首页|运用电力大数据构建企业污染指数及监测分析

运用电力大数据构建企业污染指数及监测分析

扫码查看
电力大数据作为一种新的数据源,能够提供关于企业能源消耗和生产活动的实时、连续的数据.但现有方法均未考虑电力大数据对于企业污染指数的影响,导致研究使用的数据不完整,不能全面反映企业的污染行为.为此,文中运用电力大数据,构建了一种新的企业污染指数分析方法.根据企业用电来源与污染物排放结构,构建了企业污染评价指标体系,并确定了各指标的重要性标度和权重系数.通过熵权法计算得出综合指标得分,该得分反映了企业在污染物排放、环境影响和资源利用等方面的风险或影响程度.结果表明:不同企业间的污染指数存在一定的差异,其中化工业的企业污染指数最高为0.14,酒水制造业与橡胶制造业的污染指数相较来说较低,均为0.04.证明该方法能够有效显示出不同的企业污染指数存在的差异,具有参考价值.
Constructing enterprise pollution index and monitoring analysis using electricity big data
Electricity big data,as a new data source,can provide real-time and continuous data on enterprise energy consumption and production activities.However,existing methods have not taken into account the impact of electricity big data on the pollution index of enterprises,resul-ting in incomplete data used in research that cannot fully reflect the pollution behavior of enter-prises.To this end,a new method for analyzing enterprise pollution index was constructed using power big data in the article.Based on the electricity source and pollutant emission structure of the enterprise,a pollution evaluation index system for the enterprise was constructed,and the importance scale and weight coefficient of each index were determined.The comprehensive index score was calculated using the entropy weight method,which reflected the risk or impact level of the enterprise in terms of pollutant emissions,environmental impact,and resource utilization.The results show that there are certain differences in the pollution index among different enterpri-ses,with the highest pollution index of 0.14 in the chemical industry,and lower pollution indices of 0.04 in the beverage manufacturing and rubber manufacturing industries.The proposed meth-od can effectively display the differences in pollution indices among different enterprises and has reference value.

power big dataenterprise pollution indexweight coefficiententropy weight method

奚增辉、王卫斌、陆嘉铭、瞿海妮

展开 >

国网上海市电力公司,上海 200122

电力大数据 企业污染指数 权重系数 熵权法

2024

西安工程大学学报
西安工程大学

西安工程大学学报

CSTPCD
影响因子:0.473
ISSN:1674-649X
年,卷(期):2024.38(6)