Offshore oilfield medium-and-long-term power load prediction method

Abstract

The invention relates to an offshore oilfield medium-and-long-term power load prediction method. The offshore oilfield medium-and-long-term power load prediction method comprises the following steps:1) extracting characteristic quantities of power utilization characteristics of an exploitation link and an infusion link of the offshore oil field; 2) screening the extracted characteristic quantities; and 3) performing blind number regression prediction on the screened characteristic quantities, determining a blind number regression prediction model, realizing medium and long term power load prediction of the offshore oil field, and solving the problem of colinearity among the characteristic quantities. Compared with a traditional medium-and-long-term load prediction method, the offshore oilfield medium-and-long-term power load prediction method can adapt to the characteristic of diversification of offshore oilfield power load influence factors, provides prediction intervals of load requirements under different development trends of characteristic quantities on the basis of ensuring high prediction precision, reduces prediction risks, and has guiding significance for offshore oilfield exploitation.

Description

technical field [0001] The invention relates to a load forecasting method for offshore oilfields, in particular to a medium- and long-term electric load forecasting method for offshore oilfields which is applicable to the multiple characteristics of influencing factors of electric loads in offshore oilfields and realizes interval forecasting. Background technique [0002] The medium and long-term load forecasting of power system is the basis of power system planning and design, and also the guarantee of safe and economical operation of the power grid. Establishing a medium- and long-term power load forecasting model suitable for offshore oil reservoir development has important guiding significance for oilfield production. [0003] The current medium and long-term load forecasting methods can be mainly divided into two categories: traditional forecasting methods and modern forecasting methods. Traditional forecasting methods include industrial output value unit consumption me...

AI Technical Summary

Problems solved by technology

Traditional forecasting methods include industrial output value unit consumption method, power elasticity coefficient method, regression analysis method, etc. These methods are simple to operate and have good effects, and are widely used in actual engineering. However, this type of method only considers a single factor and is difficult to apply to offshore Diversification of Factors Affecting Electric Power Load in Oilfields

Modern forecasting methods include neural network forecasting methods, support vector machine forecasting methods, gray system forecasting methods, etc. These methods establish the relationship between input volume and output volume by analyzing a large number of historical sample data, and are suitable for sequences with strong volatility. There are few sample data for medium and long-term load forecasting, so this kind of method is difficult to apply in practice

Images