Abstract: A method for making a spatio-temporal combined optimal scheduling strategy of a mobile energy storage (MES) system includes: inputting data of a power system, a traffic system, and an MES system; setting a time interval, and initializing a time interval counter; inputting real-time fault, traffic, and MES data; and performing rolling optimization and solving, and delivering regulation decision instructions of the MES system, till a fault is removed. The core of the present disclosure is to propose a spatio-temporal combined optimal model of the MES system to describe spatio-temporal coupling statuses of an energy storage vehicle, a traffic network, and a power distribution network. The present disclosure provides guidance for an optimal scheduling decision of the MES system by properly regulating a traveling path and charging and discharging power of the MES system, thereby supporting high-reliability operation of the power distribution network.

Abstract: A power transformer fault diagnosis method based on a stacked time series network, includes: collecting gas-in-oil data of a transformer in each substation; performing z-score normalization on the collected data to obtain a normalized matrix; dividing the normalized matrix into a training set and a test set in proportion; constructing a stacked time series network based on Xgboost and a bidirectional gated neural network, and inputting the training set and the test set to perform network training; and normalizing real-time collected data to obtain trainable data to predict a fault and update network parameters. The gas-in-oil data is predicted by using Xgboost and a gated neural network, obtains prediction data of a power transformer from two time series networks by using a meta learner, and obtains a fault diagnosis result of the transformer by using a Softmax layer. The neural network has accurate fault diagnosis performance and stable robustness.

Abstract: A method for diagnosing transformer fault based on a deep coupled dense convolutional neural network, includes: obtaining datasets of dissolved gas in oil of a transformer in normal and fault states; expanding the datasets by using an adaptive synthetic oversampling method; performing, in a form of a two-dimensional matrix, feature reconstruction on characteristic gas dissolved in the oil; building a transformer fault diagnosis model based on a deep coupled dense convolutional neural network; and dividing an expanded dataset into a training set and a test set, and taking the two-dimensional matrix as an input of the deep coupled dense convolutional neural network and a set label as an output to train the network to obtain a fault diagnosis model. The present disclosure can resolve a problem that a fault diagnosis accuracy rate of the transformer is low due to insufficient and unbalanced fault samples in the dissolved gas in the oil.

Abstract: A control method and system for a distribution network with distributed mobile energy storage systems is disclosed which relates to the power field. The present invention manages the multiple distributed mobile energy storage systems in the distribution network in a unified way, to improve the flexibility of the distribution network, and enable the distributed mobile energy storage systems to fully smooth new energy generation fluctuations, implement peak cut, facilitate grid auxiliary services, and improve the power quality. The control method includes: acquiring, by a sub-station coordination system, data of the distributed mobile energy storage systems; receiving, by a master-station dispatching system, the data of the distributed mobile energy storage systems, and obtaining external data; generating, by the master-station dispatching system, a control instruction; and controlling, by the sub-station coordination system, the distributed mobile energy storage systems.

Abstract: Provided is a source-load cooperation access method for a power distribution region. The method includes: establishing a timing feature model of a distributed generator and a timing feature model of a load respectively, acquiring a timing feature of the distributed generator in an access power distribution region by using maximum likelihood estimation and acquiring a timing feature of a user which accesses the power distribution region by using classification and regression trees; and inputting the timing feature of the distributed generator and the timing feature of the user which access the power distribution region into a combination optimization model, and determining a source-load access feeder through optimization.

Abstract: The present application relates to a method for evaluating an operation of a distribution network based on data capture and Spark. The method includes: acquiring a packet from a terminal, and mirroring the packet through a mirroring port of a switch to acquire a mirror packet of the packet; analyzing the mirror packet, acquiring a 101/104 protocol packet, and storing the 101/104 protocol packet into an HDFS; acquiring the 101/104 protocol packet from the HDFS, parsing the 101/104 protocol packet on a Spark platform to acquire a parameter in the 101/104 protocol packet, and analyzing and processing the parameter to obtain a key indicator for evaluating the operation of the distribution network; and displaying the key indicator through a web page.

Abstract: Disclosed are a distribution transformer terminal and a method for monitoring a state of a distribution transformer court device. The distribution transformer terminal includes an ARM core processor, a carrier communication module connected to a court device, a sub-G wireless communication module connected to the court device and a GPS module connected to the court device. The ARM core processor is connected to the carrier communication module, the sub-G wireless communication module and the GPS module. The ARM core processor is configured to identify a phase of the court device and a court to which the court device belongs, acquire an operating state and fault information of the court device through the sub-G wireless communication module, and acquire geographical location information of the court device through the GPS module.

Abstract: An active power distribution network multi-time scale coordinated optimization scheduling method and storage medium are provided. The method includes the following steps: performing long-time scale optimization scheduling of an active power distribution network; performing short-time scale rolling optimization scheduling on the basis of MPC of the active power distribution network according to an optimization result of the long-time scale optimization scheduling of the active power distribution network. By using a model prediction control method, taking the long-time scale optimization scheduling result as a reference, and performing short-time scale rolling correction, the optimization scheduling of the active power distribution network is achieved, thereby reducing unfavorable influences of prediction precision of a distributed power supply and a low-voltage load on the optimization scheduling.

Abstract: The present invention discloses an extremum seeking-based control method for maximum output tracking of a wind turbine generator, mainly comprising three steps of first closed-loop feedback, second closed-loop feedback, and third closed-loop feedback. The method for resisting mechanical fatigue of a double-fed variable speed constant frequency wind turbine generator by controlling mechanical torque while capturing maximum wind energy provided in the present invention is applied to a double-fed variable speed constant frequency wind turbine system by improving the control based on sliding mode extremum seeking with the following effects that, with regard to the maximum wind energy tracking effect, the rotating speed can be quickly adjusted to keep the tip speed ratio ? as its optimum value after the wind speed changes, so that the wind energy utilization coefficient is restored to the maximum value.

Abstract: The invention relates to an automatic checking method for clock synchronization, comprising the following steps: (1) regularly acquiring clock signals sent by a Beidou signal source, a GPS signal source and an SNTP signal source; (2) performing subtraction to the clock signals of the Beidou signal source and the GPS signal source and evaluating the absolute value of the difference; at the same time, performing subtraction to the clock signals of the Beidou signal source and the SNTP signal source and then evaluating the absolute value of the difference and finally judging the results of the two differences; and (3) constantly repeating steps (1) and (2). The operations in the present invention can efficiently avoid the problems in the existing technology, guarantee the consistency and accuracy of system time, and guarantee the stable and safe operation of the system and the normal operation of other power grid businesses.