Dynamic Representative Data Management of Multiple Time Series for Edge Computing

Hiroki Oikawa, Hangli Ge, Noboru Koshizuka

Abstract: With applications demanding increased amount of data, edge computing, where data are processed on the edge, is gaining popularity. Edge devices can store a limited amount of data and need to extract important data from the collected data. On-line interpolation-based data management (O-IDM) is an efficient method for managing time series data on an edge. O-IDM extracts and stores data to represent its overall shape. However, using this method becomes computationally expensive when the amount of the retained data is large. In this paper, we propose fast-O-IDM (FO-IDM), which can perform the same data extraction as O-IDM at a lower computational cost. Furthermore, we propose dynamic representative data management (D-RDM), which is a multiple time series management method that applies FO-IDM. D-RDM can efficiently hold the characteristics of multiple time series by dynamically controlling the capacity based on the data features. The extraction accuracy and computational costs of D-RDM are evaluated via comparison with other management methods. The experimental results confirmed that D-RDM could extract the data more accurately than the other methods, reducing the data amount required to convey the feature of the data by up to 25.0 percentage points compared to naive O-IDM. In addition, when the number of time series and the amount of the retained data were 3 and 30,000 respectively, the processing time of D-RDM was reduced by 91.2 percentage point compared to O-IDM, indicating that the computational cost of D-RDM is sufficiently small for use in edge devices.