Traditional server failure prediction methods predominantly rely on single-modality data such as system logs or system status curves. This reliance may lead to an incomplete understanding of system health and impending issues, proving inadequate for the complex and dynamic landscape of contemporary cloud computing environments. The potential of multimodal data to provide comprehensive insights is widely acknowledged, yet the lack of a holistic dataset and the challenges inherent in integrating features from both structured and unstructured data have impeded the exploration of multimodal-based server failure prediction. Addressing these challenges, this paper presents an industrial-scale, comprehensive dataset for server failure prediction, comprising nearly 80 types of structured and unstructured data sourced from real-world industrial cloud systems 1. Building on this resource, we introduce MISP, a model that leverages multimodal fusion techniques for server failure prediction. MISP transforms multimodal data into multi-dimensional sequences, extracts and encodes features both within and across the modalities, and ultimately computes the failure probability from the synthesized features. Experiments demonstrate that MISP significantly outperforms existing methods, enhancing prediction accuracy by approximately 25% over previous state-of-the-art approaches.

This paper proposes a Mobility and Activeness aware Relay Selection (MARS) algorithm for multi-hop D2D communication underlaying cellular networks. MARS takes into account the activeness and mobility of a user device in relay selection, and introduces an activeness factor and a mobility factor in calculating the utility gain of the system brought by a relay candidate. To select a relay for a pair of multi-hop D2D users, MARS first constructs a set of inactive user devices as the relay candidate set (RCS). For each relay candidate in the RCS, it then calculates the effective utility gain of the system brought by the candidate. and finally selects the one with the largest effective utility gain as the relay for the multi-hop D2D communication. Simulation results show that the proposed MARS algorithm can achieve better performance in terms of the overall system utility as compared with a random relay selection algorithm.