Scalable AutoML for Time Series Forecasting using Ray
1 like576 views
The document discusses scalable automated machine learning (AutoML) for time series forecasting utilizing Ray and Analytics Zoo, featuring an architecture that supports various forecasting algorithms and seamless data processing. It shares use cases in telecommunications like KPI forecasting and highlights the importance of features such as automatic feature generation and model tuning for effective time series analysis. Future work focuses on handling high-dimensional time series and improving data preprocessing techniques.
Scalable AutoML for Time Series Forecasting using Ray
- 2. Scalable AutoML for Time Series Forecasting using Ray Shengsheng Huang Intel Corporation Jason Dai Intel Corporation
- 3. Agenda Background Analytics Zoo, Time Series, AutoML, Ray Scalable AutoML for Time Series Architecture, workflow, etc. Use Case Sharing & Learnings Use case study, what we learn from early users, future work
- 4. Background
- 5. AI on Big Data Accelerating Data Analytics + AI Solutions At Scale Distributed, High-Performance Deep Learning Framework for Apache Spark* https://github.com/intel-analytics/bigdl Unified Analytics + AI Platform for TensorFlow*, PyTorch*, Keras*, BigDL, Ray* and Apache Spark* https://github.com/intel-analytics/analytics-zoo
- 6. Analytics Zoo https://github.com/intel-analytics/analytics-zoo Unified Data Analytics and AI Platform
- 7. Time Series In a Nutshell Time Series data ▪ A series of data that is observed sequentially in time. ▪ stock prices, sales volume, CPU/IO monitoring metrics, KPIs in telecom networks ... Time Series Analysis ▪ Time Series Forecasting ▪ Anomaly Detection ▪ Time Series Classification, clustering, etc. Applications ▪ Demand forecasting ▪ network quality management ▪ predictive maintenance ▪ AIOps Total volume of taxi passengers in NYC from 2014/07-2015/02 ( source : https://github.com/intel-analytics/analytics-zoo/blob/master/apps/anomaly- detection/anomaly-detection-nyc-taxi.ipynb)
- 8. Time Series Forecasting Problem Definition ▪ Given all history t observations 𝑦_1,…, 𝑦_𝐭 , Predict values of next 𝐡 steps, 𝑦_(𝐭+𝟏),…, 𝑦_(𝐭+𝒉) ▪ Usually only lookback 𝐤 steps, 𝑦_(𝐭−𝒌+𝟏),…, 𝑦_𝐭 Forecasting Methods ▪ Autoregression, Exponential Smoothing, ARIMA, … ▪ Machine Learning and Deep Learning methods 𝒚 𝟏 𝒚 𝟐 𝒚 𝒕 𝒚 𝒕$𝟏 𝒚 𝒕$𝒉𝒚 𝒕&𝒌$𝟏 lookback k steps forecast h steps forward
- 9. AutoML Source: Yao, Q., Wang, et. al Taking the Human out of Learning Applications : A Survey on Automated Machine Learning.
- 10. Ray and RayOnSpark Ray ▪ A distributed framework for emerging AI applications Ray Tune ▪ A library on Ray for experiment execution and hyperparameter tuning RayOnSpark ▪ a feature in Analytics Zoo ▪ Directly run Ray programs on big data cluster ▪ Seamlessly integrate ray into spark data processing pipeline https://ray.readthedocs.io/en/latest/ https://analytics-zoo.github.io/master/#ProgrammingGuide/rayonspark/
- 11. Scalable AutoML for Time Series
- 12. Time Series Solution In Analytics Zoo Rich algorithms statistical, neural-networks, hybrid state-of-art models, etc. AutoML for automatic feature generation, model selection, hyper-parameter tuning, etc. Seamless scaling with integrated analytics and AI pipelines
- 13. Software Stack AutoML Framework ▪ FeatureTransformer ▪ Model ▪ SearchEngine ▪ Pipeline Time Series upon AutoML ▪ TimeSequencePredictor ▪ TimeSequencePipeline https://medium.com/riselab/scalable-automl-for-time-series-prediction-using-ray-and-analytics- zoo-b79a6fd08139
- 15. A glimpse of API Training a Pipeline ▪ fit (w/ automl) ▪ recipe ▪ distributed mode Using a Pipeline ▪ save/load ▪ evaluate/predict ▪ fit (incremental)
- 16. Project Zouwu Use case ▪ reference time series use cases for Telco (such as network traffic forecasting, etc.) Models ▪ built-in models for time series analysis (such as LSTM and MTNet) “AutoTS” ▪ AutoML support for building E2E time series analysis pipelines (including automatic feature generation, model selection and hyperparameter tuning) Project Zouwu Built-in Models ML Workflow AutoML Workflow Integrated Analytics & AI Pipelines use-case autots model https://github.com/intel-analytics/analytics- zoo/tree/master/pyzoo/zoo/zouwu
- 17. Use Case Sharing & Learnings
- 18. Network Traffic KPI Forecasting in Telco Usage Scenario ▪ KPI/metrics forecasting is widely used in Telco applications (e.g., energy saving, network slicing, etc.) ▪ aggregated traffic KPI’s (i.e. total bytes, average rate in Mbps/Gbps) in the past week to forecast the KPI in the next two hours. 2 ways to solve this problem using Zouwu ▪ Use built-in “Forecaster” models for training, and forecasting (notebook link) ▪ Use “AutoTS” (with built-in AutoML support) to train an E2E Time Series Analysis Pipeline, and forecast (notebook link) Example result of network traffic average rate forecasting on the test period
- 19. Network Quality Prediction in SK Telecom Spark-SQL Data Loading Data Loader Data Source APIs File, HTTP, Kafka forked. DRAM Store customized. Flash Store tiering Preprocess RDD of Tensor Model Code of TF DL Training & Inferencing Data Model SIMD Acceleration https://databricks.com/session_eu19/apache-spark-ai-use-case-in- telco-network-quality-analysis-and-prediction-with-geospatial- visualization
- 20. Forecast-based Analysis for AIOps at Neusoft https://platform.neusoft.com/2020/01/17/xw-intel.html https://platform.neusoft.com/2017/03/04/qt-baomaqiche.html
- 21. Takeaways from Early Users Highlights ▪ Additional features allowed ▪ Less efforts in tuning ▪ Satisfactory accuracy Data quality matters ▪ Missing values, outliers, etc. Scale, scale, scale ▪ hundreds of thousands of cells X KPIs => millions of time series ▪ millions of servers/containers X metrics => hundreds of millions of time series
- 22. Future Work Extremely high dimensional time series Search algo, meta-learning, ensemble, … More models, features, … Automatic data preprocessing (e.g. missing data & outliers
- 23. Accelerate Your Data Analytics & AI Journey with Intel
- 24. Feedback Your feedback is important to us. Don’t forget to rate and review the sessions.