Computer-aided design (CAD) significantly enhances the efficiency, accuracy, and innovation of design processes by enabling precise 2D and 3D modeling, extensive analysis, and optimization. Existing methods for creating CAD models rely on latent vectors or point clouds, which are difficult to obtain, and storage costs are substantial. Recent advances in Multimodal Large Language Models (MLLMs) have inspired researchers to use natural language instructions and images for CAD model construction. However, these models still struggle with inferring accurate 3D spatial location and orientation, leading to inaccuracies in determining the spatial 3D starting points and extrusion directions for constructing geometries. This work introduces CAD-GPT, a CAD synthesis method with spatial reasoning-enhanced MLLM that takes either a single image or a textual description as input. To achieve precise spatial inference, our approach introduces a 3D Modeling Spatial Mechanism. This method maps 3D spatial positions and 3D sketch plane rotation angles into a 1D linguistic feature space using a specialized spatial unfolding mechanism, while discretizing 2D sketch coordinates into an appropriate planar space to enable precise determination of spatial starting position, sketch orientation, and 2D sketch coordinate translations. Extensive experiments demonstrate that CAD-GPT consistently outperforms existing state-of-the-art methods in CAD model synthesis, both quantitatively and qualitatively.

Time-Sensitive Networking (TSN) has emerged as a vital networking paradigm for timely and reliable data transmission. Recently, researchers are increasingly focusing on the scalability of algorithms for scheduling problems over diverse network topologies and flows based on deep reinforcement learning methods (DRL). However, the lack of reasonable characterization of flow conflicts and dependencies leads to limited generalization and schedulability under the discrepancies in characteristics and number of flows. To address those issues, we propose a data-driven scheduling method guided by flow sequence conflict theory, which improves generalization and schedulability over different flow characteristics and topologies. Specifically, we design a network feature encoding scheme to formulate a reasonable characterization of flow conflicts by integrating a graph-based flow sequence representation model with graph attention networks (GATs). Regarding the abovementioned characterization as the acknowledge embedding, a data-driven method is designed to learn two sub-policies in the scheduling process, including flow selection and solution searching for each selected flow. Within the scheduling process, a multi-head attention-based neural network is designed to generate the scheduling sequence of variable length, which characterizes the dependencies between flows with different numbers. Simulation results demonstrate that compared to existing DRL-based methods, the runtime of scheduling at scale is increased by at least 100 % in complex traffic scenarios while the slot utilization on the links is also improved compared to other methods.

Existing performance analyses and transmission policy designs under Time-Sensitive Networking (TSN) typically assume that all data flows are periodic and deterministic. However, in real-world scenarios, various sources of uncertainty - such as device failures, environmental variations, or upstream congestion - can lead to unexpected packet arrivals or losses, introducing non-deterministic behaviors into the network. This work develops a stochastic model based on Markov Decision Process (MDP) to capture the dynamics of TSN switch transmission under such conditions. To address the inefficiency caused by stale packets blocking fresher and more valuable ones, we propose a stale packet skipping policy to enhance the transmission efficiency. Specifically, a stale packet is discarded if a newer packet of the same flow is injected into the queue or if its deadline can no longer be met. This paper presents a detailed model description of the stochastic packet behaviors, the transmission system, and the stale packet skipping policy.

As an emerging communication technology, time-sensitive networking (TSN) holds the potential to enable real-time and deterministic interactions for streams within the Industrial Internet of Things. However, effectively and promptly scheduling large-scale streams in the TSN network poses a significant challenge due to high computational complexity. In this article, we conduct a schedulability analysis to preprocess the stream set with given routing paths, avoiding invalid searches and providing optimized guidance for stream routing. To accelerate the feasibility validation of potential solutions, an efficient stream conflict detection approach is proposed leveraging stream grouping with correlation analysis to compress the detection space. Integrating the above preprocess and efficient conflict detection, we develop a scalable scheduling algorithm with an incremental schedule synthesis to enhance scalability while ensuring low slot occupancy for all links. Evaluation results demonstrate that the proposed algorithm significantly reduces synthesis time and achieves low slot occupancy of all links compared to existing scheduling methods.

