节点文献
基于企业用电量与订单量的产能预警模型研究
Research on Capacity Early Warning Model Based on Enterprise Power Consumption and Order Quantity
【摘要】 为解决目前全球能源价格上涨、限电措施等因素造成电工装备企业产能下降、供货期延长,从而影响电网工程物资供应时效、工程无法按期投运等问题,本文提出了一种拟合供应商历史用电量信息和历史订单量信息关联关系的供应商产能预测方法。该方法是一个多模型的集成预测方法。首先是产能预警模型,通过负荷限制判断供应商能否正常生产,进行产能测算;然后根据用电户号接入系统,实现企业用电数据精准监测,并根据供应商用电量信息分析生产情况,从而判断剩余产能,测算剩余产能能否满足物资需求。该产能预警模型可以加强对供应商产能风险问题的防控力度,及时发现供应商的产能问题,实现及时报告、准确预警,预测准确性为90%,实现对供应商产能按照月度、季度、年度不同时间维度上的精准预警。
【Abstract】 In order to solve the problems caused by the rise of global energy prices and power rationing measures, such as the decrease in the production capacity of electrical equipment enterprises and the extension of the supply period, which affect the timeliness of the supply of power grid engineering materials and the project cannot be put into operation on time, this paper proposes a supplier capacity forecasting method fitting the correlation relationship between the supplier’s historical electricity consumption information and the historical order volume information.This method is a multi-model integrated forecasting method. The first is the capacity early warning model, which determines whether the supplier can produce normally through the load limit and calculates the capacity. The second is access the system according to the subscriber numbers accurately monitoring enterprise electricity data, and analyze the production situation according to the supplier electricity consumption information, so as to judge the surplus capacity and measure whether the surplus capacity can meet the material demand.This capacity early warning model can strengthen the prevention and control of suppliers’ capacity risks, discover suppliers’ capacity problems in time, achieve timely report and accurate early warning.The forecast accuracy is 90%.We can achieve accurate early warning of suppliers’ capacity in different time dimensions of monthly, quarterly and annual.
【Key words】 electricity consumption; load limit; shutdown warning; order quantity; green energy consumption;
- 【文献出处】 电力大数据 ,Power Systems and Big Data , 编辑部邮箱 ,2022年12期
- 【分类号】F426.61
- 【下载频次】15