# Multi-Level Service Performance Forecasting via Spatiotemporal Graph Neural Networks

arXiv: https://arxiv.org/abs/2508.07122 · HTML: https://mlsanity.com/paper/2508.07122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting](https://mlsanity.com/paper/2011.11004/) (2020)
- [Dynamic Operating System Scheduling Using Double DQN: A Reinforcement Learning Approach to Task Optimization](https://mlsanity.com/paper/2503.23659/) (2025)
- [Leveraging Convolutional Neural Network-Transformer Synergy for Predictive Modeling in Risk-Based Applications](https://mlsanity.com/paper/2412.18222/) (2024)
- [Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration](https://mlsanity.com/paper/2504.00282/) (2025)
- [Context-Aware Rule Mining Using a Dynamic Transformer-Based Framework](https://mlsanity.com/paper/2503.11125/) (2025)
- [Deep Probabilistic Modeling of User Behavior for Anomaly Detection via Mixture Density Networks](https://mlsanity.com/paper/2505.08220/) (2025)
- [Modeling Multi-Hop Semantic Paths for Recommendation in Heterogeneous Information Networks](https://mlsanity.com/paper/2505.05989/) (2025)
- [Time-Series Learning for Proactive Fault Prediction in Distributed Systems with Deep Neural Structures](https://mlsanity.com/paper/2505.20705/) (2025)
- [AI Back-End as a Service for Learning Switching of Mobile Apps between the Fog and the Cloud](https://mlsanity.com/paper/2110.00836/) (2021)

## Abstract (arXiv)

This paper proposes a spatiotemporal graph neural network-based performance prediction algorithm to address the challenge of forecasting performance fluctuations in distributed backend systems with multi-level service call structures. The method abstracts system states at different time slices into a sequence of graph structures. It integrates the runtime features of service nodes with the invocation relationships among services to construct a unified spatiotemporal modeling framework. The model first applies a graph convolutional network to extract high-order dependency information from the service topology. Then it uses a gated recurrent network to capture the dynamic evolution of performance metrics over time. A time encoding mechanism is also introduced to enhance the model's ability to represent non-stationary temporal sequences. The architecture is trained in an end-to-end manner, optimizing the multi-layer nested structure to achieve high-precision regression of future service performance metrics. To validate the effectiveness of the proposed method, a large-scale public cluster dataset is used. A series of multi-dimensional experiments are designed, including variations in time windows and concurrent load levels. These experiments comprehensively evaluate the model's predictive performance and stability. The experimental results show that the proposed model outperforms existing representative methods across key metrics such as MAE, RMSE, and R2. It maintains strong robustness under varying load intensities and structural complexities. These results demonstrate the model's practical potential for backend service performance management tasks.