AI System for Short Term Prediction of Hourly Electricity Demand

被引:0
|
作者
Markowska, Malgorzata [1 ]
Sokolowski, Andrzej [2 ]
Migut, Grzegorz [3 ]
Strahl, Danuta [4 ]
机构
[1] Wroclaw Univ Econ & Business, Wroclaw, Poland
[2] Warsaw Management Univ, Coll Humanum, Warsaw, Poland
[3] StatSoft Poland, Krakow, Poland
[4] WSB Univ, Dabrowa Gornicza, Poland
来源
ARTIFICIAL INTELLIGENCE-ECAI 2023 INTERNATIONAL WORKSHOPS, PT 2, XAI3, TACTIFUL, XI-ML, SEDAMI, RAAIT, AI4S, HYDRA, AI4AI, 2023 | 2024年 / 1948卷
关键词
Electricity Demand; Forecasting Models; Neural Networks; PRICES;
D O I
10.1007/978-3-031-50485-3_29
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Companies supplying electrical energy rely mainly on long term agreements with electricity produsers, but on the other hand the actual demand should be precisely predicted for 48 h ahead, to take into account the actualweather conditions. Some time series models can be used for this purpose, and the best results can be achieved by combining forecasts from regression models, exponential smoothing, ARIMA models and neural networks. In practice - more popular are average demand profiles showing the average demand distribution over 24 h. We propose to build an AI system to choose the future profile. First - from the historical data - daily profiles are obtained, by cutting the time series into 24-h periods. Then, these empirical profiles are clustered with hierarchic and non-hierarchic clustering procedures to form homogeneous groups (types of profiles). Finally the classification methods are applied using weather data and observed demand from previous days (up to one week backwards). The measure for the forecasting evaluation has been proposed. Out of the tested classification methods, neural networks performed the best, followed by some voting procedures.
引用
收藏
页码:269 / 276
页数:8
相关论文
共 50 条
  • [21] Households' hourly electricity consumption and peak demand in Denmark
    Andersen, Frits Moller
    Baldini, Mattia
    Hansen, Lars Garn
    Jensen, Carsten Lynge
    APPLIED ENERGY, 2017, 208 : 607 - 619
  • [22] Short-Term National Power System Electricity Demand Forecasting using the MARSplines Method
    Czapaj, Rafal
    Benalcazar, Pablo
    Kaminski, Jacek
    PRZEGLAD ELEKTROTECHNICZNY, 2019, 95 (07): : 133 - 136
  • [23] Hot weather and residential hourly electricity demand in Italy
    Alberini, Anna
    Prettico, Giuseppe
    Shen, Chang
    Torriti, Jacopo
    ENERGY, 2019, 177 : 44 - 56
  • [24] Forecasting Hourly Electricity Demand Using a Hybrid Method
    Cevik, Hasan Huseyin
    Harmanci, Huseyin
    Cunkas, Mehmet
    2017 INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS AND DEVICES (ICCED 2017), 2017, : 8 - 12
  • [25] Modeling and forecasting hourly electricity demand by SARIMAX with interactions
    Elamin, Niematallah
    Fukushige, Mototsugu
    ENERGY, 2018, 165 : 257 - 268
  • [26] Nonlinear dynamics of hourly ozone concentrations: Nonparametric short term prediction
    Chen, JL
    Islam, S
    Biswas, P
    ATMOSPHERIC ENVIRONMENT, 1998, 32 (11) : 1839 - 1848
  • [27] SHORT-TERM PREDICTION OF HOURLY TRAFFIC FLOWS IN HONG KONG
    Tam, Mei-Lam
    Lam, William H. K.
    Tang, Y. F.
    TRANSPORTMETRICA: ADVANCED METHODS FOR TRANSPORTATION STUDIES, 2004, : 360 - 369
  • [28] Global vs. Local Models for Short-Term Electricity Demand Prediction in a Residential/Lodging Scenario
    Buonanno, Amedeo
    Caliano, Martina
    Pontecorvo, Antonino
    Sforza, Gianluca
    Valenti, Maria
    Graditi, Giorgio
    ENERGIES, 2022, 15 (06)
  • [29] Performance Analysis of Short-Term Electricity Demand with Meteorological Parameters
    Chapagain, Kamal
    Sato, Tomonori
    Kittipiyakul, Somsak
    2017 14TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING/ELECTRONICS, COMPUTER, TELECOMMUNICATIONS AND INFORMATION TECHNOLOGY (ECTI-CON), 2017, : 330 - 333
  • [30] Performance Analysis of Short-Term Electricity Demand with Atmospheric Variables
    Chapagain, Kamal
    Kittipiyakul, Somsak
    ENERGIES, 2018, 11 (04)