Optimizing Self-Adaptation in Service-Based Systems: Leveraging Ensemble Prediction with DNN-ILSTM Models

Service-based systems (SBSs) dynamically integrate various third-party services at runtime, offering sophisticated and adaptable functionalities. However, this dynamic integration introduces unpredictability and uncertainty, posing challenges for system maintenance. Proactive self-adaptation based on prediction has emerged as a common approach to address these issues. Many existing methods focus primarily on prediction accuracy, often neglecting the crucial aspect of “earliness“ in predictions. Balancing earliness and accuracy is very crucial in practice, as it provides more time for self-adaptation while ensuring reliable predictions. Therefore, we propose PSA4SBS (Proactive Self-Adaptation for Service-Based Systems), which aims to balance this trade-off in SBSs. PSA4SBS features an ensemble prediction model based on deep neural networks (DNN) and an improved long short-term memory (ILSTM) architecture. It helps SBSs adapt to the frequent unpredictability and instability, facilitating the achievement of adaptation objectives. This mechanism im-proves the prediction and analysis of adaptation goal violations, thereby enhancing the reliability and performance of service level agreements (SLAs) for quality of service (QoS). We evaluated PSA4SBS's performance in a decentralized tele-assistance system using four key metrics. Preliminary experimental results show its exceptional performance.