BIAS Autoscaler leverages burstable instances for scaling Google Computer Engine instances on GCP. Unlike most of the autoscalers available in the industry, BIAS Austoscaler uses burstable instances for reducing cost and increasing efficiency of cloud resources while maintaining quality of service metrics.

BIAS Autoscaler uses the Google API and Google SDK for scaling out and in Google Compute Engine instances. The Google Cloud Load Balancer is used for tuning the CPU usage of the burstable instances in real time.

The internal architecture of the BIAS Autoscaler consists of three major blocks: Controller, Monitor and Scaling Policy.

• Java 11
• Micronaut Framework 2.4.1
• Swagger UI
• Lombock

• Google Compute Engine API Client Library for Java
• Google Stackdriver Monitoring Client for Java
• Google Cloud SDK

• JDK 11
• Maven 3
• Google Cloud SDK

All documentation is available here.

1. Quick Start
   • Run Autoscaler
   • Configure Autoscaler
2. Scaling Policy
3. Autoscaler Architecture
   • Monitor
   • Scaling
   • Controller
4. Benchmark Tests
5. APIs

This work was published in the WoSC7:

Jaime Dantas, Hamzeh Khazaei and Marin Litoiu. 2021. BIAS Autoscaler: Leveraging Burstable Instances for Cost-Effective Autoscaling on Cloud Systems. In Seventh International Workshop on Serverless Computing (WoSC7) 2021 (WoSC ’21), December 6, 2021, Virtual Event, Canada. ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/3493651.3493667

This project is licensed under the MIT License - see the LICENSE file for details.