Method and system for predicting short-term power load of micro-grid of offshore oilfield group

Abstract

The invention discloses a method and system for predicting the short-term power load of a micro-grid of an offshore oilfield group. The global searching capacity is high, and the prediction precisionand calculation efficiency are higher. The method comprises the steps that respective upper and lower limit values of a penalty parameter C and a nuclear parameter sigma for a support vector machine (SVM) are set; the dimension of a position vector, the maximum iteration frequency and the number of dragonfly individuals of an improved dragonfly algorithm (IDA) are set; behavior parameters of the dragonfly individuals are initialized; current adaptive values of the dragonfly individuals in the IDA are calculated; two generations of the dragonfly individuals are sorted according to mapping, andthe corresponding maximum adaptive value is calculated and saved; the positions of food and natural enemies in the IDA are updated; behaviors of the dragonfly individuals in the IDA are updated; the positions of the dragonfly individuals in the IDA are updated; when the maximum iteration frequency is achieved, according to the positions of the dragonfly individuals corresponding to the saved maximum adaptive value, the penalty parameter C and the nuclear parameter sigma of the SVM are set, and a prediction module is established based on the SVM to predict the short-term power load of the micro-grid of the offshore oilfield group.

Description

technical field [0001] The invention relates to the technical field of short-term load forecasting of power systems, in particular to a method and system for short-term power load forecasting of offshore oil field group microgrids. Background technique [0002] Power system short-term load forecasting usually refers to the process of forecasting the power demand for the next day to one week based on historical load data and other factors such as weather, seasons, and temperature. It is the basis for power dispatching departments to allocate power and directly affects the safety and reliability of power systems. run. The offshore oilfield microgrid is gradually developed from the ship power system, and its load is mostly electric submersible pumps, and the load changes relatively large. The platform is powered by diesel engines and gas turbine generator sets, and the power generation capacity is very limited. Therefore, improving the accuracy of short-term load forecasting ...

AI Technical Summary

Problems solved by technology

However, the above improved SVM algorithm is relatively complex and the modeling speed is relatively slow

When the optimal iterative selection is made, it is difficult for the SVM parameters to reach the global optimum

Images