A Unit Load Forecasting Method Based on Time Series Similarity

Abstract

The present invention relates to a unit load forecasting method based on time series similarity, including step 1): obtaining the current time t0, and obtaining the period corresponding to the historical day according to the historical matching time length T (unit h), and obtaining the previous time period from the historical database The historical matching time series of the i-th day; step 2): average the time series by hour according to the following formula; step 3): perform difference processing on the time series according to the following formula; step 4): use the weighted Euclidean distance method Time series similarity matching is based on the principle of the smallest Euclidean distance, and the most similar day is the previous s day. The beneficial effect of the present invention is: the unit load online prediction model is established by using the method of time series similarity matching; the present invention is an online analysis method, which can extract more historical load change laws; the present invention has high prediction accuracy and can satisfy The actual needs of the project, but the traditional prediction error is relatively large.

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