Large-scale terminals’ various QoS requirements are key challenges confronting the resource allocation of Satellite Internet of Things (S-IoT). This paper presents a deep reinforcement learning-based online channel allocation and power control algorithm in an S-IoT uplink scenario. The intelligent agent determines the transmission channel and power simultaneously based on contextual information. Furthermore, the weighted normalized reward concerning success rate, power efficiency, and QoS requirement is adopted to balance the performance between increasing resource efficiency and meeting QoS requirements. Finally, a practical deployment mechanism based on transfer learning is proposed to promote onboard training efficiency and to reduce computation consumption of the training process. The simulation demonstrates that the proposed method can balance the success rate and power efficiency with QoS requirement guaranteed. For S-IoT’s normal operation condition, the proposed method can improve the power efficiency by 60.91% and 144.44% compared with GA and DRL_RA, while its power efficiency is only 4.55% lower than that of DRL-EERA. In addition, this method can be transferred and deployed to a space environment by merely 100 onboard training steps.

As one of the most popular intelligent optimization algorithms, Simulated Annealing (SA) faces two key problems, the generation of perturbation solutions and the control strategy of the outer loop (cooling schedule). In this paper, we introduce the Gaussian Cloud model to solve both problems and propose a novel cloud annealing algorithm. Its basic idea is to use the Gaussian Cloud model with decreasing numerical character He (Hyper-entropy) to generate new solutions in the inner loop, while He essentially indicates a heuristic control strategy to combine global random search of the outer loop and local tuning search of the inner loop. Experimental results in function optimization problems (i.e. single-peak, multi-peak and high dimensional functions) show that, compared with the simple SA algorithm, the proposed cloud annealing algorithm will lead to significant improvement on convergence and the average value of obtained solutions is usually closer to the optimal solution.

In this paper, we propose a multi-scene adaptive crowd counting method based on meta-knowledge and multi-task learning. In practice, surveillance cameras are stationarily deployed in various scenes. Considering the extensibility of a surveillance system, the ideal crowd counting method should have a strong generalization capability to be deployed in unknown scenes. On the other hand, given the diversity of scenes, it should also effectively suit each scene for better performance. These two objectives are contradictory, so we propose a coarse-to-fine pipeline including meta-knowledge network and multi-task learning. Specifically, at the coarse-grained stage, we propose a generic two-stream network for all existing scenes to encode meta-knowledge especially inter-frame temporal knowledge. At the fine-grained stage, the regression of the crowd density map to the overall number of people in each scene is considered a homogeneous subtask in a multi-task framework. A robust multi-task learning algorithm is applied to effectively learn scene-specific regression parameters for existing and new scenes, which further improve the accuracy of each specific scenes. Taking advantage of multi-task learning, the proposed method can be deployed to multiple new scenes without duplicated model training. Compared with two representative methods, namely AMSNet and MAML-counting, the proposed method reduces the MAE by 10.29% and 13.48%, respectively.