Using Causality for Enhanced Prediction of Web Traffic Time Series

2025-02-02

AI Summary

Inter-service traffic interference degrades forecasting accuracy in Web service systems. Method: This paper pioneers the integration of cross-service causal modeling into time-series forecasting, proposing CCMPlus—a plug-and-play neural module. Grounded in conditional Granger causality and dynamic correlation analysis in embedding space, CCMPlus theoretically guarantees the construction of a causal relevance matrix that explicitly captures inter-service causal dependencies. It features a lightweight integration framework compatible with mainstream time-series models (e.g., LSTM, TCN), enabling seamless performance enhancement. Contribution/Results: Evaluated on real-world datasets from Microsoft Azure, Alibaba, and Ant Group, CCMPlus achieves average reductions of 12.7% in MSE and 9.4% in MAE over state-of-the-art methods, demonstrating both the efficacy and generalizability of causal modeling for complex Web traffic forecasting.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Reasoning under Uncertainty: Causality
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Predicting web service traffic has significant social value, as it can be applied to various practical scenarios, including but not limited to dynamic resource scaling, load balancing, system anomaly detection, service-level agreement compliance, and fraud detection. Web service traffic is characterized by frequent and drastic fluctuations over time and are influenced by heterogeneous web user behaviors, making accurate prediction a challenging task. Previous research has extensively explored statistical approaches, and neural networks to mine features from preceding service traffic time series for prediction. However, these methods have largely overlooked the causal relationships between services. Drawing inspiration from causality in ecological systems, we empirically recognize the causal relationships between web services. To leverage these relationships for improved web service traffic prediction, we propose an effective neural network module, CCMPlus, designed to extract causal relationship features across services. This module can be seamlessly integrated with existing time series models to consistently enhance the performance of web service traffic predictions. We theoretically justify that the causal correlation matrix generated by the CCMPlus module captures causal relationships among services. Empirical results on real-world datasets from Microsoft Azure, Alibaba Group, and Ant Group confirm that our method surpasses state-of-the-art approaches in Mean Squared Error (MSE) and Mean Absolute Error (MAE) for predicting service traffic time series. These findings highlight the efficacy of leveraging causal relationships for improved predictions.

Problem

• Website Traffic Prediction
• Mutual Influence
• Service Interactions

Innovation

• CCMPlus
• Inter-service Influence
• Traffic Prediction Enhancement