Unit load prediction method based on time sequence similarity

Abstract

The invention relates to a unit load prediction method based on time sequence similarity, which comprises the following steps of 1) obtaining a current moment t0, obtaining a time period correspondingto a historical day according to a historical matching time length T (unit h), and obtaining a historical matching time sequence of the previous i-th day from a historical database; 2), performing the averaging processing on the time sequence according to the following formula by hours; 3), performing difference processing on the time sequence according to the following formula; and 4) carrying out time sequence similarity matching by using a weighted Euclidean distance method, and taking the minimum Euclidean distance as the principle to obtain the most similar day which is the previous s-thday. The method has the beneficial effects that a unit load online prediction model is established by using a time sequence similarity matching method; the method is an online analysis method, and more historical load change rules can be extracted; the method is high in prediction precision, can meet the actual needs of engineering, and is larger in traditional prediction error.

Description

technical field [0001] The invention relates to a load forecasting method for a thermal power unit, in particular to a unit load forecasting method based on time series similarity. Background technique [0002] Optimizing operation has always been an important means for coal-fired units to improve efficiency and reduce energy consumption. However, at present, large-scale coal-fired units have to participate in deep peak regulation. The units are often in the process of dynamic changes, and the thermal parameters of the units are also constantly changing, which brings new challenges to the optimal operation of the units. The premise of proposing a reliable optimization strategy is to be able to predict the thermal parameters, and most of the thermal parameters are closely related to the unit load, so the unit load forecasting work is particularly important. [0003] Genset load forecasting is to determine the load data at a specific moment in the future based on the operatin...

AI Technical Summary

Problems solved by technology

However, the modeling process of the classic model is relatively complicated, and the method has high requirements on the accuracy of historical data, and the abnormal data has a great influence on the prediction; when the weather and temperature changes little, the model is easy to obtain satisfactory results; large or encountering holidays, etc., this method has a large prediction error, and the longer the number of prediction steps, the worse the prediction accuracy

Images