改进ID3算法实现智能调度负荷特性分析及其可视化研究

针对传统ID3算法偏向于选择取值较多的属性问题，提出了改进的ID3算法，同时考虑决策树两层结点的信息增益，又引入了密合度概念，使决策树生成的规模相对较小，能够减小算法复杂度，提高挖掘速度和效率．运用改进的算法分析了智能调度用电负荷特性，建立了决策树，并结合可视化技术展示了业务分析数据和模型．实例运行结果能够满足电网业务功能需求，支持智能调度运营，具有较高的应用价值．

Intelligent Dispatching Load Characteristics Analysis Based on Improved ID3 and Visualization Research

The paper improves the ID3 algorithm based on calculating the information plus of decision tree＇s two layer node,to avoid the preference bias in selecting attributes with multiple values. The paper defines the concept of the concourse density to reduce the size of decision tree, and the complexity of algo- rithm. This paper presents the example of intelligent dispatching load characteristics analysis based on im- proved ID3,gives the structure of decision tree. Meanwhile,this paper introduces the visualization applica- tion of the business data. It is indicated that the result suffices the requirement and operation of intelligent dispatching. It is effective when it is applied.