Power distribution network investment decision-making method based on deep transfer learning
A technology of transfer learning and decision-making method, which is applied in the field of distribution network investment decision-making based on deep transfer learning, and can solve problems such as lack of power grid data sample support, complex and diverse distribution network upgrading and transformation measures, and benefit gap
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2021-09-14
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the technical field of power grid investment decision-making, in particular to a distribution network investment decision-making method based on deep transfer learning. Background technique
[0002] In the field of power grid investment decision-making, with the rapid development of clean energy and the deepening of the interaction between supply and demand, investment transformation measures have become increasingly complex and diverse. Traditional investment decision-making methods have the following problems: (1) The upgrading and transformation measures of the distribution network are complex and diverse, and the benefits obtained by different investment projects are significantly different. Taking the addition of smart meters as an example, it is usually difficult to quantify the impact of smart meters on the grid through the establishment of mathematical models. Impact. (2) The traditional investment decision-making sche...
Examples
Embodiment
[0025] Such as Figure 1 to Figure 2 As shown, the distribution network investment decision-making method based on deep transfer learning mainly includes three parts: data collection and screening, edge distribution adaptation, and conditional distribution adaptation. The specific process of each part is as follows:
[0026] S10. Data collection and screening: Since power grid investment planning usually takes years as a cycle, the historical operation data of the target distribution network is often difficult to meet the sample size requirements required for deep learning training, so collecting n R The historical data of a distribution network is used as the original data set D for migration learning of the target distribution network R ={d R (1),d R (2),...,d R (n R )}.
[0027] Based on the maximum mean difference MMD to measure the difference between variables in different data sets, its mathematical expression is:
[0028]
[0029] in, Represents the source do...