Wind resource simulated estimation method for region without wind measurement records

Abstract

The invention provides a wind resource simulated estimation method for a region without wind measurement records, belonging to the technical field of wind resource evaluation. The method comprises the following steps: establishing a data structure of an artificial intelligence network model in a computer; inputting raw wind resource data into the artificial intelligence network model; computing to obtain the relationship between the input layer and output layer of the artificial intelligence network model; and inputting wind resource data of the adjacent wind measurement recording region, which has the same time sequence as the to-be-estimated wind resource data of the region without wind measurement records, into the input layer of the artificial intelligence network model, and obtainingthe to-be-estimated wind resource data according to the established relationship between the input layer and output layer. The method solves the technical problem of how to evaluate the wind resources in the wind electric field under the conditions of lacking in wind measurement data and terrain data of the wind electric field.

Description

technical field [0001] The invention belongs to the technical field of wind resource assessment, and in particular relates to a method for simulating and calculating wind resources in areas without wind measurement records. Background technique [0002] The preliminary work of wind farm development and design is the macro site selection and preliminary feasibility study or feasibility study design of the proposed wind farm. In the feasibility study stage of wind farm construction, it is necessary to conduct wind resource assessment for the proposed wind farm. The purpose of the assessment is mainly to provide a basis for determining the installed capacity of the wind farm and the selection and layout of wind turbines, so as to facilitate the economic evaluation of the entire project. The key issue in wind power development is to clearly understand the wind resource status of the proposed wind farm, and the prerequisite for the evaluation is to have long-term measured data in...

AI Technical Summary

Problems solved by technology

Dimensional upscaling is to map samples to high-dimensional spaces. In general, this will increase the complexity of calculations. However, for problems such as classification and regression, it is likely that sample sets that cannot be processed linearly in low-dimensional sample spaces will be processed in high-dimensional space. In the dimensional feature space, linear division (or regression) can be achieved through a linear hyperplane

Images