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

CN113393051APending Publication Date: 2021-09-14SICHUAN UNIV
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2021-09-14

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a power distribution network investment decision-making method based on deep transfer learning, and the method comprises the steps: collecting and screening data, describing the data distribution characteristics of a power grid through an edge distribution probability, representing the network relation characteristics of the power grid through a conditional distribution probability, and completing the characteristic transfer from a source domain power grid to a target power grid, so that adaptive learning under a small sample of power distribution network investment is realized, and finally an input-output nonlinear mapping model based on a target power distribution network is established to make a decision on power distribution network investment. According to the method, a power grid investment input-output association relationship is constructed through a deep learning network, a power grid investment decision problem is analyzed from the perspective of pure data, a transfer learning process is introduced, and data distribution characteristics and network relationship characteristics are migrated from other similar power grids through a small number of samples of the transfer learning process by utilizing the self-adaptive characteristic of the transfer learning process, so that the problem that training samples are insufficient in the association mining process of an existing data driving method is solved.
Need to check novelty before this filing date? Find Prior Art

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...