Industrial time-sensitive networking (TSN) is pivotal for ensuring real-time and reliable flow transmission. There is a growing focus on its scalable scheduling for time-critical flows pursuing ultralow latency and jitter. Its time-aware shaper protocol tackles uncertain delay and frame loss but introduces high scheduling complexity. However, existing works lack a scheduling feature mining mechanism. They impose unnecessarily tight rules to simplify the problem but sacrifice scheduling optimality. To address this, especially in industrial networks with large-scale complex flows, we propose a flow-overlap graph based distributed scheme to improve scheduling scalability concerning schedulability, scheduling efficiency, and latency and jitter. The distributed framework is established with the pipeline-parallelism pattern and verified superior in scalability. It first incorporates the deterministic feature into the distributed TSN configuration standard. Under this, specific scheduling is refined by building a so-called flow-overlap graph that efficiently characterizes flow-based scheduling features and further designing a hierarchical scheduling algorithm GFD. This scheme Pareto dominates the three scalability criteria theoretically and simulatively.

With the rapid development of Industrial Internet of Things (IIoT), time-sensitive networking (TSN) with deterministic and real-time features has gained broad interest. However, most existing research focuses on the network scheduling with fixed task placement and computing resource allocation, restricting the scheduling space of coupled task-network. To tackle this coupling problem, an efficient task-network scheduling (ETNS) scheme is proposed in this article for TSN. A task-conflict metric (TCM) is established to quantify the competition degree of scheduling resources. For increasing the overall scheduling space, a TCM-aware prescheduling method is proposed by optimizing task placement and routing paths to reduce the potential conflicts between tasks. Integrated with the prescheduling method, we design a TCM-aware parallel group-scheduling algorithm by reducing the conflicts between task groups to enhance schedulability and scalability. Experiments show that our ETNS scheme significantly improves the schedulability and scalability performances compared with the existing scheduling approaches. The larger the number of tasks, the higher the performance improvement.

Industrial Time-Sensitive Networking (TSN) provides deterministic mechanisms for real-time and reliable flow transmission. Increasing attention has been paid to efficient scheduling for time-sensitive flows with stringent requirements such as ultra-low latency and jitter. In TSN, the fine-grained traffic shaping protocol, cyclic queuing and forwarding (CQF), eliminates uncertain delay and frame loss via traffic timing in and out of queues. However, it inevitably causes high scheduling complexity. Moreover, complexity is quite sensitive to flow attributes and network scale. The problem stems in part from the lack of an attribute mining mechanism in existing frame-based scheduling. For time-critical industrial networks with large-scale complex flows, a so-called hyper-flow graph based scheduling scheme is proposed to improve the scheduling scalability in terms of schedulability, scheduling efficiency and latency & jitter. The hyper-flow graph is built by aggregating similar flow sets as hyper-flow nodes and designing a hierarchical scheduling framework. The flow attribute-sensitive scheduling information is embedded into the condensed maximal cliques, and reverse maps them precisely to congestion flow portions for re-scheduling. Its parallel scheduling reduces network scale induced complexity. Further, this scheme is designed in its entirety as a comprehensive scheduling algorithm GH2. It improves the three criteria of scalability along a Pareto front. Extensive simulation studies demonstrate its superiority. Notably, GH2 is verified its scheduling stability with a runtime of less than 100 ms for 1000 flows and near 1/190 of the SOTA FITS method for 3000 flows.

The development of the Industrial Internet of Things (1IoT) has given rise to massive information from the networked controllers, sensors and actuators, leading to the increasing demands for real-time and reliable transmission. Time-Sensitive Networking (TSN) provides the deterministic mechanism guar-antee for these demands, but with an open scheduling problem. For the low-latency and low-jitter traffic, it is hard to schedule in a scalable way, that is, increasing the scheduling speed under the Quality-of-Service (QoS) requirements. Therefore, this paper constructs a no-wait forwarding (NW-TAS) model with a time-aware shaper to eliminate the queuing delay and jitter, and further converts it into a flow-aware model by divisibility theory for scheduling simplification. With the converted model, an interval transformation-based method is proposed to get the analytical expression of feasible scheduling for each flow. Then, a flow-aware NW- TAS scheduling algorithm (FANS) with cyclic interval searching is designed to compress invalid search spaces. The evaluation results show that our method decreases the transmission latency of 1000 flows by more than 23 % while increasing the scheduling speed by 43x than the existing works.

