Systems and methods for solving multi-objective hierarchical linear programming problems using previously-solved solution information

    公开(公告)号:US12131282B1

    公开(公告)日:2024-10-29

    申请号:US17679871

    申请日:2022-02-24

    发明人: Vishal Shinde

    CPC分类号: G06Q10/083 G06Q10/04

    摘要: A system and method of solving supply chain planning problems modeled as multi-objective hierarchical linear programming problems receive supply chain input data for a supply chain planning problem, solve a first multi-objective hierarchical linear programming problem, store a cumulative list of bound changes, receive changes to the supply chain input data, model a second supply chain planning problem as a second multi-objective hierarchal linear programming problem based, at least in part, on the one or more changes to the supply chain input data, derive an intermediate objective based, at least in part, on the cumulative list of bound change, and solve the second multi-objective hierarchical linear programming problem, using the basis of the solved intermediate objective.

    Multi-device site selection method for integrated energy virtual power plant

    公开(公告)号:US12118483B2

    公开(公告)日:2024-10-15

    申请号:US17633343

    申请日:2021-05-10

    摘要: The present invention discloses a multi-device site selection method for an integrated energy virtual power plant, and belongs to the field of virtual power plants. The multi-device site selection method for an integrated energy virtual power plant includes the following steps: constructing a calculation method for calculating a comprehensive energy flow distribution entropy through power flow distribution in a power distribution network and flow distribution in a heat distribution network, to reflect energy distribution balance in an energy network; under a condition that capacity of each device is known, establishing a multi-device site selection optimal planning model of the integrated energy virtual power plant with a goal of maximizing a comprehensive energy flow distribution entropy index; and determining an installation location of each device of the integrated energy virtual power plant in the energy network, and determining an operating state of each device.

    Method of Determining River Nitrous Oxide Emission based on Land-River-Atmosphere Simulation

    公开(公告)号:US20240321403A1

    公开(公告)日:2024-09-26

    申请号:US18605776

    申请日:2024-03-14

    IPC分类号: G16C20/20 G06Q10/04

    CPC分类号: G16C20/20 G06Q10/04

    摘要: A method of determining nitrous oxide emission of a river based on land-river-atmosphere simulation, includes the steps of: obtaining nitrogen emission from land in each region; dividing the nitrogen emission into a prediction set and a test set; using nitrogen emission prediction set, and geographical variables and climate variables under the nitrogen emission prediction set to process RF regression model training to obtain a trained RF regression model, using nitrogen emission test set, and geographical variables and climate variables under the nitrogen emission test set to process RF regression model training to obtain a trained RF regression model, and outputting a river water quality concentration of each sub-basin in each region; obtaining river hydrological parameters of each sub-basin, inputting the river hydrological parameters and river water quality concentration of each sub-basin to an air-water interface gas exchange model to obtain a total river N2O emission in each sub-basin.

    INSURANCE LOSS RATIO FORECASTING FRAMEWORK
    10.
    发明公开

    公开(公告)号:US20240320749A1

    公开(公告)日:2024-09-26

    申请号:US18609626

    申请日:2024-03-19

    IPC分类号: G06Q40/08 G06Q10/04

    CPC分类号: G06Q40/08 G06Q10/04

    摘要: A system and method for insurance loss ratio forecasting, which utilizes faster feature reduction by blending traditional statistical method and feature importance, and applying a Boruta algorithm for further feature reduction. Final feature selection is achieved by creating a balance between Light GBM model feature importance and coverage rate. These processes are all completely automated. Faster hyperparameter tuning is achieved by applying a randomized search algorithm. In the out-of-time sample dataset and production sample dataset for an insurance loss ratio forecast, faster segmentation is conducted by applying unsupervised ML, using cosine similarity. The system is a significant technical improvement, which requires uniquely critical computer implementation and ensures that the models are stable for users, across different samples of data, without extensive fine tuning and no manual searches. In addition, the system framework is easy for non-native users to use, enabling almost anyone to build ML models.