Data-driven unit commitment intelligent decision-making method based on E-Seq2Seq technology

A unit combination, data-driven technology, applied in the research field of unit combination decision-making method, can solve the problem that the unit combination elastic multi-sequence mapping type sample cannot be applied, etc.

CN110674460AActive Publication Date: 2020-01-10CHINA THREE GORGES UNIV
3 Cites 3 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2020-01-10

Smart Images

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

Abstract

A data-driven unit commitment intelligent decision-making method based on an E-Seq2Seq technology, comprising the steps: 1, carding the types and structures of input and output sequences of a unit commitment model, and forming a unit commitment elastic multi-sequence mapping type sample; 2, constructing a unit commitment deep learning model based on an E-Seq2Seq technology by taking the GRU as a neuron; and 3, carrying out deep learning on the unit combination deep learning model. Compared with the existing intelligent decision-making method, the data-driven unit commitment intelligent decision-making method disclosed by the invention can consider the influence of multi-type and multi-dimensional input factors on the unit commitment decision-making at the same time, and can adapt to the elastic change of sample types and dimensions, so that the decision-making precision is higher.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of electric power system and automation research, and in particular relates to the research of a unit combination decision-making method based on a deep learning intelligent algorithm. Background technique

[0002] A market-oriented power system often requires an independent power market operator (Independent System Operators, ISO) with powerful computing capabilities to implement market supervision and formulate intelligent and refined day-ahead power generation plans. The unit combination problem is one of the important theoretical foundations for the decision-making of the electricity market and the preparation of the generation plan. In recent years, with the extensive application of new energy technologies such as electric vehicles, renewable energy, and demand-side management, the theoretical and technical challenges faced by power market decision-making have also emerged in an endless stream. Therefore, it is ...

Examples

Embodiment

[0106] In order to verify the correctness and effectiveness of the method of the present invention, the following three methods are used to solve the calculation examples of the present invention, and the calculation results are compared and analyzed.

[0107] Method 1: The method of the literature "Research on intelligent decision-making method of unit combination with self-learning ability based on data", that is, a data-driven unit combination decision-making method based on a single LSTM structure;

[0108] Method 2: A data-driven unit combination decision-making method based on a single GRU structure;

[0109] Method 3: Based on the E-Seq2Seq technology, a data-driven unit combination intelligent decision-making method based on a composite GRU structure is proposed, which is the method of the present invention.

[0110]The MAE values ​​in this chapter are the unit combination decision results (unit combination sample data) based on calculations. That is to say, the unit...