From ML2 to ML2+: Integrating Time Series Forecasting in Model-Driven Engineering of smart IoT Applications

Abstract

Time-series forecasting is essential for anomaly detection, predictive maintenance, and real-time optimization in IoT environments, where sensor data is sequential. However, most model-driven engineering (MDE) frameworks lack specialized mechanisms to capture temporal dependencies, restricting the creation of intelligent and adaptive IoT systems. IoT inherently involves sequential data, yet most frameworks do not support time-series forecasting, essential for real-world systems. This paper presents ML2+, an enhanced version of the ML-Quadrat framework that integrates software engineering (SE) with machine learning (ML) in modeldriven engineering. ML2+ allows users to define models, things, and messages for time-series forecasting. We evaluated ML2+ through two IoT use cases, focusing on development time, performance metrics, and lines of code (LOC). Results show that ML2+ maintains prediction accuracy similar to manual coding while significantly reducing development time by automating tedious tasks for developers. By automating feature engineering, model training, and evaluation for time-series data, ML2+ streamlines forecasting, improving scalability. ML2+ supports various forecasting models, including deep learning, statistical, and hybrid models. It offers preprocessing capabilities such as handling missing data, creating lagged features, and detecting data seasonality. The tool automatically generates code for time-series forecasting, making it easier for developers to train and deploy ML models without coding.