With the increasing adoption of IIoT in industrial production producing massive heterogeneous data, Retrieval-Augmented Generation (RAG) has become a promising approach for industrial knowledge-based Question Answering (QA). However, retrieved top-k documents often contain distracting content that degrades the quality of the generation. Existing research focuses on optimizing retrieval and reranking while overlooking semantic enrichment of useful information and targeted handling of distractions. To address this issue, we propose CP-RAG (Categorize and Process RAG), which categorizes retrieved documents using attention scores and processes them with tailored strategies to mitigate distracting content. Direct-assist documents, which contain concentrated useful information, are enhanced via multi-level semantic optimization to enhance information density. Indirect-assist documents, which carry contextual but distracting elements, are processed through rearrangement with noise mixing to mitigate interference. To maximize LLMs utility, direct-assist documents are placed at both ends of the context window, while indirect-assist documents are positioned centrally. Experimental results show that CP-RAG improves QA accuracy and demonstrates strong practical effectiveness in industrial systems, supporting intelligent decision making over heterogeneous industrial data streams.

With the increasing on-board demand for intelligent connected vehicles (ICVs), the fifth-generation (5G) wireless systems are being massively utilized in vehicular networks. As an essential component, content retrieval in the ICV provides a basis for vehicle-to-vehicle or vehicle-to-infrastructure data interaction for many applications. However, content access is still subject to performance degradation due to congested communication channels, diverse requests patterns, and intermittent network connectivity. To mitigate these issues, in-network caching in 5G-enabled ICV has been leveraged to benefit content access by allowing edge nodes to store content for data generators. In this paper, we propose an in-network caching scheme to support various provisions of data sharing in the ICVs by exploring the advantages of information-centric networks (ICN). We first divide each on-board service into several content units. Then, we place these units at the ICV and small cell base stations (SBSs) to reduce the content retrieval delay, further model the proposed system as an integer nonlinear program (INLP) and attain the optimal QoE (Quality of Experience) by placing content units at appropriate cache entities. Finally, we verify the effectiveness and correctness of our proposed model through extensive simulations.

In recent years, vehicular named data networking (VNDN) has quickly ascended to the spotlight and gained enormous popularity, which has emerged as a candidate to support various applications of vehicular communications. VNDN has the potential improve the data dissemination efficiency by mitigating the performance degradation from Internet Protocol (IP) addressing, unstable connectivity and diversified service requirements. With the number of connected vehicles increasing rapidly, the traffic burden of the base station (BS) also grows. As an effective edge computing paradigm, in-vehicle caching can significantly relieve the pressure of the BS. However, the design of a fair caching strategy is still challenging due to the selfish nature of individuals. In this paper, to address the above issues, a popularity-incentive caching scheme (PICS) is proposed in VNDN, where the BS will reward vehicles who execute cache offloading and content sharing with others. To balance the conflict of interest between the BS and vehicles, a Stackelberg game is modeled with rational utilities envisioned. Next, we propose the solution of this game model and evaluate the influence of different weight parameters. Finally, simulation results validate the effectiveness of PICS.

Internet of Vehicles (IoV) have been attracting increasing interests in recent years, targeting to support services between vehicles or vehicles and infrastructures involving driving safety, traffic and infotainment. However, the dynamic nature of IoV make it quite challenging by applying traditional TCP/IP protocol stack, considering the complex signaling and addressing procedure of TCP/IP as well as the strict End-to-End service requirements in vehicular environment. To address these issues, an information centric data dissemination scheme (IDDS) in IoV is proposed. At first, the framework of our IDDS is introduced with the PDU (Protocol Data Unit) type, data structure and protocol signaling procedure given. After that, to increase the data delivery ratio and reduce the incurred latency, a defer time based forwarder selection scheme is presented, with which the “Interest” and “Reply” packets could be exchanged on the link with better transmission performance, thus mitigating the negative impact of high mobility of vehicles. Simulation results show that IDDS could outperforms some traditional strategies in terms of average hop count and content acquisition delay, thus significantly increasing the data dissemination efficiency in vehicular information-centric networks.

With the increasing demand for high speed and low latency services on the Internet of Vehicles, researches on wireless networks in intelligent connected vehicles (ICVs) with communication and caching capability have attracted much attention. Content retrieving in ICVs is subject to performance degradation as a result of channel fading and intermittent network connectivity. The emerging fifth-generation (5G) networks are promising in supporting the needs of data transmission and alleviating the communication problems in ICVs. Specifically, to improve the users' quality of experience (QoE) and reduce the access delay of content retrieval, it helps to leverage in-network caching in on-board units and small cell base stations (SBSs). In this paper, we propose a cooperative caching scheme based on content popularity and transmission power restriction for inhomogeneous ICV, which pre-caches content files at SBSs to significantly reduce content retrieval delay. In specific, we model the proposed system as a cache management problem and attain optimal QoE by allocating proper transmission power for each content file. Using extensive simulations, we demonstrate that the proposed solution can effectively provide service for ICVs with high QoE in different scenarios.

Vehicular named data networking (VNDN) has recently emerged as a novel paradigm to facilitate content-centric data sharing for Internet of Vehicles. However, an information holder can spread fake data to clients for malicious purposes, which may affect the driving decision of the recipient, or even worse, cause traffic congestion and accidents. In this article, we build a data-sharing system that consists of a double-layer blockchain. The nodes at the bottom layer request for service by announcing their requirements in the NDN paradigm. For the upper layer, the nodes submit their demands and supplies to the nearest roadside unit for further matching. We model the balance between the demand and supply as a matching game. To encourage nodes to provide positive services, a reputation management mechanism that combines negative and positive transaction records is proposed. Simulation results verify the validity of our system, and the data-sharing mechanism fosters a secure information interaction in the VNDN.

Driving safety has been a hot topic in recent vehicular research. However, research on active control strategy, by which an accident might be avoided before it really happens, is still lacking, especially those appealing to machine learning methods with real traffic data. In addition, previous works constructed models with only one or a few factors considered, while the impact of multiple factors on a collision probability is overlooked. In this paper, based on machine learning methods with an actual traffic dataset, we propose a multi-level active safety control strategy taking the Multi-source, Multi-parameter, and Multi-purpose (3M) properties of an accident into consideration. First, by analyzing the impact of different conditions on an accident with the AHP (Analytic Hierarchy Process)-Ridge regression and bisecting K-means clustering model, the safety inter-vehicle distance is derived by learning from an actual traffic dataset. Besides, ELM(Extreme Learning Machines) is adopted as a verification scheme for safety distance calculation. Subsequently, we design a three-level active safety control scheme using the LQG (Linear Quadratic Gaussian) optimal-control model based on the obtained safety inter-vehicle distance. Numerical results show that by comparing with some classical braking and car-following models, our strategy can always keep the distance of two followed vehicles at a safety state. To further explore the impact of the time complexity on the rear-end collisions, we also implemented a road-test and verified that our model can timely respond to the risks and keep two cars always in safety.