Skip to Main content Skip to Navigation
Journal articles

A Fractional Brownian Motion Model for Forecasting Lost Load and Time Interval Between Power Outages

Abstract : A novel idea is proposed to forecast lost load and time interval between power outages based on the similarity between the series generated by a stochastic model and the actual series. The lost load obeys a power-law distribution, which can be described as a stochastic process with long-range dependence (LRD). Fractional Brownian motion (fBm) is a stochastic model with LRD, we discretize the stochastic differential equation (SDE) driven by fBm and the difference iterative equation is constructed for forecasting. By calculating the Hurst exponent of lost load series proves that it has LRD characteristics. The stochastics series produced by fBm has a strong similarity with the actual series when the Hurst exponent is taken into fBm model. Moreover, the forecasting accuracy is enriched by considering the appropriate sample size and forecasting step size. The same process for the analysis of lost load can be applied to forecast the time interval between power outages. The efficiency of the proposed model is demonstrated by a case study of the medium voltage power grid in Shanghai compared with other approaches. Finally, the value at risk (VaR) and the conditional value at risk (CVaR) as two system-level indices for assessment of future power outages.
Document type :
Journal articles
Complete list of metadata

https://hal-mines-paristech.archives-ouvertes.fr/hal-03479390
Contributor : Magalie Prudon Connect in order to contact the contributor
Submitted on : Tuesday, December 14, 2021 - 12:15:22 PM
Last modification on : Monday, January 3, 2022 - 2:54:01 PM

Links full text

Identifiers

Citation

Lijia Ren, Juequan Deng, Wanqing Song, Enrico Zio, Carlo Cattani. A Fractional Brownian Motion Model for Forecasting Lost Load and Time Interval Between Power Outages. IEEE Access, IEEE, 2021, 9, pp.6623-6632. ⟨10.1109/ACCESS.2020.3048499⟩. ⟨hal-03479390⟩

Share

Metrics

Les métriques sont temporairement indisponibles