As the global industrial upgrading requires higher reliability and real-time performance of data communication, Time-sensitive Networking (TSN) has been widely studied. Al-though many TSN scheduling algorithms are designed, there is no standardized analysis report after scheduling and comprehensive scheduling performance evaluation. This paper presents a complete automatic report generation system to analyze the scheduling performance. To standardize various data in TSN-based manufacturing, a uniform auto-generated report model is defined based on the Open Platform Communication Unified Architecture (OPC UA). A learning-based performance evaluation (LPE) method is established to comprehensively analyze the performance of TSN scheduling. In LPE, analytical hierarchy process (AHP) and entropy weight method (EWM) is adopted to optimize the weight distribution of performance indexes objectively, and convolutional neural network (CNN) is used to get the final evaluation result rapidly. Compared with the previous evaluation methods, simulations show the training time of the evaluation method is significantly reduced.

The deterministic and real-time communication is the indispensable requirement in Industrial Internet of Things (IIoT) application areas. Time-sensitive networking (TSN) is a promising technology for this kind of communication demands through designing proper scheduling and routing mechanisms. However, it is still challenging to design the mechanisms for large-scale instances due to high computational complexity. In order to guarantee schedulability and scalability, a learning-based scalable scheduling and routing co-design (LSSR) architecture is proposed in this article for TSN. A stream partition method combining classification and graph-based clustering is established to reduce interpartition conflicts to enhance schedulability based on the explored domain knowledge and the characterized stream data set for practical requirements. Integrated with the stream partition method, we construct the constraints of scheduling and routing co-design to guarantee the deterministic and real-time transmission. An iterative scheduling algorithm is proposed to reduce the computational complexity and thus, to enhance scalability. Simulations demonstrate the effectiveness and advantages of the proposed LSSR scheme.

As an emerging communication technology, time-sensitive networking (TSN) promises the real time and deterministic interaction of massive data in Industrial Internet of Things. However, it is challenging to schedule the time-sensitive flows timely and superiorly through the mechanism analysis for current TSN scheduling models, especially in complex industrial scenarios. In this article, we propose an analysis approach of flow sequences based on divisibility theory to characterize the flow conflicts and dependencies, which derives the scheduling flexibility based on flow position diversity (PD) and the equivalent flow judgment conditions for slot occupancy. Integrating the abovementioned derivation, a parallel computing framework with the generalized slot length is established to lower the scheduling complexity. Within each computing unit, an incremental scheduling algorithm with the flow judgment conditions and PD-based search boundary is proposed. It reduces the scheduling complexity further while maintaining load balance for the mixed transmission of periodic and aperiodic flows. To achieve the optimality of runtime and load balance, two PD-based flow sorting strategies are designed, respectively. The evaluation results show that compared with the existing works, the runtime efficiency of scheduling at scale is increased by at least 1500 times in complex traffic scenarios while the load balance on the network links is also improved.

Time-Sensitive Networking (TSN) is a series of standards designed to enhance reliable and real-time transmission. Switching architecture is the essential component in TSN switches to guarantee the different quality of service (QoS) requirements. However, most existing TSN switching architectures are based on the fixed queue scheduling such as Input Queue or Output Queue, which leads to complex schedule processes and inefficient memory utilization. Therefore, a flexible and efficient switching architecture is needed in terms of heterogeneous traffics requirements. This paper proposes a Virtual-Queue Switching (VQS) architecture with Parallel Shared Memory (PSM) for TSN switches. First, we develop a virtual queue scheduler using the queue ID and the flow rank. By configuring the queue ID and the flow rank, the VQS architecture supports multiple scheduling strategies. Second, parallel shared memory (PSM) management is designed to ensure that storage of TS flows takes precedence over other flows. All kinds of flows share storage resources in PSM, which improves memory utilization. At last, a scheduling algorithm for IEEE 802.1Qbv based on VQS architecture is designed. Compared From the comparison results with the previous switching