Interactivity Anomaly Detection in Remote Work Scenarios Using LSTM

In recent years, there has been a notable surge in the utilization of remote desktop services, largely driven by the emergence of new remote work models introduced during the pandemic. These services cater to interactive cloud-based applications (CIAs), whose core functionality operates in the cloud, demanding strict end-user interactivity requirements. This boom has led to a significant increase in their deployment, accompanied by a corresponding increase in associated maintenance costs. Service administrators aim to guarantee a satisfactory Quality of Experience (QoE) by monitoring metrics like interactivity time, particularly in cloud environments where variables such as network performance and shared resources come into play. This paper analyses anomaly detection state of the art and proposes a novel system for detecting interactivity time anomalies in cloud-based remote desktop environments. We employ an automatic model based on LSTM neural networks that achieves an accuracy of up to 99.97%.