With the rapid development of cloud computing and container technology, more and more applications are deployed to the cloud, and the scale of cloud platform is expanding. Due to the large number of container instances running in the platform, complex dependency relationship, fast version iteration and other characteristics, the update of business can often cause the change of the whole cloud resource environment, which triggers the repetitive scheduling problem of related tasks and affects stability of the business. In this paper, we propose a self-adapting task scheduling algorithm (ADATSA) using learning automata to solve these problems. Firstly, we design a learning automata model and objective function for the system on task scheduling problem. Then, we realize an effective reward-penalty mechanism for scheduling actions in combination with the idle state of resources and the running state of tasks in the current environment. Meanwhile, the environment is modeled by cluster, node and task, and the probability of action selected is optimized by scheduling execution, thus enhancing the adaptability to the cloud environment of the scheduling and accelerating convergence. Finally, we construct a framework of task load monitoring with buffer queue to achieve dynamic scheduling based on priority. The experimental part verifies the effectiveness of proposed algorithm with different angles such as resource imbalance degree, resource residual degree and QoS. Compared with other learning automata scheduling models such as LAEAS, non-automata technology based algorithms such as PSOS and K8S scheduling engine, ADATSA shows the better performance of environment adaptability, resource optimization efficiency and QoS in dynamic scheduling. The theoretical analysis was consistent with the experimental results.

Optical satellites are the most popular observation platforms for humans viewing Earth. Driven by rapidly developing multi-source optical remote sensing technology, content-based remote sensing image retrieval (CBRSIR), which aims to retrieve images of interest using extracted visual features, faces new challenges derived from large data volumes, complex feature information and various spatio-temporal resolutions. Most previous works delve into optical image representation and transformation to the semantic space of retrieval via supervised or unsupervised learning. These retrieval methods fail to fully leverage geospatial information, especially spatio-temporal features, which can improve the accuracy and efficiency to some extent. In this article, we propose a cross-modal contrastive learning method (CCLS2T) to maximize the mutual information of multi-source remote sensing platforms for correlation-aware retrieval. Specifically, we develop an asymmetric dual-encoder architecture with a vision encoder that operates on multi-scale visual inputs, and a lightweight text encoder that reconstructs spatio-temporal embeddings and adopts an intermediate contrastive objective on representations from unimodal encoders. Then, we add a hash layer to transform the deep fusion features into compact hash index codes. Additionally, CCLS2T exploits the prompt template (R2STFT) for multi-source remote sensing retrieval to address the text heterogeneity of metadata files and the hierarchical semantic tree (RSHST) to address the feature sparsification of semantic-aware indexing structures. The experimental results on three optical remote sensing datasets substantiate that the proposed CCLS2T can improve retrieval performance by 11.64% and 9.91% compared with many existing hash learning methods and server-side retrieval engines, respectively, in typical optical remote sensing retrieval scenarios.

With the development and popularization of remote sensing earth observation technology and the remote sensing satellite system, the problems of insufficient proactiveness, relevance and timeliness of large-scale remote sensing supporting services are increasingly prominent, which seriously restricts the application of remote sensing resources in multi-domain and cross-disciplinary. It is urgent to help terminal users make appropriate decisions according to real-time network environment and domain requirements, and obtain the optimal resources efficiently from the massive remote sensing resources. In this paper, we propose a recommendation algorithm using fusion of attention and multi-perspective (MRS_AMRA). Based on MRS_AMRA, we further implement an active service recommendation model (MRS_ASRM) for massive multi-source remote sensing resources by combining streaming pushing technology. Firstly, we construct value evaluation functions from multi-perspective in terms of remote sensing users, data and services to enable the adaptive provision of remote sensing resources. Then, we define multi-perspective heuristic policies to support resource discovery, and fusion these policies through the attention network, to achieve the accurate pushing of remote sensing resources. Finally, we implement comparative experiments to simulate accurate recommendation scenarios, compared with state-of-the-art algorithms, such as DIN and Geoportal. Furthermore, MRS_AMRA achieves an average improvement of 10.5% in the recommendation accuracy NDCG@K, and in addition, we developed a prototype system to verify the effectiveness and timeliness of MRS_ASRM.

Container-based task scheduling is critical for ensuring a reliable, flexible and cost-effective cloud computing mode. However, in different business cloud systems, state-of-theart scheduling models are not as effective as those in the simulated world due to the sparsity issues associated with sample sizes and features. Herein, we propose a novel containerized task scheduling framework (SA2CTS) based on reinforcement learning (RL) that incorporates cross-modal contrastive learning (CL) loss. This framework optimizes the scheduler's understanding of the container-based cloud state in RL by adding a pretraining stage, promoting accurate scheduling action inference. Specifically, we design a two-stage learning pipeline. The initial stage involves pretraining the model on a large collection of aligned image-text pairs to extract fine-grained scheduling affinity features, and the high-level semantic representations of scheduling tasks are learned in the multimodal space. In the second stage, we fine-tune the pretrained model with multisource cluster feedback, i.e., build a mapping from state representations to scheduling actions through the RL paradigm, achieving task-oriented and semanticaware scheduling. The experimental results obtained on three large-scale production cluster datasets substantiate that the proposed SA2CTS method can provide average convergence efficiency and resource utilization improvements of 17.57% and 10.42%, respectively, over the state-of-the-art RL scheduling methods.