Edge-cloud jobs are rapidly prevailing in many application domains, posing the challenge of using both resource-strenuous edge devices and elastic cloud resources. Efficient resource allocation on such jobs via scheduling algorithms is essential to guarantee their performance, e.g. latency. Deep reinforcement learning (DRL) is increasingly adopted to make scheduling decisions but faces the conundrum of achieving high rewards at a low training overhead. It is unknown if such a DRL can be applied to timely tune the scheduling algorithms that are adopted in response to fast changing workloads and resources. In this paper, we propose EdgeTuner to effectively leverage DRL to select scheduling algorithms online for edge-cloud jobs. The enabling features of EdgeTuner are sophisticated DRL model that captures complex dynamics of Edge-Cloud jobs/tasks and an effective simulator to emulate the response times of short-running jobs in accordance to dynamically changing scheduling algorithms. EdgeTuner trains DRL agents offline by directly interacting with the simulator. We implement EdgeTuner on Kubernetes scheduler and extensively evaluate it on Kubernetes cluster testbed driven by the production traces. Our results show that EdgeTuner outperforms prevailing scheduling algorithms by achieving significant lower job response time while accelerating DRL training speed by more than 180x.

New membrane materials with excellent water permeability and high ion rejection are needed. Metal-organic frameworks (MOFs) are promising candidates by virtue of their diversity in chemistry and topology. In this work, continuous aluminum MOF-303 membranes were prepared on α-Al2O3 substrates via an in situ hydrothermal synthesis method. The membranes exhibit satisfying rejection of divalent ions (e.g., 93.5% for MgCl2 and 96.0% for Na2SO4) on the basis of a size-sieving and electrostatic-repulsion mechanism and unprecedented permeability (3.0 L·m-2·h-1·bar-1·μm). The water permeability outperforms typical zirconium MOF, zeolite, and commercial polymeric reverse osmosis and nanofiltration membranes. Additionally, the membrane material exhibits good stability and low production costs. These merits recommend MOF-303 as a next-generation membrane material for water softening.

Cyber-physical systems embed software into the physical world. They appear in a wide range of applications such as smart grids, robotics, and intelligent manufacturing. Cyber-physical systems have proved resistant to modeling due to their intrinsic complexity arising from the combination of physical and cyber components and the interaction between them. This study proposes a general framework for discovering cyber-physical systems directly from data. The framework involves the identification of physical systems as well as the inference of transition logics. It has been applied successfully to a number of real-world examples. The novel framework seeks to understand the underlying mechanism of cyber-physical systems as well as make predictions concerning their state trajectories based on the discovered models. Such information has been proven essential for the assessment of the performance of cyber-physical systems; it can potentially help debug in the implementation procedure and guide the redesign to achieve the required performance.