Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Office building thermal comfort control system and method based on deep reinforcement learning

A technology of reinforcement learning and control systems, applied in general control systems, control/regulation systems, temperature control, etc., can solve problems such as state and action dimension increase, dimension disaster, etc.

Active Publication Date: 2021-03-23
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the two types of systems are directly controlled jointly, the state and action dimensions show an exponential upward trend, which leads to the "curse of dimensionality" problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Office building thermal comfort control system and method based on deep reinforcement learning
  • Office building thermal comfort control system and method based on deep reinforcement learning
  • Office building thermal comfort control system and method based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] Such as figure 1 As shown, a thermal comfort control system for office buildings based on deep reinforcement learning includes the following modules:

[0083] The deep reinforcement learning agent module connected with the HVAC subsystem and the personal comfort subsystem, the deep reinforcement learning agent module includes an information collection sub-module, an information storage sub-module, an online learning sub-module and a control strategy sub-module.

[0084] The HVAC subsystem consists of split indoor and outdoor units with a wireless actuator module for automatically setting the air conditioner temperature set point, and the HVAC subsystem is used to regulate the internal temperature of the multi-user shared office area.

[0085] Consisting of a desktop fan or / and heating device with a wireless actuator module, the personal comfort subsystem is used to regulate the microenvironment around its associated user. It is worth noting that the number of personal ...

Embodiment 2

[0093] Such as figure 2 , image 3 As shown, the present invention provides a method for thermal comfort control of office buildings based on deep reinforcement learning, including:

[0094] Step 1: The information collection sub-module acquires state information at the beginning of each time slot and sends it to the information storage sub-module and the control strategy sub-module.

[0095] Step 2: The control strategy sub-module outputs the control behavior of the HVAC subsystem and the personal comfort subsystem after receiving the state information at the beginning of each time slot, and sends the control behavior information to the information storage sub-module. At the same time, the control behavior implementation information is sent to the HVAC subsystem and the personal comfort subsystem for execution. Then judge whether to update the deep neural network model. If it needs to be updated, obtain the parameters of the deep neural network training model from the onl...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an office building thermal comfort control system and method based on deep reinforcement learning. The system comprises a deep reinforcement learning intelligent agent module which is connected with a heating, ventilation and air conditioning subsystem and a personal comfort subsystem, and comprises a control strategy sub-module and an online learning sub-module; the control strategy sub-module can output cooperative behaviors of the heating, ventilating and air conditioning subsystem and the personal comfort subsystem based on the environment state information and sendthe cooperative behavior information to the heating, ventilating and air conditioning subsystem and the personal comfort subsystem to be executed; and the online learning sub-module and the control strategy sub-module work in parallel, the deep neural network is trained online by using the environment state information and the cooperative behavior information, and the trained deep neural networkmodel is copied to the control strategy sub-module regularly for decision making. Personalized user thermal comfort experience can be provided, and the total electric charge / energy consumption of thesystem can be optimized.

Description

technical field [0001] The invention relates to a thermal comfort control system and method for office buildings based on deep reinforcement learning, and belongs to the interdisciplinary technical field of building energy management and artificial intelligence. Background technique [0002] In December 2019, the Global Building and Construction Alliance led by the United Nations Environment Program released the "Global Status Report 2019". According to the report, energy consumption related to building construction and operation accounted for 36% of the world's total energy consumption in 2018, and the corresponding carbon emissions accounted for 39% of the world's energy-related carbon emissions. In addition, with further population growth and the rapid increase in purchasing power in emerging economies, building energy demand will increase by 50% in 2050 compared to 2016. Due to the limited amount of traditional energy sources (such as coal, oil, and natural gas), the ev...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G05B13/04G05B13/02G05D23/19
CPCG05B13/042G05B13/027G05D23/1919Y02P90/84
Inventor 余亮魏良兵岳东窦春霞
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com