# An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism

arXiv: https://arxiv.org/abs/2607.15511 · HTML: https://mlsanity.com/paper/2607.15511/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 95 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization](https://mlsanity.com/paper/2305.19420/) (2023)
- [Recent Advances in Bayesian Optimization](https://mlsanity.com/paper/2206.03301/) (2022)
- [Do RNN and LSTM have Long Memory?](https://mlsanity.com/paper/2006.03860/) (2020)
- [Bayesian model averaging: A systematic review and conceptual classification](https://mlsanity.com/paper/1509.08864/) (2015)
- [A Primer on Bayesian Neural Networks: Review and Debates](https://mlsanity.com/paper/2309.16314/) (2023)
- [A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systems](https://mlsanity.com/paper/1609.03590/) (2016)
- [Serverless Computing: A Survey of Opportunities, Challenges and Applications](https://mlsanity.com/paper/1911.01296/) (2019)
- [Working Memory Connections for LSTM](https://mlsanity.com/paper/2109.00020/) (2021)
- [A Comprehensive Survey on Spectral Clustering with Graph Structure Learning](https://mlsanity.com/paper/2501.13597/) (2025)
- [Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks](https://mlsanity.com/paper/1701.03441/) (2017)
- [AI-based Resource Allocation: Reinforcement Learning for Adaptive Auto-scaling in Serverless Environments](https://mlsanity.com/paper/2005.14410/) (2020)
- [A Holistic View on Resource Management in Serverless Computing Environments: Taxonomy and Future Directions](https://mlsanity.com/paper/2105.11592/) (2021)
- [LSTM with Working Memory](https://mlsanity.com/paper/1605.01988/) (2016)
- [Rise of the Planet of Serverless Computing: A Systematic Review](https://mlsanity.com/paper/2206.12275/) (2022)
- [Depth-Gated LSTM](https://mlsanity.com/paper/1508.03790/) (2015)
- [A Deep Reinforcement Learning based Algorithm for Time and Cost Optimized Scaling of Serverless Applications](https://mlsanity.com/paper/2308.11209/) (2023)
- [Automatic Cloud Resource Scaling Algorithm based on Long Short-Term Memory Recurrent Neural Network](https://mlsanity.com/paper/1701.03295/) (2017)
- [Self-adaptive, Requirements-driven Autoscaling of Microservices](https://mlsanity.com/paper/2403.08798/) (2024)
- [Dirigo: Self-scaling Stateful Actors For Serverless Real-time Data Processing](https://mlsanity.com/paper/2308.03615/) (2023)
- [Non-Stationary Gradient Descent for Optimal Auto-Scaling in Serverless Platforms](https://mlsanity.com/paper/2502.01284/) (2025)
- [Marlin: Efficient Coordination for Autoscaling Cloud DBMS (Extended Version)](https://mlsanity.com/paper/2508.01931/) (2025)
- [Key Considerations for Auto-Scaling: Lessons from Benchmark Microservices](https://mlsanity.com/paper/2510.02585/) (2025)

## Abstract (arXiv)

Serverless computing provides automatic resource management and pay-per-use execution, but effective autoscaling remains challenging because of dynamic workloads, cold-start latency, and dependencies among functions. We present a dependency-aware autoscaling framework that integrates graph-based bottleneck identification, short-term workload forecasting, multi-model consensus, and cost-aware scaling control. Serverless applications are represented as directed dependency graphs, and structurally important functions are identified using weighted degree centrality. Resource demand is predicted using lightweight MLP, LSTM, and CNN models. Their outputs are combined through a performance-weighted probabilistic ensemble inspired by Bayesian model averaging. The controller further incorporates cold-start awareness and cost comparison to select among scale-up, scale-down, and hold actions. Experiments using real workload traces show that supervised forecasting substantially outperforms unsupervised clustering for autoscaling decision generation. The proposed ensemble achieves 99.88 percent prediction accuracy and reduces prediction error compared with representative hybrid forecasting methods. Evaluations across multiple cloud pricing models also demonstrate consistent infrastructure cost reductions while maintaining performance targets. The results show that combining dependency analysis, multi-expert forecasting, and cost-aware control provides a robust and practical solution for serverless autoscaling.