In the active sound control problem considered in paper, a quite arbitrary closed region is acoustically shielded from ambient noise generated outside via implementation of secondary sources which are situated at perimeter domain to be protected. It presumed that information available for operation only limited by acoustic field can measured on surface around region. The becomes much more compl...

We use a deep neural network to generate controllers for optimal trading on high-frequency data. For the first time, learns mapping between preferences of trader, i.e. risk aversion parameters, and controls. An important challenge in learning this is that, intra-day trading, trader's actions influence price dynamics closed loop via market impact. The exploration–exploitation tradeoff generated ...

Cyber attacks are emerging threats in the Internet of Things applications, and power systems typical cyber attack targets. As one most essential operation functions, frequency control is threatened by intrusions, existing centralized mode cannot effectively address risks. In this study, a new distributed cyber-attack-tolerant scheme designed. The also serves as convenient tool for identificatio...