公开(公告)号：US11689021B2

公开(公告)日：2023-06-27

申请号：US17025154

申请日：2020-09-18

Applicant: TSINGHUA UNIVERSITY

Inventor： Wenchuan Wu ,  Haotian Liu ,  Hongbin Sun ,  Bin Wang ,  Qinglai Guo ,  Tian Xia

IPC: H02J3/18 ,  G06F30/20

CPC classification number: H02J3/18 ,  G06F30/20 ,  H02J2203/20

Abstract: A power grid reactive voltage control model training method. The method comprises: establishing a power grid simulation model; establishing a reactive voltage optimization model, according to a power grid reactive voltage control target; building interactive training environment based on Adversarial Markov Decision Process, in combination with the power grid simulation model and the reactive voltage optimization model; training the power grid reactive voltage control model through a joint adversarial training algorithm; and transferring the trained power grid reactive voltage control model to an online system. The power grid reactive voltage control model trained by using the method according to the present disclosure has transferability as compared with the traditional method, and may be directly used for online power grid reactive voltage control.

公开(公告)号：US11514206B2

公开(公告)日：2022-11-29

申请号：US17136941

申请日：2020-12-29

Applicant: Tsinghua University

Inventor： Wenchuan Wu ,  Boming Zhang ,  Zihao Li ,  Hongbin Sun ,  Bin Wang ,  Qinglai Guo

IPC: G05B19/042 ,  H02J3/00 ,  G06F30/13

Abstract: The disclosure provides a method for planning a power distribution network, an apparatus for planning a power distribution network, and a storage medium. The method includes: establishing a model for planning the power distribution network, the model including a target function and constraints, the target function for minimizing a cost of the power distribution network when branches and nodes are installed into the power distribution network, the nodes including transformers and substations, the constraints including a power balance constraint of the power distribution network, a power constraint of the branches, a power constraint of the transformers, a radial operation constraint of the power distribution network, a fault constraint, a calculation constraint of indices of a reliability, a constraint of the indices of the reliability, and a logic constraint; and solving the model to determine whether the branches and the nodes are installed into the power distribution network.

公开(公告)号：US11442420B2

公开(公告)日：2022-09-13

申请号：US17026364

申请日：2020-09-21

Applicant: TSINGHUA UNIVERSITY

Inventor： Wenchuan Wu ,  Haotian Liu ,  Hongbin Sun ,  Bin Wang ,  Qinglai Guo ,  Tian Xia

IPC: G05B19/00 ,  G05B19/042 ,  G06N20/00

Abstract: A power grid reactive voltage control method and control system based on two-stage deep reinforcement learning, comprising steps of: building interactive training environment based on Markov decision process, according to a regional power grid simulation model and a reactive voltage optimization model; training a reactive voltage control model offline by using a SAC algorithm, in the interactive training environment based on Markov decision process; deploying the reactive voltage control model to a regional power grid online system; and acquiring operating state information of the regional power grid, updating the reactive voltage control model, and generating an optimal reactive voltage control policy. As compared with the existing power grid optimizing method based on reinforcement learning, the online control training according to the present disclosure has costs and safety hazards greatly reduced, and is more suitable for deployment in an actual power system.

公开(公告)号：US11415952B2

公开(公告)日：2022-08-16

申请号：US17146767

申请日：2021-01-12

Applicant: Tsinghua University

Inventor： Hongbin Sun ,  Qinglai Guo ,  Bin Wang ,  Guanxiong Yin ,  Tongtian Sheng ,  Zhaoguang Pan

IPC: G05B17/02 ,  F24D19/10

Abstract: The disclosure provides a method, an apparatus, and a storage medium for controlling a heating system in a combined heat and power system. The method includes: establishing a load flow model of the heating system, in which the heating system includes pipelines and nodes; the nodes include loads and heating sources; the load flow model includes an objective function and constraints; the objective function for maximizing and minimizing an inlet water temperature of each load or each source; solving the load flow model to obtain an upper limit and a lower limit of the inlet water temperature of each load or each source; and controlling the inlet water temperature of each load or each source based on the upper limit and the lower limit of the inlet water temperature of each load or each source.

公开(公告)号：US11228179B2

公开(公告)日：2022-01-18

申请号：US16848654

申请日：2020-04-14

Applicant: TSINGHUA UNIVERSITY ,  STATE GRID BEIJING ELECTRIC POWER COMPANY ,  STATE GRID JIBEI ELECTRIC POWER COMPANY

Inventor： Bin Wang ,  Hongquan Ji ,  Yanling Du ,  Qinglai Guo ,  Xijuan Yu ,  Haitao Liu ,  Hongbin Sun ,  Guannan Wang ,  Mang Jiang ,  Huaichang Ge ,  Wenchuan Wu

IPC: H02J3/38 ,  F03D7/04 ,  H02P9/04 ,  H02P101/15

Abstract: The present disclosure proposes a decomposition-coordination voltage control method for wind power to be transmitted to a nearby area via flexible DC. The method includes: initializing parameters; sending the parameters to wind power farms; for each of the wind power farms, establishing a voltage control optimization sub-model; solving the voltage control optimization sub-model to obtain a first optimal result; for the control center, establishing a voltage control optimization main model; solving the voltage control optimization main model to obtain a second optimal result; calculating a determination index based on the first optimal result and the second optimal result; and determining whether the determination index is convergent to an admissible value, if no, updating the parameters and returning to establishing the voltage control optimization sub-model.

