Service-based systems (SBSs) are a unique category of software systems that dynamically combine various third-party services at runtime to deliver complex and adaptive functionality. This dynamic composition introduces a high level of unpredictability and uncertainty, creating potential anomalies and exerting significant pressure on system maintenance. To tackle this challenge, the conventional approach involves employing prediction-based proactive self-adaptation. Despite the prevalence of existing approaches emphasizing prediction accuracy, the critical aspect of “earliness” in predictions is often overlooked. Striking a balance between early and accurate predictions is paramount in practice. In response, we propose Proactive Self-Adaptation based on Ensemble Prediction (PSA-EP) to effectively balance the trade-off between the prediction earliness and accuracy of in SBSs. At the heart of PSA-EP lies an ensemble prediction model built upon a deep neural network and an enhanced long short-term memory (DNN-ELSTM) architecture. PSA-EP is crafted to empower SBSs to adapt to the inherent unpredictability and instability, facilitating the achievement of their adaptation goals. This adaptation mechanism not only enables effective prediction and analysis of adaptation goal violations but also addresses the reliability and performance of service level agreements (SLAs) governing quality of service (QoS). We evaluated the performance of PSA-EP in a decentralized tele-assistance system using four key metrics, and the experimental results, examined from various perspectives, underscore its exceptional performance.

基于服务的系统 (SBS) 是一类独特的软件系统，它在运行时动态组合各种第三方服务，以提供复杂的自适应功能。这种动态组合引入了高度的不可预测性和不确定性，造成潜在的异常并对系统维护施加巨大压力。为了应对这一挑战，传统方法涉及采用基于预测的主动自适应。尽管现有方法普遍强调预测准确性，但预测中“早期性”的关键方面经常被忽视。在实践中，在早期预测和准确预测之间取得平衡至关重要。为此，我们提出基于集成预测的主动自适应（PSA-EP），以有效平衡 SBS 的预测早期性和准确性之间的权衡。PSA-EP 的核心是基于深度神经网络和增强型长短期记忆 (DNN-ELSTM) 架构构建的集成预测模型。PSA-EP 旨在使 SBS 能够适应固有的不可预测性和不稳定性，从而促进其适应目标的实现。这种适应机制不仅能够有效预测和分析适应目标违规情况，而且还解决了管理服务质量 (QoS) 的服务级别协议 (SLA) 的可靠性和性能问题。我们使用四个关键指标评估了 PSA-EP 在分散式远程协助系统中的性能，从不同角度检验的实验结果强调了其卓越的性能。