Migration Selection Method using two Factors based LSTM in Micro DataCenter

In recent years, cloud service has been used in many field. In particular, a micro datacenter based on edge computing has been used to overcome the limitations of latency and bandwidth of cloud network architecture. Micro datacentre is small-scaled to reduce environmental constraints and minimize the complexity of fieldwork. Since there are not enough computing resources when compared with existing datacentre, efficient operation methods of services are being researched. Migration is used as a way to duplicate services and load balance services. However, migration is executed when the workload was overloading, delay may occur. This paper propose novel method MSFL(Migration Selection Method using two Factors based LSTM) that provides service availability by predicting power values based on past resource utilization rates and Long Short-Term Memory(LSTM) and pre-selecting migration target based on the relationship between servers and workloads, and values predicted. This method calculates the power consumption of servers and workloads by collecting the utilization of workload resource(CPU, Memory, Network, Disk I/O). The collected power consumption is an input value of LSTM to predict future workload is defined by analyzing the resource utilization of the workload and the server, the weight of the LSTM result is calculated using the two factors. Finally, the target of migration is selected.