Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data manag...
详细信息
Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data management. The combination of Web3.0 and edge content caching holds promise in providing low-latency data access for CAVs’ real-time applications. Web3.0 enables the reliable pre-migration of frequently requested content from content providers to edge nodes. However, identifying optimal edge node peers for joint content caching and replacement remains challenging due to the dynamic nature of traffic flow in IoV. Addressing these challenges, this article introduces GAMA-Cache, an innovative edge content caching methodology leveraging Graph Attention Networks (GAT) and Multi-Agent Reinforcement Learning (MARL). GAMA-Cache conceptualizes the cooperative edge content caching issue as a constrained Markov decision process. It employs a MARL technique predicated on cooperation effectiveness to discern optimal caching decisions, with GAT augmenting information extracted from adjacent nodes. A distinct collaborator selection mechanism is also developed to streamline communication between agents, filtering out those with minimal correlations in the vector input to the policy network. Experimental results demonstrate that, in terms of service latency and delivery failure, the GAMA-Cache outperforms other state-of-the-art MARL solutions for edge content caching in IoV.
The rapid advancements in big data and the Internet of Things (IoT) have significantly accelerated the digital transformation of medical institutions, leading to the widespread adoption of Digital Twin Healthcare (DTH...
详细信息
The rapid advancements in big data and the Internet of Things (IoT) have significantly accelerated the digital transformation of medical institutions, leading to the widespread adoption of Digital Twin Healthcare (DTH). The Cloud DTH Platform (CDTH) serves as a cloud-based framework that integrates DTH models, healthcare resources, patient data, and medical services. By leveraging real-time data from medical devices, the CDTH platform enables intelligent healthcare services such as disease prediction and medical resource optimization. However, the platform functions as a system of systems (SoS), comprising interconnected yet independent healthcare services. This complexity is further compounded by the integration of both black-box AI models and domain-specific mechanistic models, which pose challenges in ensuring the interpretability and trustworthiness of DTH models. To address these challenges, we propose a Model-Based systemsengineering (MBSE)-driven DTH modeling methodology derived from systematic requirement and functional analyses. To implement this methodology effectively, we introduce a DTH model development approach using the X language, along with a comprehensive toolchain designed to streamline the development process. Together, this methodology and toolchain form a robust framework that enables engineers to efficiently develop interpretable and trustworthy DTH models for the CDTH platform. By integrating domain-specific mechanistic models with AI algorithms, the framework enhances model transparency and reliability. Finally, we validate our approach through a case study involving elderly patient care, demonstrating its effectiveness in supporting the development of DTH models that meet healthcare and interpretability requirements.
Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. ...
详细信息
Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. To address this issue, this paper proposes a novel approach to extracting vehicle velocity and acceleration, enabling the learning of vehicle dynamics and encoding them as auxiliary information. The VDI-LSTM model is designed, incorporating graph convolution and attention mechanisms to capture vehicle interactions using trajectory data and dynamic information. Specifically, a dynamics encoder is designed to capture the dynamic information, a dynamic graph is employed to represent vehicle interactions, and an attention mechanism is introduced to enhance the performance of LSTM and graph convolution. To demonstrate the effectiveness of our model, extensive experiments are conducted, including comparisons with several baselines and ablation studies on real-world highway datasets. Experimental results show that VDI-LSTM outperforms other baselines compared, which obtains a 3% improvement on the average RMSE indicator over the five prediction steps.
GECON - Grid Economics and Business Models Cloud computing is seen by many people as the natural evolution of Grid computing concepts. Both, for instance, rely on the use of service-based approaches for pro- sioning ...
详细信息
ISBN:
(数字)9783642038648
ISBN:
(纸本)9783642038631
GECON - Grid Economics and Business Models Cloud computing is seen by many people as the natural evolution of Grid computing concepts. Both, for instance, rely on the use of service-based approaches for pro- sioning compute and data resources. The importance of understanding business m- els and the economics of distributed computing systems and services has generally remained unchanged in the move to Cloud computing. This understanding is nec- sary in order to build sustainable e-infrastructure and businesses around this paradigm of sharing Cloud services. Currently, only a handful of companies have created s- cessful businesses around Cloud services. Among these, Amazon and Salesforce (with their offerings of Elastic Compute Cloud and force. com among other offerings) are the most prominent. Both companies understand how to charge for their services and how to enable commercial transactions on them. However, whether a wide-spread adoption of Cloud services will occur has to seen. One key enabler remains the ability to support suitable business models and charging schemes that appeal to users o- sourcing (part of) their internal business functions. The topics that have been addressed by the authors of accepted papers reflect the above-described situation and the need for a better understanding of Grid economics. The topics range from market mechanisms for trading computing resources, capacity planning, tools for modeling economic aspects of service-oriented systems, archit- tures for handling service level agreements, to models for economically efficient resource allocation.
This volume constitutes the refereed proceedings of the Confederated International Conferences: Cooperative Information systems, CoopIS 2014, and Ontologies, Databases, and Applications of Semantics, ODBASE 2014, held...
详细信息
ISBN:
(数字)9783662455630
ISBN:
(纸本)9783662455623
This volume constitutes the refereed proceedings of the Confederated International Conferences: Cooperative Information systems, CoopIS 2014, and Ontologies, Databases, and Applications of Semantics, ODBASE 2014, held as part of OTM 2014 in October 2014 in Amantea, Italy.
The 39 full papers presented together with 12 short papers and 5 keynotes were carefully reviewed and selected from a total of 115 submissions. The OTM program covers subjects as follows: process designing and modeling, process enactment, monitoring and quality assessment, managing similarity, software services, improving alignment, collaboration systems and applications, ontology querying methodologies and paradigms, ontology support for web, XML, and RDF data processing and retrieval, knowledge bases querying and retrieval, social network and collaborative methodologies, ontology-assisted event and stream processing, ontology-assisted warehousing approaches, ontology-based data representation, and management in emerging domains.
暂无评论