ABSTRACT Edge‐cloud computing offers an efficient method to flexibly allocate various computing resources for periodic workflow applications commonly employed in industrial production, commercial operations, and scientific research. Rationalized allocation of computational resources for scheduling in the edge‐cloud environment is the key to reducing energy consumption of the periodic workflows scheduling process. To this end, this paper proposes an optimization method for dynamic energy‐efficient scheduling of periodic workflows based on the collaboration of edge‐cloud computational resources while satisfying the constraints of workflow deadlines. In our method, periodic workflow scheduling is defined to be performed on a three‐tier integrated scheduling architecture of user terminals, edge computing platform, and cloud computing platform. Task groups are generated based on workflow critical paths, and appropriate edge‐cloud computing resources are selected for workflow tasks using corresponding scheduling policies at each scheduling stage. It reduces energy consumption during task scheduling while satisfying workflow deadline constraints. Comparative experiments in a simulated edge‐cloud environment show that our method reduces energy consumption of the scheduling process by 19.38%, 22.7%, and 37.34% compared to GA, PSO, and cloud computing, respectively. That is, the method effectively reduces the scheduling energy consumption during periodic workflow processing and significantly improves computational resource utilization.

For the task of unsupervised image translation, transforming the image style while preserving its original structure remains challenging. In this paper, we propose an unsupervised image translation method with structural enhancement in frequency domain named SEIT. Specifically, a frequency dynamic adaptive (FDA) module is designed for image style transformation that can well transfer the image style while maintaining its overall structure by decoupling the image content and style in frequency domain. Moreover, a wavelet-based structure enhancement (WSE) module is proposed to improve the intermediate translation results by matching the high-frequency information, thus enriching the structural details. Furthermore, a multi-scale network architecture is designed to extract the domain-specific information using image-independent encoders for both the source and target domains. The extensive experimental results well demonstrate the effectiveness of the proposed method.

The transformer model has gained a lot of success in various computer vision tasks owing to its capacity of modeling long-range dependencies. However, its application has been limited in the area of high-resolution unpaired image translation using GANs due to the quadratic complexity with the spatial resolution of input features. In this paper, we propose a novel transformer-based GAN for high-resolution unpaired image translation named Swin-UNIT. A two-stage generator is designed which consists of a global style translation (GST) module and a recurrent detail supplement (RDS) module. The GST module focuses on translating low-resolution global features using the ability of self-attention. The RDS module offers quick information propagation from the global features to the detail features at a high resolution using cross-attention. Moreover, we customize a dual-branch discriminator to guide the generator. Extensive experiments demonstrate that our model achieves state-of-the-art results on the unpaired image translation tasks.