Caisheng Wang, Yang Wang, Carol J. Miller, Jeremy Lin
{"title":"使用机器学习方法实时估计PJM市场区域的每小时边际排放量","authors":"Caisheng Wang, Yang Wang, Carol J. Miller, Jeremy Lin","doi":"10.1109/PESGM.2016.7741759","DOIUrl":null,"url":null,"abstract":"There has been no marginal emission information and/or marginal fuel mix data published by the regional transmission organizations (RTOs) or independent system operators (ISOs) in real-time. This paper presents a support vector machine (SVM) based method to estimate and predict hourly marginal emissions and marginal fuel mix in real-time in the PJM market area. Input to our SVM-based model includes a variety of publicly available data including the real-time locational marginal prices (LMPs), load demand, wind generation, historical marginal fuel data, and other information (such as day of the week and holidays). The results from the SVM are compared with real data from the years 2014 and 2015.","PeriodicalId":155315,"journal":{"name":"2016 IEEE Power and Energy Society General Meeting (PESGM)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"Estimating hourly marginal emission in real time for PJM market area using a machine learning approach\",\"authors\":\"Caisheng Wang, Yang Wang, Carol J. Miller, Jeremy Lin\",\"doi\":\"10.1109/PESGM.2016.7741759\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"There has been no marginal emission information and/or marginal fuel mix data published by the regional transmission organizations (RTOs) or independent system operators (ISOs) in real-time. This paper presents a support vector machine (SVM) based method to estimate and predict hourly marginal emissions and marginal fuel mix in real-time in the PJM market area. Input to our SVM-based model includes a variety of publicly available data including the real-time locational marginal prices (LMPs), load demand, wind generation, historical marginal fuel data, and other information (such as day of the week and holidays). The results from the SVM are compared with real data from the years 2014 and 2015.\",\"PeriodicalId\":155315,\"journal\":{\"name\":\"2016 IEEE Power and Energy Society General Meeting (PESGM)\",\"volume\":\"55 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-07-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE Power and Energy Society General Meeting (PESGM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/PESGM.2016.7741759\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Power and Energy Society General Meeting (PESGM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PESGM.2016.7741759","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Estimating hourly marginal emission in real time for PJM market area using a machine learning approach
There has been no marginal emission information and/or marginal fuel mix data published by the regional transmission organizations (RTOs) or independent system operators (ISOs) in real-time. This paper presents a support vector machine (SVM) based method to estimate and predict hourly marginal emissions and marginal fuel mix in real-time in the PJM market area. Input to our SVM-based model includes a variety of publicly available data including the real-time locational marginal prices (LMPs), load demand, wind generation, historical marginal fuel data, and other information (such as day of the week and holidays). The results from the SVM are compared with real data from the years 2014 and 2015.