Chen Ji

TL;DR: In this article, a distribution equipment condition monitoring system based on the Internet of Things technology and an implementation method thereof, relates to the technical field of online monitoring of power equipment, and can simultaneously promote the technical fusion of an intelligent power grid, the internet of things and cloud computing, so that users can quickly develop and upgrade and maintain own distribution equipment.

TL;DR: In this paper, a single phase grounding fault line selection method of a small current grounding system is proposed, which comprises the steps that the three phase voltage V and a three-phase current I of each return and output line are collected in a substation, the active power P, the reactive power Q, and power factors cos phi of all the return-and output-lines are calculated, and all the parameters are preserved; an eigenmatrix X * is obtained according to the preserved parameters; a deep belief network DBN is constructed, the E * is input

TL;DR: In this article, an early warning coordination rolling optimization method for minimizing surplus water of a hydraulic power plant is proposed, which comprises the steps of fitting a related curve according to acquired power plant data, setting a rolling calculation period and calculating an actual interval, and reading real-time water condition data and a current planned output of a set.

TL;DR: In this article, a cloud-computing-based real-time grid monitoring and alarming system and realization method thereof under SOA architecture is proposed to solve the problems that a cross-platform effect can not be realized, the development cots is high, maintenance becomes difficult, and the alarm voice type is single according to the existing grid alarm system in the prior art.

TL;DR: In this article, a distribution network theoretical line loss calculation method based on a line loss load characteristic curve is proposed, in which a relationship between a load rate and line loss rate is established, and rise and fall of distribution network line loss can be learned through the line loss Load characteristic curve, so that the method is highly reliable.