SG10201808290XA - Systems and methods for optimization of data center cooling - Google Patents
Systems and methods for optimization of data center coolingInfo
- Publication number
- SG10201808290XA SG10201808290XA SG10201808290XA SG10201808290XA SG10201808290XA SG 10201808290X A SG10201808290X A SG 10201808290XA SG 10201808290X A SG10201808290X A SG 10201808290XA SG 10201808290X A SG10201808290X A SG 10201808290XA SG 10201808290X A SG10201808290X A SG 10201808290XA
- Authority
- SG
- Singapore
- Prior art keywords
- data center
- neural network
- center cooling
- cooling system
- data
- Prior art date
Links
Landscapes
- Air Conditioning Control Device (AREA)
- Feedback Control In General (AREA)
Abstract
SYSTEMS AND METHODS FOR OPTIMIZATION OF DATA CENTER COOLING Systems and methods for optimizing control parameters of a data center cooling system using reinforcement learning are disclosed. A method for optimizing control parameters for a data center cooling system, comprises: initializing an actor neutral network configured to generate an indication of a subsequent control action in response to an actor neural network input vector comprising an indication of a current state of the data center cooling system; initializing a critic neutral network configured to generate a cost indication in response to a critic neural network input vector comprising an indication of the current state of the data center cooling system and a subsequent control action; receiving trace data indicating control actions, previous states of the data center cooling system, and corresponding temperature data and energy usage data for the data center cooling system; training the critic neural network by determining a set of parameter weights for the critic neural network which minimizes error between an output of the critic neural network and reward data corresponding to the temperature data and energy usage data for the data center cooling system; training the actor neural network by determining a set of parameter weights for the actor neural network which minimize the cost indication generated by the critic neural network; and using the trained actor neural network to generate a set of control parameters for the data center cooling system. [Figure to be printed with ] 31
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
SG10201707838W | 2017-09-22 |
Publications (1)
Publication Number | Publication Date |
---|---|
SG10201808290XA true SG10201808290XA (en) | 2019-04-29 |
Family
ID=66250388
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
SG10201808290XA SG10201808290XA (en) | 2017-09-22 | 2018-09-24 | Systems and methods for optimization of data center cooling |
Country Status (1)
Country | Link |
---|---|
SG (1) | SG10201808290XA (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021254589A1 (en) * | 2020-06-15 | 2021-12-23 | Huawei Technologies Co., Ltd. | Method and system for a controller |
-
2018
- 2018-09-24 SG SG10201808290XA patent/SG10201808290XA/en unknown
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021254589A1 (en) * | 2020-06-15 | 2021-12-23 | Huawei Technologies Co., Ltd. | Method and system for a controller |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101945863B1 (en) | Method for computer-aided plant control optimisation using a simulation module | |
Yin et al. | Online ship roll motion prediction based on grey sequential extreme learning machine | |
MX2019015040A (en) | Automated response server device, terminal device, response system, response method, and program. | |
WO2017213857A1 (en) | System for iteratively training an artificial intelligence using cloud-based metrics | |
MX2018000942A (en) | Continuous control with deep reinforcement learning. | |
EA201391111A1 (en) | SYSTEM AND METHOD FOR USE OF ARTIFICIAL NEURAL NETWORK FOR MODELING A HYDRAULIC OF PIPELINES IN THE SIMULATOR | |
WO2020111754A3 (en) | Method for providing diagnostic system using semi-supervised learning, and diagnostic system using same | |
Han et al. | A direct self-constructing neural controller design for a class of nonlinear systems | |
Yin et al. | Robust control for nonhomogeneous Markov jump processes: an application to DC motor device | |
US20240037677A1 (en) | Method for power consumption analysis and troubleshooting of production line based on industrial internet of things, system and storage medium thereof | |
WO2020112186A3 (en) | Autonomous system including a continually learning world model and related methods | |
MX2012010627A (en) | Systems for machine emulation and process response prediction. | |
SG10201808290XA (en) | Systems and methods for optimization of data center cooling | |
MX2015008690A (en) | System and method for prescriptive analytics. | |
CN107168066B (en) | Greenhouse environment self-adaptive control method | |
CN106605179A (en) | Predicted value modification system, control system, predicted value modification method, control method, and predicted value modification program | |
Yan et al. | Study on prediction model of dissolved oxygen about water quality monitoring system based on BP neural network | |
JP2019219741A5 (en) | ||
CN104200038A (en) | Optimized design method of electric steel sheet magnetic hysteresis loss Preisach model | |
CN105224779A (en) | Electrical power distribution network fault location method and device | |
US8190536B2 (en) | Method of performing parallel search optimization | |
Zhang | Robust synchronization of FitzHugh–Nagumo network with parameter disturbances by sliding mode control | |
CN115438588B (en) | Temperature prediction method, system, equipment and storage medium for lithium battery | |
Gerkšič et al. | Plasma current and shape control for ITER using fast online MPC | |
Wakitani et al. | Design of a cmac-based pid controller using operating data |