A system and method for using artificial intelligence to realize energy-saving temperature control in data centers
A data center, artificial intelligence technology, applied in heating and ventilation control systems, neural learning methods, heating and ventilation safety systems, etc., to minimize HVAC consumption, improve control effects, and avoid discrete problems.
Active Publication Date: 2021-09-17
上海外高桥万国数据科技发展有限公司
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to provide a system and method for energy-saving temperature control of data centers, based on the algorithm of deep reinforcement learning of energy-saving and temperature, which can solve the existing problems, can not only meet the temperature requirements, but also minimize the HVAC consume
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0045] A system that uses artificial intelligence (AI) to realize energy-saving and temperature control of data centers, which includes: sensors, controllers, and heating, ventilation, and air-conditioning systems (HVAC); the sensors regularly measure indoor and outdoor temperature and humidity data; the controller receives indoor and outdoor temperature and humidity data; The environmental information and the working information of the HVAC system are used to obtain the adjustment plan of the HVAC system through the model algorithm; the sensor is connected to the controller, and the HVAC system receives the controller's instructions to perform heating, cooling or dehumidification.
[0046] This embodiment also provides a method for implementing energy-saving and temperature control in a data center by using artificial intelligence through the system. The method combines deep neural network and deep reinforcement learning. temperature comfort, and then combined with the deep re...
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
Login to View More Abstract
The invention discloses a system and method for realizing energy-saving temperature control of a data center by using artificial intelligence. The system includes: a sensor, a controller and a heating, ventilating and air-conditioning system. The invention also discloses a method of using artificial intelligence to realize energy-saving and temperature control of data centers through the system. The method combines deep neural network and deep reinforcement learning, and first uses deep neural network combined with Bayesian regularization algorithm to predict multiple influencing factors Under the temperature comfort, and then combined with the algorithm of deep reinforcement learning, to find the optimal adjustment plan. The system and method provided by the present invention are used in data centers. Based on the algorithm of deep reinforcement learning of energy saving and temperature, artificial intelligence is used to realize energy saving and temperature control, which can not only meet the temperature requirements, but also minimize the consumption of HVAC systems.
Description
technical field [0001] The present invention relates to a system and method for energy-saving temperature control of a data center, in particular, to a system and method for realizing energy-saving temperature control of a data center by using artificial intelligence. Background technique [0002] Data centers need to set up heating, ventilation and air conditioning (HVAC; Heating, Ventilation and Air Conditioning; HVAC systems), but HVAC is very energy-intensive and can account for 15% of the total base consumption of the data center. Therefore, it is crucial to design a control system that can both save energy and meet temperature demands. However, it is challenging to implement because it involves a variety of factors that affect the built environment, and meeting all requirements is often difficult and can vary from situation to situation. [0003] Regarding energy-saving temperature control, there are many other methods, such as Proportional IntegralDerivative (PID, pr...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): F24F11/62F24F11/46H05K7/20G06N3/04G06N3/08
CPCF24F11/62F24F11/46H05K7/20827G06N3/08G06N3/045
Inventor 陈昱
Owner 上海外高桥万国数据科技发展有限公司