Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
In power systems, power load forecasting is essential to ensure the reliability and efficiency of power supply. Since power load is affected by many factors, including weather, seasonality, and social activities, its patterns and changes are complex and diverse, and traditional forecasting methods may make it difficult to meet demand. In this backg...
Context in source publication
Context 1
... algorithm evaluates the similarity degree of each data in the data set by similarity measurement method and divides the data with high similarity into the same set. The clustering process of the K-means algorithm consists of the following key steps: As shown in Figure 1. x , its distance from the K initialised clustering centres is calculated and the data object is assigned to the dataset belonging to the cluster centre with the nearest distance. ...
Citations
Material demand forecasting has a profound impact on the supply chain and is an important prerequisite for manufacturing enterprises to produce. In order to accurately predict the material demand of enterprises, this paper proposes a material demand forecasting algorithm based on multi-dimensional feature fusion (DFMF). Secondly, in order to obtain the spatial features, the vector representation of the relevant materials of a material is obtained through the attention mechanism. Then, the authors aggregate the relevant material representation and material vector representation of materials to obtain the final material vector representation through aggregation function. Then the final material vector representation under different time scales is used as input, and the prediction value of material demand is obtained by using BP neural network. Finally, experiments show that the model can effectively obtain multi-dimensional features of materials for prediction, and the prediction results have high accuracy.
