51 Citations (Scopus)

Abstract

In this paper, short-term forecast of wind farm generation is investigated by applying spatio-temporal analysis to extensive measurement data collected from a large wind farm where multiple classes of wind turbines are installed. Specifically, using the data of the wind turbines' power outputs recorded across two consecutive years, graph-learning based spatio-temporal analysis is carried out to characterize the statistical distribution and quantify the level crossing rate of the wind farm's aggregate power output. Built on these characterizations, finite-state Markov chains are constructed for each epoch of three hours and for each individual month, which accounts for the diurnal non-stationarity and the seasonality of wind farm generation. Short-term distributional forecasts and a point forecast are then derived by using the Markov chains and ramp trend information. The distributional forecast can be utilized to study stochastic unit commitment and economic dispatch problems via a Markovian approach. The developed Markov-chain-based distributional forecasts are compared with existing approaches based on high-order autoregressive models and Markov chains by uniform quantization, and the devised point forecasts are compared with persistence forecasts and high-order autoregressive model-based point forecasts. Numerical test results demonstrate the improved performance of the Markov chains developed by spatio-temporal analysis over existing approaches.

Original languageEnglish (US)
Article number6727513
Pages (from-to)1611-1622
Number of pages12
JournalIEEE Transactions on Power Systems
Volume29
Issue number4
DOIs
StatePublished - 2014

Fingerprint

Markov processes
Farms
Wind turbines
Economics

Keywords

  • Distributional forecast
  • graphical learning
  • Markov chains
  • point forecast
  • short-term wind power forecast
  • spatio-temporal analysis
  • wind farm

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Energy Engineering and Power Technology

Cite this

A spatio-temporal analysis approach for short-term forecast of wind farm generation. / He, Miao; Yang, Lei; Zhang, Junshan; Vittal, Vijay.

In: IEEE Transactions on Power Systems, Vol. 29, No. 4, 6727513, 2014, p. 1611-1622.

Research output: Contribution to journalArticle

@article{a3f60b79742b4299a86eba76fe2d5ebb,
title = "A spatio-temporal analysis approach for short-term forecast of wind farm generation",
abstract = "In this paper, short-term forecast of wind farm generation is investigated by applying spatio-temporal analysis to extensive measurement data collected from a large wind farm where multiple classes of wind turbines are installed. Specifically, using the data of the wind turbines' power outputs recorded across two consecutive years, graph-learning based spatio-temporal analysis is carried out to characterize the statistical distribution and quantify the level crossing rate of the wind farm's aggregate power output. Built on these characterizations, finite-state Markov chains are constructed for each epoch of three hours and for each individual month, which accounts for the diurnal non-stationarity and the seasonality of wind farm generation. Short-term distributional forecasts and a point forecast are then derived by using the Markov chains and ramp trend information. The distributional forecast can be utilized to study stochastic unit commitment and economic dispatch problems via a Markovian approach. The developed Markov-chain-based distributional forecasts are compared with existing approaches based on high-order autoregressive models and Markov chains by uniform quantization, and the devised point forecasts are compared with persistence forecasts and high-order autoregressive model-based point forecasts. Numerical test results demonstrate the improved performance of the Markov chains developed by spatio-temporal analysis over existing approaches.",
keywords = "Distributional forecast, graphical learning, Markov chains, point forecast, short-term wind power forecast, spatio-temporal analysis, wind farm",
author = "Miao He and Lei Yang and Junshan Zhang and Vijay Vittal",
year = "2014",
doi = "10.1109/TPWRS.2014.2299767",
language = "English (US)",
volume = "29",
pages = "1611--1622",
journal = "IEEE Transactions on Power Systems",
issn = "0885-8950",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A spatio-temporal analysis approach for short-term forecast of wind farm generation

AU - He, Miao

AU - Yang, Lei

AU - Zhang, Junshan

AU - Vittal, Vijay

PY - 2014

Y1 - 2014

N2 - In this paper, short-term forecast of wind farm generation is investigated by applying spatio-temporal analysis to extensive measurement data collected from a large wind farm where multiple classes of wind turbines are installed. Specifically, using the data of the wind turbines' power outputs recorded across two consecutive years, graph-learning based spatio-temporal analysis is carried out to characterize the statistical distribution and quantify the level crossing rate of the wind farm's aggregate power output. Built on these characterizations, finite-state Markov chains are constructed for each epoch of three hours and for each individual month, which accounts for the diurnal non-stationarity and the seasonality of wind farm generation. Short-term distributional forecasts and a point forecast are then derived by using the Markov chains and ramp trend information. The distributional forecast can be utilized to study stochastic unit commitment and economic dispatch problems via a Markovian approach. The developed Markov-chain-based distributional forecasts are compared with existing approaches based on high-order autoregressive models and Markov chains by uniform quantization, and the devised point forecasts are compared with persistence forecasts and high-order autoregressive model-based point forecasts. Numerical test results demonstrate the improved performance of the Markov chains developed by spatio-temporal analysis over existing approaches.

AB - In this paper, short-term forecast of wind farm generation is investigated by applying spatio-temporal analysis to extensive measurement data collected from a large wind farm where multiple classes of wind turbines are installed. Specifically, using the data of the wind turbines' power outputs recorded across two consecutive years, graph-learning based spatio-temporal analysis is carried out to characterize the statistical distribution and quantify the level crossing rate of the wind farm's aggregate power output. Built on these characterizations, finite-state Markov chains are constructed for each epoch of three hours and for each individual month, which accounts for the diurnal non-stationarity and the seasonality of wind farm generation. Short-term distributional forecasts and a point forecast are then derived by using the Markov chains and ramp trend information. The distributional forecast can be utilized to study stochastic unit commitment and economic dispatch problems via a Markovian approach. The developed Markov-chain-based distributional forecasts are compared with existing approaches based on high-order autoregressive models and Markov chains by uniform quantization, and the devised point forecasts are compared with persistence forecasts and high-order autoregressive model-based point forecasts. Numerical test results demonstrate the improved performance of the Markov chains developed by spatio-temporal analysis over existing approaches.

KW - Distributional forecast

KW - graphical learning

KW - Markov chains

KW - point forecast

KW - short-term wind power forecast

KW - spatio-temporal analysis

KW - wind farm

UR - http://www.scopus.com/inward/record.url?scp=84903191929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903191929&partnerID=8YFLogxK

U2 - 10.1109/TPWRS.2014.2299767

DO - 10.1109/TPWRS.2014.2299767

M3 - Article

VL - 29

SP - 1611

EP - 1622

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

SN - 0885-8950

IS - 4

M1 - 6727513

ER -