CN-122026488-A - Coordinated control method, device, medium and product based on multiple time scales

CN122026488ACN 122026488 ACN122026488 ACN 122026488ACN-122026488-A

Abstract

The embodiment of the application provides a coordinated control method, a coordinated control device, a coordinated control medium and a coordinated control product based on multiple time scales, which are applied to a multi-source heterogeneous energy system, wherein the method comprises the steps of obtaining multi-time scale prediction data corresponding to the multi-source heterogeneous energy system; the multi-time scale prediction data comprises prediction data of the multi-source heterogeneous energy system under various different time scales, each prediction data is generated through different prediction models, feature fusion is carried out on the various prediction data to obtain a prediction feature vector, and a control strategy crossing the time scales is obtained based on the prediction feature vector by combining a preset hierarchical objective function. The method is used for solving the problems of asynchronous response and cross-scale control conflict of the multi-source equipment in the network-structured micro-grid so as to improve the running stability, economy and cooperative control precision of the system under the complex working condition.

Inventors

LIU HAITAO
JI XIAOJIAN
YU GUOXIN
Xi Yaqing

Assignees

海尔新能源科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260413

Claims (10)

1. The coordination control method based on the multiple time scales is characterized by being applied to a multi-source heterogeneous energy system; the method comprises the following steps: the multi-time scale prediction data comprises prediction data of the multi-source heterogeneous energy system under a plurality of different time scales, and each prediction data is generated through different prediction models; Performing feature fusion on a plurality of prediction data to obtain a prediction feature vector; Acquiring a cross-time scale control strategy based on the predictive feature vector by combining a preset hierarchical objective function, wherein the hierarchical objective function at least comprises an energy storage state optimization target corresponding to a first time scale, a power fluctuation smoothing target corresponding to a second time scale and a voltage frequency stabilization target corresponding to a third time scale; the control strategy at least comprises a first sub-strategy corresponding to the first time scale, a second sub-strategy corresponding to the second time scale and a third sub-strategy corresponding to the third time scale.
2. The method of claim 1, wherein the obtaining a control strategy across time scales based on the predictive feature vector in combination with a predetermined hierarchical objective function comprises: Acquiring the first sub-strategy based on the prediction feature vector and the energy storage state optimization target; acquiring the second sub-strategy based on the prediction feature vector and the power fluctuation smoothing target; and acquiring the third sub-strategy based on the prediction feature vector and the voltage frequency stabilizing target.
3. The method of claim 2, wherein the multi-source heterogeneous energy system comprises at least one energy production end and at least one energy consumption end; after the cross-time scale control strategy is acquired, the method further comprises the following steps: setting distribution advance time corresponding to each energy production end and each energy consumption end based on delay characteristics corresponding to the energy production end and the energy consumption end; and according to the priority order preset by the first sub-strategy, the second sub-strategy and the third sub-strategy, distributing the first sub-strategy, the second sub-strategy and the third sub-strategy in sequence according to the distribution advance time corresponding to each energy source production end and each energy source consumption end, so that the equipment in the multi-source heterogeneous energy system can perform state adjustment according to the first sub-strategy, the second sub-strategy or the third sub-strategy.
4. The method according to claim 1, wherein the feature fusion of the plurality of prediction data to obtain a prediction feature vector includes: dynamically distributing weights for time scales corresponding to the plurality of prediction data based on the change trends corresponding to the plurality of prediction data; and combining weights corresponding to the time scales, and carrying out feature fusion on the plurality of prediction data to obtain the prediction feature vector.
5. The method of claim 4, wherein dynamically assigning weights to time scales corresponding to the plurality of predicted data based on the trend of the plurality of predicted data comprises: Calculating correlation among the prediction data of different time scales based on the prediction data corresponding to the multiple time scales; And distributing corresponding weights for the predicted data corresponding to the time scales of different time spans based on the magnitude of the correlation, wherein the magnitude of the weights of the predicted data corresponding to the different time scales and the magnitude of the correlation are changed from positive correlation to negative correlation according to the sequence of the time spans from large to small.
6. The method according to claim 1, wherein the method further comprises: Acquiring environment data of an environment where the multi-source heterogeneous energy system is located and operation data corresponding to at least one energy production end and at least one energy consumption end in the multi-source heterogeneous energy system; and correcting the multi-time scale prediction data and the control strategy based on the environment data and the operation data.
7. The coordination control device based on the multiple time scales is characterized by being applied to a multi-source heterogeneous energy system; the device comprises: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring multi-time-scale prediction data corresponding to the multi-source heterogeneous energy system, the multi-time-scale prediction data comprises prediction data of the multi-source heterogeneous energy system under a plurality of different time scales, and each prediction data is generated through different prediction models; The fusion module is used for carrying out feature fusion on the plurality of prediction data to obtain a prediction feature vector; The system comprises a first acquisition module, a second acquisition module and a third time scale generation module, wherein the first acquisition module is used for acquiring a time-scale-crossing control strategy based on a prediction feature vector by combining a preset hierarchical objective function, and the hierarchical objective function at least comprises an energy storage state optimization target corresponding to a first time scale, a power fluctuation smoothing target corresponding to a second time scale and a voltage frequency stabilization target corresponding to a third time scale; the control strategy at least comprises a first sub-strategy corresponding to the first time scale, a second sub-strategy corresponding to the second time scale and a third sub-strategy corresponding to the third time scale.
