High-reliability data storage method and device for hyper-converged power data center

• Main Authors: YIN LU, ZHANG YUNHOU, LIU FUYANG, PENG YUHUAI, SONG YANG, REN JIYUAN, WANG ZHE
• Format: Patent
• Language: Chinese; English
• Published: 16.11.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a data storage method and device for a hyper-converged power data center and a storage medium, and relates to the technical field of data storage. The method comprises the steps of: taking a hyper-converged server as a data storage node; inputting a historical data set of each data storage node into a reliability evaluation model based on long and short term memory and a convolutional neural network, and outputting node reliability; taking the node reliability as the input of a parallel data storage algorithm, performing reinforcement learning modeling by using a Markov decision process, and determining parameters corresponding to a network state set, an action set, a state transition probability and a reward function; training a parallel data storage algorithm based on the parameters, wherein the parallel data storage algorithm comprises an Actor network and a Critic network; and utilizing the trained parallel data storage algorithm to select a position set for storing files in a curre