Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2results about How to "Avoid local extrema" patented technology

Photovoltaic maximum power point tracking method based on two-dimensional convolution and multi-agent deep reinforcement learning

PendingCN119002621Afast trackingUniform trackingElectric variable regulationSimulationPoint tracking
The invention provides a photovoltaic maximum power point tracking method based on two-dimensional convolution and multi-agent deep reinforcement learning. The main steps of the photovoltaic maximum power point tracking method based on two-dimensional convolution and multi-agent deep reinforcement learning are as follows: (1) measuring the maximum power points of a photovoltaic array under different irradiances and temperatures; (2) obtaining an area where a photovoltaic maximum power point is located through a two-dimensional convolutional network; (3) the multi-agent deep reinforcement learning model obtains an optimal control hyper-parameter in exploration and training; and (4) outputting the optimal control quantity. The method based on two-dimensional convolution and multi-agent deep reinforcement learning can solve the problems of complex environment change and stable control during photovoltaic maximum power point tracking, realizes a dynamic photovoltaic maximum power real-time tracking control function, optimizes the power generation stability of a photovoltaic system, and improves the performance and efficiency of the photovoltaic system.
Owner:GUANGXI UNIV

Method and device for predicting vehicle carpooling demand, electronic equipment and storage medium

PendingCN122089545Aavoid interferenceCapturing ridesharing demand characteristicsEnsemble learningForecastingFeature setEngineering
This application relates to the field of carpooling demand prediction technology, and particularly to a method, device, electronic device, and storage medium for predicting carpooling demand. The method includes: constructing a feature tensor set based on historical order data, meteorological parameters, and regional static feature data; transforming the target low-dimensional statistical features into target high-dimensional semantic features; and mapping the target high-dimensional semantic features to a target orthogonal subspace to generate a feature set that eliminates redundant temporal correlations. The feature set is then used to optimize the hyperparameters of a pre-constructed ensemble learning gradient boosting tree model until an iteration stopping condition is met, thus constructing a carpooling demand prediction model. This model outputs carpooling demand. This solves the problem that related technologies fail to couple the temporal and spatial dependencies of passenger travel demand, and that the prediction models are sensitive to hyperparameters, making it difficult to adapt to unconventional scenarios and output accurate carpooling demand.
Owner:TSINGHUA UNIVERSITY