8. A multi-source heterogeneous energy system, wherein the multi-source heterogeneous energy system comprises at least one energy production end and at least one energy consumption end; The multi-source heterogeneous energy system is used for acquiring multi-time-scale prediction data corresponding to the multi-source heterogeneous energy system by adopting the multi-time-scale-based coordination control method according to any one of claims 1-6, wherein the multi-time-scale prediction data comprises prediction data of the multi-source heterogeneous energy system under various different time scales, each prediction data is generated through different prediction models, and the various prediction data are subjected to feature fusion to obtain a prediction feature vector, and a cross-time-scale control strategy is acquired by combining a preset hierarchical objective function based on the prediction feature vector, wherein the hierarchical objective function at least comprises an energy storage state optimization objective corresponding to a first time scale, a power fluctuation smoothing objective corresponding to a second time scale and a voltage frequency stabilization objective corresponding to a third time scale, and the time spans corresponding to the first time scale, the second time scale and the third time scale are sequentially reduced; the control strategy at least comprises a first sub-strategy corresponding to the first time scale, a second sub-strategy corresponding to the second time scale and a third sub-strategy corresponding to the third time scale.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Coordinated control method, device, medium and product based on multiple time scales Technical Field The application relates to the technical field of power system control, in particular to a coordinated control method, a coordinated control device, a coordinated control medium and a coordinated control product based on multiple time scales. Background With the wide application of distributed energy sources, a grid-structured light-storage heat-charging micro-grid becomes a key system for improving the energy utilization efficiency. However, the system relates to multi-source heterogeneous equipment such as photovoltaic equipment, energy storage equipment, charging piles, heat pumps and the like, and faces the challenges of large output fluctuation, high load uncertainty, obvious equipment response delay difference and the like. In actual operation, the control requirements of multiple time scales such as long-term energy optimization, medium-term power smoothing, short-term voltage frequency stabilization and the like are simultaneously met, and the traditional single control mode is difficult to consider economical efficiency and stability. In the prior art, a layered control architecture is mostly adopted, and long-term, medium-term and short-term control of the fracturing treatment is carried out, so that targets of all time scales lack coordination. For example, short-term power fluctuation constraint is not considered in long-term energy storage planning, control strategy conflict is easy to cause, a prediction model is usually constructed aiming at a single time scale, and trans-scale information fusion is lacked, so that prediction accuracy is limited. In addition, the prior art relies on a central cloud platform to predict and control, so that the problems of high communication delay and insufficient instantaneity exist, and the requirements of micro-grid on second-level response are difficult to meet. Therefore, a coordinated control method is needed to solve the above technical bottleneck. Disclosure of Invention The embodiment of the application provides a coordinated control method, a device, a medium and a product based on multiple time scales, which are used for solving the problems of asynchronous response and cross-scale control conflict of multi-source equipment in a network-structured micro-grid so as to improve the running stability, economy and cooperative control precision of a system under a complex working condition. In a first aspect, an embodiment of the present application provides a coordinated control method based on multiple time scales, which is applied to a multi-source heterogeneous energy system, where the method includes: the multi-time scale prediction data comprises prediction data of the multi-source heterogeneous energy system under a plurality of different time scales, and each prediction data is generated through different prediction models; Performing feature fusion on a plurality of prediction data to obtain a prediction feature vector; Acquiring a cross-time scale control strategy based on the predictive feature vector by combining a preset hierarchical objective function, wherein the hierarchical objective function at least comprises an energy storage state optimization target corresponding to a first time scale, a power fluctuation smoothing target corresponding to a second time scale and a voltage frequency stabilization target corresponding to a third time scale; the control strategy at least comprises a first sub-strategy corresponding to the first time scale, a second sub-strategy corresponding to the second time scale and a third sub-strategy corresponding to the third time scale. In a possible implementation manner, the acquiring a control strategy across time scales based on the prediction feature vector in combination with a preset hierarchical objective function includes: Acquiring the first sub-strategy based on the prediction feature vector and the energy storage state optimization target; acquiring the second sub-strategy based on the prediction feature vector and the power fluctuation smoothing target; and acquiring the third sub-strategy based on the prediction feature vector and the voltage frequency stabilizing target. In one possible embodiment, the multi-source heterogeneous energy system comprises at least one energy production end and at least one energy consumption end; after the cross-time scale control strategy is acquired, the method further comprises the following steps: setting distribution advance time corresponding to each energy production end and each energy consumption end based on delay characteristics corresponding to the energy production end and the energy consumption end; and according to the priority order preset by the first sub-strategy, the second sub-strategy and the third sub-strategy, distributing the first sub-strategy, the second sub-strategy and the third sub-strategy in sequence according to the distribution advance