set of states with the energy profiles and the set of states with the comfort profiles, comprises :

predicting the reward vector for the remaining states based on a static learning method (100) and a dynamic learning method (100) .

9. The method (100) as claimed in claim 1, further comprising :

receiving at least one occupant feedback on the new state of the building automation environment (302, 802, 1002), wherein the at least one feedback is associated with emotion and behaviour pattern of an occupant in the building automation environment (302, 802, 1002); and

updating the building environment model at predetermined intervals with the at least one occupant feedback.

10. The method (100) as claimed in claim 1, wherein the building automation environment (302, 802, 1002) comprises a plurality of occupants and wherein optimizing the energy and com-fort of the building automation environment (302, 802, 1002) comprises :

clustering the plurality of occupants in into groups based on similarity in occupant profile, wherein the occupant profile is generated based on emotion and behaviour patterns, an oc-cupant data and an energy data;

optimizing the energy and comfort of the building automation environment (302, 802, 1002) based on the clustering of the plurality of occupants.

11. The method (100) as claimed in claim 1, wherein the building automation environment (302, 802, 1002) is divided into plurality of sections comprising a building, a building floor and a room and wherein optimizing the energy and comfort of the building automation environment (302, 802, 1002) comprises :

optimizing energy and comfort at each of the plurality of sections based on a section optimization policy for each of the plurality of sections; and

optimizing the energy and comfort for the building automation environment (302, 802, 1002) based on the optimized energy and comfort for each section.

12. The method (100) as claimed in claim 1, comprising:

displaying a recommended action to at least one occupant to enter a recommended state, wherein a probability of transition to the recommended state indicates high probability of achieving an effective goal associated with optimizing energy and comfort in the building automation environment (302, 802, 1002); and

optimizing the energy and comfort of the building automation environment (302, 802, 1002) when the recommended action is selected by the occupant.

13. The method (100) as claimed in one of claims 1 to 12, wherein the environment data comprises sensor data, energy data, occupant data and ambient data associated with the building automation environment (302, 802, 1002), and wherein the action and the recommended action comprises change in operation parameters of the energy sources and the plug load including fans, air conditioners, heaters, radiators, humidifiers, vents, windows, blinds, and consumer electronics, associated with the building automation environment (302, 802, 1002).

14. The method (100) as claimed in one of claims 1 to 13, wherein the energy and comfort optimization in the building automation environment (302, 802, 1002) is performed in realtime using a deep reinforcement learning technique.

15. A computing device (200) for energy and comfort optimization in a building automation environment (302, 802, 1002), the computing device (200) comprising:

a communication unit (202) to receive environment data associated with the building automation environment (302, 802, 1002) ;

at least one processor (204) communicatively coupled to the communication unit; and

a memory (210) communicatively coupled to the at least one processor, the computing device (200) characterized by the memory comprising:

a model generator module (212) to generate a building model for the building automation environment (302, 802,

1002), wherein the building model is represented by a set of states comprising energy profiles and comfort profiles;

a learning module (214) to determine reward vectors for the set of states with the energy profiles and the set of states with the comfort profiles, wherein the reward vectors are determined based on probabilities of transition from a current state to remaining states of the set of states; and

a policy module (216) to determine an optimization policy for energy and comfort based on the reward vectors, wherein the computing device (200) performs an action based on the optimization policy whereby the building automation environment (302, 802, 1002) transitions to a new state in the set of states, and

wherein the energy and comfort are optimized by itera-tively determining the reward vectors and the optimization policy for the new state.

16. The computing device (200) as claimed in claim 15, wherein the action and the recommended action comprises change in operation parameters of the energy sources and the plug load including fans, air conditioners, heaters, radiators, humidifiers, vents, windows, blinds, and consumer electronics, as-sociated with the building automation environment (302, 802, 1002) .

17. The computing device (200) as claimed in claim 15, wherein the learning module (214) comprises:

a state module (232) to generate a state matrix with the probabilities of transition from the current state to remaining states, wherein the probabilities of transition comprises probabilities of achieving an effective goal associated with optimizing energy and comfort in the building automation environment (302, 802, 1002); and

a reward module (234) to predict the reward vector for the remaining states based on a static learning method (100) and a dynamic learning method (100) .

18. The computing device (200) as claimed in claim 15, wherein the memory comprises:

a recommendation module (218) configured to select a recommended state, wherein a probability of transition to the recommended state indicates high probability of achieving an effective goal associated with optimizing energy and comfort in the building automation environment (302, 802, 1002);

a render module (220) configured to display a recommended action associated with the recommended state to at least one user device of at least one occupant, wherein the computing device (200) performs the recommended action with the at least one occupant selects the recommended state; and

a model updater module (222) to update the building environment model at predetermined intervals with the selection of the at least one occupant.

19. The computing device (200) as claimed in claim 15, wherein the learning module comprises:

a comfort optimizer module (236) to identify emotion and behaviour pattern of at least one occupant in of the building automation environment (302, 802, 1002), wherein the occupant comprise living and non-living entities.

20. The computing device (200) as claimed in claim 19, further comprising :

a capturing device (206) to capture emotion and behavior of the occupants in form of audio data, video data and image data, wherein the comfort optimizer module is configured to auto-correlating the audio data, video data and image data in a chronological sequence using at least one neural network, wherein the at least one neural network comprises one of a recurrent neural network and convolution neural network.

21. The computing device (200) as claimed in claim 15, wherein the learning module comprises:

an energy optimizer module (238) comprising:

an energy analyzer (242) to monitor an energy data comprising plug load and energy sources associated with the building automation environment (302, 802, 1002); a consumption analyzer (244) to monitor an occupant data comprising occupant metabolic rate, occupant energy consumption, occupant clothing; and

an ambient analyzer (246) to determine an ambient data comprising weather, air quality, air temperature, radiant temperature, air velocity, relative humidity, time, day.

22. The computing device (200) as claimed in claim 15, wherein the memory comprises:

a clustering module (224) to cluster a plurality of occupants in the building automation environment (302, 802, 1002) into groups based on similarity in occupant profile, wherein the occupant profile is generated based on emotion and behaviour patterns, an occupant data and an energy data, wherein the energy and comfort of the building automation environment (302, 802, 1002) is optimized based on the clustering of the plurality of occupants.

23. A system (300, 600, 700, 800) for energy and comfort optimization in a building automation environment (302, 802, 1002), the system (300, 600, 700, 800) comprising:

a server (320) operable on a cloud computing platform; a network interface (350) communicatively coupled to the server; and

at least one computing device (200) as claimed in claims 15 - 22, communicatively coupled to the server via the network interface and wherein the at least one computing device (200) is associated with at least one section of the building automation environment (302, 802, 1002).

24. The system (300, 600, 700, 800) as claimed in claim 23, wherein the building automation environment (302, 802, 1002) is divided into a plurality of sections (802a, 802b, 802c) comprising a building, a building floor and a room.

25. The system (300, 600, 700, 800) as claimed in claim 23, wherein the server comprises:

a database (330) comprising environment data, historical environment data and predicted environment data associated with the building automation environment (302, 802, 1002), wherein the environment data comprises sensor data, energy data, occupant data and ambient data associated with the building automation environment (302, 802, 1002).

26. The system (300, 600, 700) as claimed in claim 23, further comprising :

a plurality of capture devices 310 communicatively coupled to the server (320) via the network interface (350), the plurality of capture devices are one of manned devices and unmanned devices selected comprising image sensors, a motion sensors, a GPS devices and communication devices.