6 results about "Island state" patented technology

The invention provides an island division and load recovery method, device and equipment for a power distribution network. The method comprises the following steps: acquiring real-time state data of the power distribution network; preprocessing the real-time state data to obtain target state data; inputting the target state data into an island division model for processing to obtain an island division result; the island division model is obtained by training historical fault processing data; according to the island division result, utilizing a load recovery model to recover loads in sequence; the load recovery model comprises an evaluation network layer and a target network layer, the evaluation network layer outputs an action decision according to the island state data, the target network layer outputs action value evaluation according to the island state data, and the weight of the evaluation network layer is adjusted according to the action value evaluation. According to the invention, the efficiency and stability of power distribution network island division and load recovery can be improved.

The invention relates to an island separation control method and device, equipment and a medium. The method comprises the steps of obtaining operation data corresponding to a preset load node of a to-be-separated island in a power distribution network; according to the operation data, determining whether the to-be-separated island has an instability risk; setting a control mode of a current converter connected between the to-be-separated island and a main power grid as a constant-voltage and constant-frequency control mode under the condition that the to-be-separated island has an instability risk; in the constant-voltage and constant-frequency control mode, the separation time is determined according to the exchange power data of the interconnection line; wherein the interconnection line is a connection line between the to-be-separated island and the main power grid; and controlling the to-be-separated island to be separated from the main power grid at the separation time. According to the invention, stable switching of the to-be-separated island from the grid-connected state to the island state can be realized.

The application relates to a kind of distributed power island detection method, system, terminal and medium, comprising the following steps: discrete sampling distributed power grid-connected power generation system voltage signal at the public coupling point in non-island and island state;The voltage signal of the public coupling point collected is decomposed by multilayer wavelet packet transform;Island detection characteristic quantity extraction is carried out to the multilayer signal decomposed by wavelet packet transform;A neural network training model is constructed, the extracted island detection characteristic quantity is used as the input signal of the neural network training model, island detection is carried out, and a detection result is obtained;The island detection algorithm of the wavelet decomposition reconstruction method used in the application and the LSTM neural network combination is superior to the traditional intelligent detection algorithm.

The invention discloses an energy storage system island detection method and device and a medium, and relates to the technical field of data processing. Comprising the following steps: extracting local key features of frequency domain features of a target energy storage system and a time sequence change rule of time domain features and dynamic features of the target energy storage system based on a hybrid model constructed by a convolutional neural network and a long-short term memory network; the local key features and the time sequence change rule are fused based on a full connection layer, a fused high-dimensional feature vector is obtained, and the high-dimensional feature vector is used for reflecting the operation state of the target energy storage system; the high-dimensional feature vectors are analyzed based on a classification model, a classification result of whether the operation state is an island state is obtained, and the hybrid model and the classification model are obtained through training based on a dynamic weight distribution mechanism. The island state under the condition that the matching degree of the load and the output power of the energy storage system is relatively high can be effectively identified through the hybrid model and the classification model trained by using the dynamic weight distribution mechanism, so that the accuracy of island detection is improved.

The invention discloses an active island detection method, system and device for an energy storage converter, and aims to solve the problems that in an existing active island detection method, theoretical and actual circuit characteristics are inconsistent, an analytical solution can not be obtained possibly, and rapidity is poor. According to the method, RL resistive and inductive loads with the same connection relation are determined to be adopted according to the load connection condition of an actual site; calculating a per unit value of a frequency offset based on the quality factor of the RL resistance-inductance load and a set phase offset function; wherein the set phase offset function is a high-order polynomial based on the quality factor and the per unit value of the frequency offset; injecting a phase offset disturbance quantity, and detecting a frequency offset corresponding to the energy storage converter; and when the frequency offset is determined to be greater than or equal to the per-unit value of the frequency offset, judging that the energy storage converter is in an island state. In this way, the number of control parameters needing to be adjusted in the calculation process is reduced, debugging is easier, and meanwhile it is guaranteed that solutions exist under the condition of any load and parameter combination.

The invention discloses a method and system for detecting and terminating a remote control Trojan horse in an island state based on an ETW event, and relates to the field of network and information security. In order to solve the defect that high-precision and low-overhead detection and timely termination cannot be carried out on the remote control Trojan horse in an island state in the prior art, the technical scheme provided by the invention comprises the following steps of: capturing an ETW event in real time, constructing an event sequence according to a process identifier, and extracting characteristics such as reconnection frequency, receiving and transmitting event quantity, receiving and transmitting proportion and memory use; quickly screening out high-confidence Trojan horses through a threshold model; and constructing an event Markov matrix for other sequences, and inputting the event Markov matrix into a depth detection model to carry out further discrimination, thereby identifying the remote control Trojan horse in the island state. If the Trojan horse is judged to be the remote control Trojan horse at any stage, the corresponding process is immediately terminated according to the process identifier, and alarm information is sent. The method is used for real-time detection and automatic processing of the remote control Trojan horse in the island state by the terminal host, and the system safety is improved.