6 results about "Loop closing" patented technology

The application discloses an in-loop enhancement method for super-low code rate video coding based on artificial intelligence, and relates to the technical field of artificial intelligence, which comprises the following steps: step 1: obtaining a reconstructed frame generated by a current decoder as a visual input and a current code rate indicator as a control input; generating an initial pulse event stream containing event timestamps and polarity and a pulse timing consistency graph thereof; step 2: under the constraint of the pulse timing consistency graph, performing pulse consistency re-estimation and asynchronous residual back-annotation based on interleaved phase cross-checking; step 3: under the control of in-loop closed-loop and code rate collaborative regulation, generating a pulse reconstruction enhancement frame by using the enhanced pulse event stream, and replacing a reference frame with the pulse reconstruction enhancement frame. The application can significantly reduce the cross-frame distortion accumulation risk, improve the subjective viewing quality and the reliability of the reference frame, and has practical application value in low-bandwidth transmission and limited storage scenarios.

The invention discloses a closed-loop current adjusting method and device of a power grid, a storage medium and electronic equipment. The method comprises the following steps: acquiring an initial voltage amplitude and an initial phase angle value at two sides of a target loop closing point, and determining an initial loop closing current value of the target loop closing point; if the initial loop closing current value is greater than a preset loop closing current threshold value, based on the initial loop closing current value, determining a first-stage adjusting quantity of the adjusting equipment, performing first-stage adjustment on the adjusting equipment, and after the first-stage adjustment is completed, determining a first updated loop closing current value of the target loop closing point; based on the first updated loop closing current value, carrying out second-stage adjustment on the adjusting equipment; and after the second-stage regulation is finished, if the obtained second updated loop closing current value is greater than the preset loop closing current threshold value, continuously regulating the regulating equipment by adopting a second-stage regulation mode until a regulation stop condition is met. The technical problem that the loop closing current adjusting precision of the loop closing point of the power grid is insufficient in the prior art is solved.

The invention discloses an ultra-low bit rate video coding and decoding in-loop enhancement method based on artificial intelligence, and relates to the technical field of artificial intelligence, and the method comprises the steps: 1, obtaining a reconstruction frame generated by a current decoder as a visual input, and obtaining a current bit rate indication quantity as a control input; generating an initial pulse event stream containing an event timestamp and polarity and a pulse time sequence consistency graph of the initial pulse event stream; 2, under the constraint of the pulse time sequence consistency graph, pulse consistency reestimation and asynchronous residual error reinjection based on staggered phase rechecking are executed; and step 3, under the control of in-loop closed loop and code rate cooperative adjustment, generating a pulse reconstruction enhanced frame by using the enhanced pulse event stream, and replacing a reference frame with the pulse reconstruction enhanced frame. According to the method, the cross-frame distortion accumulation risk can be remarkably reduced, the subjective watching quality and the reliability of the reference frame are improved, and the method has the practical application value in low-bandwidth transmission and limited storage scenes.

A power distribution network closed-loop power supply switching key influence factor evaluation method based on LASSO regression and an improved XGBoost algorithm comprises the steps that a power distribution network closed-loop simulation model is built, initial influence factors influencing closed-loop current are analyzed, and multiple sets of sample data are generated through parametric scanning and Latin hypercube sampling; carrying out standardization and normalization processing on the initial influence factors; carrying out dimensionality reduction on the preprocessed high-dimensional features by adopting an LASSO regression model, determining an optimal regularization parameter through cross validation, and screening key influence factors; an improved XGBoost model is constructed based on the screened key influence factors, model hyper-parameters are optimized through grid search, and model precision is evaluated by using multiple indexes; and based on a feature importance result output by the improved XGBoost model, quantifying the weight of each key influence factor and determining a priority order, and formulating a hierarchical regulation and control strategy according to the priority order.

The invention discloses a multi-loop cooperative pre-synchronization control method and system based on a virtual synchronous generator, relates to the technical field of VSG control, and is suitable for an inverter grid-connected scene. According to the method, output voltages of a power grid and an inverter are collected in real time and filtered, a mathematical model is established based on a voltage signal, and a voltage compensation amount, an angular frequency compensation amount and a phase compensation amount are calculated; the three compensation quantities are cooperatively fused into a VSG control equation, multi-loop closed-loop adjustment is carried out on the amplitude, the angular frequency and the phase of the output voltage, and accurate matching with the three elements of the power grid voltage is achieved; and detecting deviation in real time, and sending a grid-connected instruction to complete operation after the deviation reaches the standard Through multi-loop cooperative compensation, the problems that phase difference elimination is inaccurate and the pre-synchronization speed is low in the prior art are solved, high-precision pre-synchronization can be rapidly completed under the large initial phase difference, the grid-connected impact current is remarkably reduced, power fluctuation after grid connection is restrained, the grid-connected stability and response speed of the system are improved, and the method has important engineering application value.

This invention relates to the field of power systems, specifically to a method, system, equipment, and medium for selecting the access location of a loop-closing device. The process involves generating typical daily scenarios for new energy power generation systems and loads; randomly simulating different times and line faults in the distribution network; calculating grid operation status indicators between different nodes of the distribution network where the loop-closing device is connected; constructing an indicator matrix; evaluating different loop-closing device access schemes; and forming an evaluation decision vector for loop-closing device access schemes for specific fault scenarios through standardization and maximum / minimum value analysis. The process then determines whether the number of simulations for the fault scenario is less than a preset total number of simulations. If so, the number of simulations is increased, and the grid operation status indicators are recalculated; otherwise, the process proceeds to the next step. Using evidence theory, a final access scheme for the loop-closing device, incorporating multiple indicators across multiple scenarios, is formed. This invention guides the selection of the access location for loop-closing devices, improving the reliability of power system operation and the power service capabilities of the distribution network.