# TS-Cabinet: Hierarchical Storage for Cloud-Edge-End Time-series Database

## TL;DR

TS-Cabinet introduces a hierarchical storage scheduler for cloud-edge-end time-series databases that uses workload forecasting to optimize data placement, significantly improving data access hit rates and reducing storage and transfer overhead.

## Contribution

It is the first hierarchical storage management strategy for cloud-edge-end time-series databases based on workload forecasting and temperature modeling.

## Key findings

- Achieves about 94% data access hit rate, 12% better than existing methods.
- Reduces storage overhead by avoiding full data storage at all three sides.
- Decreases data transfer overhead during collaborative queries.

## Abstract

Hierarchical data storage is crucial for cloud-edge-end time-series database. Efficient hierarchical storage will directly reduce the storage space of local databases at each side and improve the access hit rate of data. However, no effective hierarchical data management strategy for cloud-edge-end time-series database has been proposed. To solve this problem, this paper proposes TS-Cabinet, a hierarchical storage scheduler for cloud-edge-end time-series database based on workload forecasting. To the best of our knowledge, it is the first work for hierarchical storage of cloud-edge-end time-series database. By building a temperature model, we calculate the current temperature for the timeseries data, and use the workload forecasting model to predict the data's future temperature. Finally, we perform hierarchical storage according to the data migration policy. We validate it on a public dataset, and the experimental results show that our method can achieve about 94% hit rate for data access on the cloud side and edge side, which is 12% better than the existing methods. TS-Cabinet can help cloud-edge-end time-series database avoid the storage overhead caused by storing the full amount of data at all three sides, and greatly reduce the data transfer overhead between each side when collaborative query processing.