By decoupling services and enabling elastic deployment, microservice architecture improves system scalability and evolutionary capability. At the same time, it substantially increases operational complexity. Failures often exhibit cross service propagation and a mismatch between observed symptoms and underlying root causes. To address the heterogeneity and fragmentation of multi source observability data such as logs, metrics, and distributed traces, this study proposes a unified modeling and intelligent root cause localization method for microservice systems. The approach treats each service as a basic modeling unit and maps heterogeneous observations into a shared representation space. Service dependency structure is explicitly incorporated to characterize system state at a global level. Through structure aware modeling on the dependency graph, anomaly information is propagated and constrained along real invocation relations. This design enables more accurate separation of local disturbances from structural anomalies. In addition, a consistency based measure derived from state deviation is constructed to score service anomalies. Dependency relations are then used for attribution and ranking, which unifies root cause localization and impact analysis within a single framework. Comparative results show that the proposed method achieves more stable and consistent advantages across multiple evaluation metrics. It captures anomaly propagation patterns in microservice systems more effectively and provides a unified and structure aware solution for intelligent diagnosis of complex distributed systems.

Deploying Large Language Models (LLMs) in cloud environments presents significant challenges due to their substantial memory footprint and computational requirements. While serverless architectures offer attractive pay-per-use economics, they suffer from prohibitively long cold start times when loading multi-gigabyte model weights into GPU memory. This paper presents FlashServe, a serverless LLMinference system that achieves fast cold starts through three key innovations: (1) a tiered memory snapshotting mechanism that pre-stages model checkpoints in host DRAM and leverages high-speed DMAtransfers via PCIe for rapid GPU memory loading, (2) a hybrid Prophet-LSTM prediction model for proactive pod pre-warming based on request arrival patterns, and (3) efficient LoRA adapter multiplexing that enables serving multiple fine-tuned models on shared GPU resources. Extensive experiments on the Azure Functions trace dataset demonstrate that FlashServe reduces cold start latency by up to 49× compared to baseline S3-based loading approaches and by 3.3× compared to state-of-the-art systems like ServerlessLLM. Under realistic bursty workloads, FlashServe achieves 32% reduction in GPU idle costs while maintaining sub-second time-to-first-token (TTFT) latency for 95%of requests. These results demonstrate that FlashServe represents meaningful progress toward practical serverless LLM deployment.

Identifying abnormal behaviors plays a vital role in ensuring cloud infrastructure remains secure and operationally stable. Conventional methods that aggregate data at a single location create substantial privacy concerns, especially within shared cloud platforms hosting multiple organizations with confidential operational information. This paper proposes HierFedDP, a hierarchical federated learning framework integrated with a two-stage differential privacy mechanism for privacy-preserving anomaly detection in cloud services. Our approach employs a three-tier architecture consisting of local clients, edge servers, and a central cloud server, where clients apply local differential privacy to their updates before transmission. We introduce an edge aggregation frequency parameter that enables edge servers to perform multiple local aggregation rounds before communicating with the central cloud. Experiments on the CICIDS2017 dataset demonstrate that HierFedDP achieves detection performance comparable to standard local differential privacy approaches while reducing wide-area network (WAN) communication overhead by 49%. This significant communication reduction, achieved without sacrificing privacy guarantees or detection accuracy, makes HierFedDP particularly suitable for bandwidth-constrained, geo-distributed cloud deployments.

Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing ranking methods in RAG pipelines primarily optimize for document-query relevance, neglecting crucial factors for generation quality such as factual consistency and information coverage. We propose a novel multiobjective ranking framework that explicitly models three critical dimensions: relevance, coverage, and faithfulness support. Unlike traditional IR-centric approaches, our method introduces a utilitybased scoring mechanism that evaluates each document’s contribution to reducing hallucinations, improving answer completeness, and maintaining relevance. We formulate the ranking problem as a multi-objective optimization task and employ listwise learning with carefully constructed utility labels derived from existing QA datasets. Extensive experiments on Natural Questions, TriviaQA, and HotpotQA demonstrate that our approach achieves substantial improvements over state-of-the-art baselines, with an average 4.8- point increase (8.6% relative improvement) in Exact Match scores, 10.1% improvement in faithfulness metrics, and 35.7% reduction in hallucination rates compared to RankRAG, all while maintaining computational efficiency comparable to traditional reranking methods.

This study addresses the challenge of forecasting backend service metrics in highly dynamic and disturbed environments and proposes a robust time series prediction framework based on uncertainty estimation. The method first applies a multi-scale encoding structure to decompose and represent service metric sequences, allowing the model to capture mixed characteristics of trends, periodic patterns, and noise disturbances. It then constructs a cross-sequence dependency modeling module to describe structural coupling among multiple metrics so that the model can identify implicit interaction patterns across different service nodes in backend systems. On this basis, the framework outputs both the mean and variance of future metrics through distributed prediction heads, enabling joint characterization of predictions and their associated risk ranges. A noise response mechanism is incorporated to enhance model stability under anomalous disturbances. To improve the controllability of the overall prediction process, a risk adjustment module is designed to transform uncertainty signals into actionable adjustment factors, allowing the model to maintain consistent outputs in high volatility environments. The experiments evaluate hyperparameter sensitivity, environmental sensitivity, and data sensitivity. The results show that the proposed framework maintains high stability and robustness under multiple source disturbances and effectively suppresses error propagation caused by anomalous samples, structural changes, and system scaling. By jointly modeling point predictions and risk estimation, the study verifies the effectiveness of an uncertainty-driven robust forecasting framework for backend metric management and system reliability, providing a scalable technical path for data-driven analysis in complex systems.