Mobile crowdsensing is a popular platform that takes advantage of the onboard sensors and resources on mobile nodes. The crowdsensing platform chooses to assign several sensing tasks each day, whose utility is based on the quality of harvested sensing data, the payment of transmitting data, and the recruitment of mobile nodes. An Internet service provider (ISP) selects a portion of access points (APs) to power on for uploading data, whose utility depends on three parts: the traffic income of transmitting sensing data, the energy cost of operating APs, and the energy cost of data transmissions by APs. The interaction between the crowdsensing platform and ISP is formulated as an iterated game, with social welfare defined as the sum of their expected utilities. In this paper, our objective is to unilaterally control social welfare without considering the opponent’s strategy, with the aim of achieving stable and maximized social welfare. To achieve this goal, we leverage the concept of a zero-determinant strategy in the game theory. We introduce a zero-determinant strategy for the vehicular crowdsensing platform (ZD-VCS) and analyze it in discrete and continuous models in the vehicular crowdsensing scenario. Furthermore, we analyze an extortion strategy between the platform and ISP. Experimental results demonstrate that the ZD-VCS strategy enables unilateral control of social welfare, leading to a high and stable value.

In the current landscape of online data services, data transmission and cloud computing are often controlled separately by Internet Service Providers (ISPs) and cloud providers, resulting in significant cooperation challenges and suboptimal global data service optimization. In this study, we propose an end-to-end scheduling method aimed at supporting low-latency and computation-intensive medical services within local wireless networks and healthcare clouds. This approach serves as a practical paradigm for achieving low-latency data services in local private cloud environments. To meet the low-latency requirement while minimizing communication and computation resource usage, we leverage Deep Reinforcement Learning (DRL) algorithms to learn a policy for automatically regulating the transmission rate of medical services and the computation speed of cloud servers. Additionally, we utilize a two-stage tandem queue to address this problem effectively. Extensive experiments are conducted to validate the effectiveness for our proposed method under various arrival rates of medical services.