Abstract
this paper proposed a variable input structure SVM prediction model based on state analysis. By identifying the key load characteristics in the load data and storing the load characteristics instead of the original load data, user load data can be realized more accurate and efficient. Based on the variable input structure SVM model of state analysis, the same state load is searched according to the results of state prediction in each period of the forecast day, and the same state historical load is used as the input factor of the model to predict. It effectively overcomes the interference of user power drift effect on load forecasting., and the forecasting accuracy is effectively improved.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.