Temperature-Load Sensitivity Study for Adjusting MISO Day-ahead Load Forecast

被引:0
|
作者
Yan, Jiahong [1 ,2 ]
Zheng, Hui [3 ]
Lu, Ning [1 ,2 ]
机构
[1] North Carolina State Univ, Elect & Comp Engn Dept, Raleigh, NC 27606 USA
[2] North Carolina State Univ, Future Renewable Elect Energy Delivery & Manageme, Raleigh, NC 27606 USA
[3] MISO, Load Forecasting Engn, Carmel, IN 46032 USA
关键词
Load forecasting; temperature sensitivity; similar day; general linear regression; forecast adjustment;
D O I
暂无
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This paper presents the results of a temperature-load sensitivity study carried out at the Midcontinent Independent System Operator (MISO) for adjusting MISO day-ahead load forecast. As the area operated by MISO is growing rapidly, operators at MISO have to examine the day-ahead load forecast results generated by commercial software packages on a daily basis and manually correct anticipated discrepancies to enhance the forecast accuracy. To quantify the adjustment of the forecasted load, a series of temperature-load sensitivity studies are conducted using the actual MISO load data from past 5 years. A piecewise general linear model (GLM) is developed to capture the impact of time-dependent factors and temperature variations on the magnitude of MISO temperature-load sensitivity. A numerical study case compares the results before and after the tuning with the presented temperature-load sensitivity analysis.
引用
收藏
页数:5
相关论文
共 50 条
  • [1] Probabilistic Day-Ahead Load Forecast Using Quantile Regression Forests
    Lahouar, Ali
    Mejri, Amal
    Slama, Jaleleddine Ben Hadj
    2017 INTERNATIONAL CONFERENCE ON ENGINEERING & MIS (ICEMIS), 2017,
  • [2] Data quality analysis in day-ahead load forecast by means of LSTM
    Nespoli, Alfredo
    Ogliari, Emanuele
    Pretto, Silvia
    Gavazzeni, Michele
    Vigani, Sonia
    Paccanelli, Franco
    2020 20TH IEEE INTERNATIONAL CONFERENCE ON ENVIRONMENT AND ELECTRICAL ENGINEERING AND 2020 4TH IEEE INDUSTRIAL AND COMMERCIAL POWER SYSTEMS EUROPE (EEEIC/I&CPS EUROPE), 2020,
  • [3] In Day-Ahead Electricity Load Forecasting
    Klempka, Ryszard
    Swiatek, Boguslaw
    2009 10TH INTERNATIONAL CONFERENCE ON ELECTRICAL POWER QUALITY AND UTILISATION (EPQU 2009), 2009, : 313 - 317
  • [4] Day-ahead load forecast using random forest and expert input selection
    Lahouar, A.
    Slama, J. Ben Hadj
    ENERGY CONVERSION AND MANAGEMENT, 2015, 103 : 1040 - 1051
  • [5] Load2Load: Day-ahead load forecasting at aggregated level
    Yilmaz, Mustafa Berkay
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2022, 30 (07) : 2636 - 2653
  • [6] Forecasting quantiles of day-ahead electricity load
    Li, Z.
    Hurn, A. S.
    Clements, A. E.
    ENERGY ECONOMICS, 2017, 67 : 60 - 71
  • [7] Day-Ahead Electric Load Forecast for a Ghanaian Health Facility Using Different Algorithms
    Chaaraoui, Samer
    Bebber, Matthias
    Meilinger, Stefanie
    Rummeny, Silvan
    Schneiders, Thorsten
    Sawadogo, Windmanagda
    Kunstmann, Harald
    ENERGIES, 2021, 14 (02)
  • [8] Probabilistic Load Forecasting for Day-Ahead Congestion Mitigation
    Guerses-Tran, Gonca
    Flamme, Hendrik
    Monti, Antonello
    2020 INTERNATIONAL CONFERENCE ON PROBABILISTIC METHODS APPLIED TO POWER SYSTEMS (PMAPS), 2020,
  • [9] Day-Ahead and Intra-Day Building Load Forecast With Uncertainty Bounds Using Small Data Batches
    Lauricella, Marco
    Fagiano, Lorenzo
    IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2023, 31 (06) : 2584 - 2595
  • [10] Day-Ahead Building Load Forecasting with a Small dataset
    Lauricella, Marco
    Cai, Zhongtian
    Fagiano, Lorenzo
    IFAC PAPERSONLINE, 2020, 53 (02): : 13076 - 13081