公开(公告)号：US20210365619A1

公开(公告)日：2021-11-25

申请号：US17322912

申请日：2021-05-18

Applicant: TSINGHUA UNIVERSITY

Inventor： Hongbin Sun ,  Qinglai Guo ,  Bin Wang ,  Guanxiong Yin ,  Zhaoguang Pan ,  Binbin Chen

IPC: G06F30/28 ,  G06F17/16

Abstract: Provided is a method for a dynamic state estimation of a natural gas network considering dynamic characteristics of natural gas pipelines. The method can obtain a result of the dynamic state estimation of the natural gas network by establishing an objective function of the dynamic state estimation of the natural gas network, a state quantity constraint of a compressor, a state quantity constraint of the natural gas pipeline and a topological constraint of the natural gas network, and using a Lagrange method or an interior point method to solve a state estimation model of the natural gas network. The method takes the topological constraint of the natural gas network into consideration, and employs a pipeline pressure constraint in a frequency domain to implement linearization of the pipeline pressure constraint, thereby obtain a real-time, reliable, consistent and complete dynamic operating state of the natural gas network.

公开(公告)号：US20210356923A1

公开(公告)日：2021-11-18

申请号：US17026364

申请日：2020-09-21

Applicant: TSINGHUA UNIVERSITY

Inventor： Wenchuan Wu ,  Haotian Liu ,  Hongbin Sun ,  Bin Wang ,  Qinglai Guo ,  Tian Xia

IPC: G05B19/042 ,  G06N20/00

Abstract: A power grid reactive voltage control method and control system based on two-stage deep reinforcement learning, comprising steps of: building interactive training environment based on Markov decision process, according to a regional power grid simulation model and a reactive voltage optimization model; training a reactive voltage control model offline by using a SAC algorithm, in the interactive training environment based on Markov decision process; deploying the reactive voltage control model to a regional power grid online system; and acquiring operating state information of the regional power grid, updating the reactive voltage control model, and generating an optimal reactive voltage control policy. As compared with the existing power grid optimizing method based on reinforcement learning, the online control training according to the present disclosure has costs and safety hazards greatly reduced, and is more suitable for deployment in an actual power system.

公开(公告)号：US10291027B2

公开(公告)日：2019-05-14

申请号：US15015225

申请日：2016-02-04

Applicant: Tsinghua University

Inventor： Wenchuan Wu ,  Boming Zhang ,  Hongbin Sun ,  Zhuang Tian ,  Qinglai Guo ,  Bin Wang

IPC: H02J3/38 ,  G05B17/02 ,  H02J3/06 ,  H02J3/16 ,  H02J3/48 ,  H02J3/50 ,  G05F1/66 ,  H02J3/18 ,  H02J3/00

Abstract: The present disclosure provides a method and a device for controlling an active distribution network, relating to the field of power system operation and control technology. The method includes: creating a power loss objective function; determining first power flow equations; obtaining second power flow equations by performing linearization on the first power flow equations; determining a sub-scale adjustment model of a transformer; obtaining a linearized model of the transformer by performing linearization on the sub-scale adjustment model; obtaining control parameters by solving the power loss objective function according to the second power flow equations, the linearized model of the transformer, an operation constraint of the continuous reactive power compensator, an operation constraint of the grouping switching capacitor, an operation constraint of the distributed generator and a safety operation constraint in the active distribution network, such that the active distribution network is controlled by the obtained parameters to minimize power loss.

公开(公告)号：US10235340B2

公开(公告)日：2019-03-19

申请号：US14858861

申请日：2015-09-18

Applicant: Tsinghua University

Inventor： Hongbin Sun ,  Qinglai Guo ,  Bin Wang ,  Boming Zhang ,  Wenchuan Wu ,  Lei Tang

IPC: H02P9/02 ,  G06F17/10 ,  H02J3/00 ,  H02P9/00

Abstract: A method and apparatus for controlling a reactive power of a generator in a power plant are provided. The method includes: S1, dividing a plurality of power plants into a plurality of plant-plant coordination groups; S2, dividing generators into a first generator and a second generator set; S3, calculating a deviation between a measured voltage and a preset voltage of a central bus; S4, comparing the deviation with a control dead band threshold; S5, establishing a reactive power tracking model if the deviation is greater than the control dead band threshold; S6, establishing a reactive power keeping model; and S7, obtaining sum reactive power adjustments of the generators according to the first reactive power adjustments and the second reactive power adjustments, and obtaining voltage adjustments of buses according to the sum reactive power adjustments.

公开(公告)号：US10001762B2

公开(公告)日：2018-06-19

申请号：US14601390

申请日：2015-01-21

Applicant: Tsinghua University

Inventor： Hongbin Sun ,  Qinglai Guo ,  Bin Wang ,  Boming Zhang ,  Xuran Wang ,  Huaichang Ge ,  Wenchuan Wu

IPC: G05B15/02 ,  H02J3/16

CPC classification number: G05B15/02 ,  H02J3/16 ,  Y02E40/34

Abstract: A voltage control method and apparatus of a central bus in a power system are provided. The method comprises: S1: obtaining a predetermined voltage and a current voltage; S2: obtaining a first voltage adjustment of the generator and a second voltage adjustment of the dynamic reactive power compensation device; S3: sending the first voltage adjustment and the second voltage adjustment; S4: judging whether a current reactive power of the dynamic reactive power compensation device is between a first predetermined reactive power and a second predetermined reactive power; S5: if yes, obtaining a third voltage adjustment of the generator and a fourth voltage adjustment of the dynamic reactive power compensation device; S6: sending the third voltage adjustment and the fourth voltage adjustment; repeating steps S1-S7 after a predetermined period of time; S7: if no, repeating steps S1-S7 after the predetermined period of time.