Search

Driven by the rise of intelligent manufacturing and Industry 4.0, the manufacturing industry faces significant challenges in adapting to flexible and efficient production methods. This study presents an innovative approach to solving the Flexible Job-Shop Scheduling Problem (FJSP) by integrating Heterogeneous Graph Neural Networks based on Relation (HGNNR) with Deep Reinforcement Learning (DRL). The proposed framework models the complex relationships in FJSP using heterogeneous graphs, where operations and machines are represented as nodes, with directed and undirected arcs indicating dependencies and compatibilities. The HGNNR framework comprises four key components: relation-specific subgraph decomposition, data preprocessing, feature extraction through graph convolution, and cross-relation feature fusion using a multi-head attention mechanism. For decision-making, we employ the Proximal Policy Optimization (PPO) algorithm, which iteratively updates policies to maximize cumulative rewards through continuous interaction with the environment. Experimental results on four public benchmark datasets demonstrate that our proposed method outperforms four state-of-the-art DRL-based techniques and three common rule-based heuristic algorithms, achieving superior scheduling efficiency and generalization capabilities. This framework offers a robust and scalable solution for complex industrial scheduling problems, enhancing production efficiency and adaptability. [ABSTRACT FROM AUTHOR]

Traffic flow forecasting is an essential task of an intelligent transportation system (ITS), closely related to intelligent transportation management and resource scheduling. Dynamic spatial-temporal dependencies in traffic data make traffic flow forecasting to be a challenging task. Most existing research cannot model dynamic spatial and temporal correlations to achieve well-forecasting performance. The multi-head self-attention mechanism is a valuable method to capture dynamic spatial-temporal correlations, and combining it with graph convolutional networks is a promising solution. Therefore, we propose a multi-head self-attention spatiotemporal graph convolutional network (MSASGCN) model. It can effectively capture local correlations and potential global correlations of spatial structures, can handle dynamic evolution of the road network, and, in the time dimension, can effectively capture dynamic temporal correlations. Experiments on two real datasets verify the stability of our proposed model, obtaining a better prediction performance than the baseline algorithms. The correlation metrics get significantly reduced compared with traditional time series prediction methods and deep learning methods without using graph neural networks, according to MAE and RMSE results. Compared with advanced traffic flow forecasting methods, our model also has a performance improvement and a more stable prediction performance. We also discuss some problems and challenges in traffic forecasting., Author(s): Yang Cao [1]; Detian Liu [1]; Qizheng Yin [1]; Fei Xue [1]; Hengliang Tang (corresponding author) [1] 1. Introduction With the development of society and accelerated urbanization, the demand [...]

Artificial Intelligence of Things (AIoT) is a new research area in AI and IoT. For the massive data and connections at the edge of AIoT, how to schedule the resource load is a key problem to be solved. For the multi‐objective resource scheduling problem in a cross‐domain environment, this article proposes a resource scheduling method based on edge computing and multi‐objective algorithms. First, a cloud‐edge hybrid AIoT hierarchical network resource management architecture is constructed. Then, the resource scheduling problem is modeled and a linear weighting strategy is designed for search space "pruning", which is then optimized by three multi‐objective algorithms. Finally, we conducted a series of experiments based on the iFogSim platform. The simulation results show that the proposed resource scheduling strategy can effectively reduce the processing delay of AIoT and effectively improve the energy utilization efficiency of devices in the network. [ABSTRACT FROM AUTHOR]