Time Series Predict DB

by   Abdullah Alomar, et al.

In this work, we are motivated to make predictive functionalities native to database systems with focus on time series data. We propose a system architecture, Time Series Predict DB, that enables predictive query in any existing time series database by building an additional "prediction index" for time series data. To be effective, such an index needs to be built incrementally while keeping up with database throughput, able to scale with volume of data, provide accurate predictions for heterogeneous data, and allow for "predictive" querying with latency comparable to the traditional database queries. Building upon a recently developed model agnostic time series algorithm by making it incremental and scalable, we build such a system on top of PostgreSQL. Using extensive experimentation, we show that our incremental prediction index updates faster than PostgreSQL (1μ s per data for prediction index vs 4μ s per data for PostgreSQL) and thus not affecting the throughput of the database. Across a variety of time series data, we find? that our incremental, model agnostic algorithm provides better accuracy compared to the best state-of-art time series libraries (median improvement in range 3.29 to 4.19x over Prophet of Facebook, 1.27 to 1.48x over AMELIA in R). The latency of predictive queries with respect to SELECT queries (0.5ms) is < 1.9x (0.8ms) for imputation and < 7.6x (3ms) for forecasting across machine platforms. As a by-product, we find that the incremental, scalable variant we propose improves the accuracy of the batch prediction algorithm which may be of interest in its own right.


page 1

page 2

page 3

page 4


SciTS: A Benchmark for Time-Series Databases in Scientific Experiments and Industrial Internet of Things

Time-series data has an increasingly growing usage in Industrial Interne...

Scalable data storage for PV monitoring systems

Efficient PV research which includes a prolonged data monitoring from mu...

TimeCrypt: A Scalable Private Time Series Data Store

We present TimeCrypt, an efficient and scalable system that augments tim...

Learning Time Series from Scale Information

Sequentially obtained dataset usually exhibits different behavior at dif...

TimeClave: Oblivious In-enclave Time series Processing System

Cloud platforms are widely adopted by many systems, such as time series ...

Modelling and predicting soil carbon sequestration: is current model structure fit for purpose?

Soil carbon accounting and prediction play a key role in building decisi...

KV-match: An Efficient Subsequence Matching Approach for Large Scale Time Series

Time series data have exploded due to the popularity of new applications...

Please sign up or login with your details

Forgot password? Click here to reset