Due to the increasing concerns about environmental and economic issues of traditional ships, all-electric ships with energy storage renewable integration have become more appealing for forthcoming future. In this paper, an optimal system (ESS) capacity determination method a marine ferry ship is proposed; has diesel generators PV panels. ESSs sizing optimization power scheduling are simultaneously conducted it converted mixed-integer quadratic programming (MIQP) model special modeling...

In this paper, a graph neural network anomaly detection framework is proposed to improve the safety of linear induction motors, key component high-speed maglev trains. our framework, each sensor sequence treated as separate feature. The similarity and correlation between multi-dimensional features are learned prior knowledge for structure learning. spatial-temporal attention incorporates learn complex correlations nodes. Furthermore, optimises joint model detection, avoiding trap falling...

I2C module is one of the most vital components in lots chips. A flexible hardware architecture for slave device protocol designed this paper. The divided into two levels: level and application level. implements basic operations protocol, level, which bases on aiming to demand various applications. When complete implementation simulation architecture, a verification platform built verify performance architecture.

With the complexity and refinement of industrial systems, fast fault diagnosis is crucial to ensuring stable operation equipment. The main limitation current methods lack real-time performance in resource-constrained embedded systems. Rapid online detection can help deal with equipment failures time prevent damage. Inspired by ideas compressed sensing (CS) deep extreme learning machines (DELM), a data-driven general method proposed for diagnosis. contains two modules: data sampling module...

This paper presents an in-depth measurement study of in-memory key-value systems. We examine data placement and processing techniques, including structures, caching, performance read/write operations, effects different structures on throughput big workloads. Based the analysis our results, we attempt to answer a number challenging yet most frequently asked questions regarding systems, such as how do systems respond workloads, which exceeds capacity physical memory or pre-configured size...

When a fault occurs, driven by the reconfiguration strategy, topology of ship power system (SPS) will be changed to isolate area and restore lost load. However, traditional optimization methods have limitations, such as getting stuck in suboptimal solutions or not offering real-time solutions. This paper proposes novel deep reinforcement learning (DRL) method address dynamic problem for SPS. While considering load priorities, model is formulated with goal maximum weighted minimum switching...

As more and individuals have multiple computing devices, how to maintain the consistency of user files stored on devices becomes a challenge. Cloud-based file synchronization services (FSS), e.g., Drop box iFolder, are promising approaches. However, we haven't seen any public documents discussing protocol, which plays vital role in FSS. This paper focuses maintaining We define new abstraction layer called view, describes all their metadata sync-folder. propose view based protocol with...

Many popular web service networks are content-rich in terms of heterogeneous types entities and links, associated with incomplete attributes. Clustering such demands new clustering techniques that can handle two heterogeneity challenges: (1) multiple co-exist the same network attributes, (2) links between have diverse carry different semantics. Existing graph tend to pick initial centroids uniformly at random, specify number k clusters advance, fix during process. In this paper, we propose...

NoSQL (Not only SQL) data stores become a vital component in many big computing platforms due to its inherent horizontal scalability. HBase is an open-source distributed store that widely used by Internet enterprises handle their applications (e.g. Facebook h

NoSQL systems have become the vital components to deliver big data services in Cloud. However, existing rely on experienced administrators configure and tune wide range of configurable parameters order achieve high performance. In this paper, we present a policy-driven configuration management system for systems, called PCM. PCM can identify workload sensitive capture tuned different workloads as policies. also be used analyze that may impact runtime performance terms read write workloads....

NoSQL systems are deployed as the core components for delivering big data Web services today. With growing main memory capacity, we witness interest and deployment of in-memory (IM-NoSQL), which designed to maximize utilization DRAM ultra low latency services. To address volatility computing services, persistence failure recovery important functionality IM-NoSQL. In this paper report an extensive measurement study on performance We evaluate effectiveness several common mechanisms used in...

The new generation ship integrated power system (IPS) realizes high level informatization for various physical equipments, and gradually develops to a cyber-physical (CPS). future trend is collecting big data achieve data-driven intelligence IPS. However, traditional relational management framework becomes inefficient handle the real-time processing in cyber-physics system. In order process large-scale that collected from numerous sensors by field bus of IPS devices within acceptable...

NoSQL systems have become vital components to deliver big data services due their high horizontal scalability.However, existing rely on experienced administrators configure and tune the wide range of configurable parameters for optimized performance.In this work, we present a configuration management framework systems, called xConfig.With xConfig, its users can first identify performance sensitive capture tuned different workloads as policies.Next, based policies, xConfig be implemented...

While high‐speed maglev trains offer convenient travel options, they also pose challenging issues for fault detection and early warning in critical components. This study proposes a Temporal‐Knowledge fusion Spatiotemporal Graph Convolutional Network (TK‐STGCN) of faults the traction control system (TCS). Compared with existing literature that leverages spatiotemporal characteristics big data feature discovery, TK‐STGCN focuses on integrating prior knowledge to capture correlations between...