Open Access
Gumbel copula based aggregated net load forecasting for modern power systems
Author(s) -
Sreekumar Sreenu,
Sharma Kailash Chand,
Bhakar Rohit
Publication year - 2018
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2018.5472
Subject(s) - gumbel distribution , copula (linguistics) , renewable energy , computer science , electric power system , probabilistic forecasting , reliability engineering , scheduling (production processes) , wind power , mathematical optimization , probabilistic logic , econometrics , engineering , statistics , extreme value theory , mathematics , power (physics) , artificial intelligence , physics , quantum mechanics , electrical engineering
Wind and solar have major share among the growing renewable penetration, due to their extensive availability and improved technologies. Both wind and solar generation are highly uncertain and intermittent as compared to system load. The increased number of such uncertain and intermittent variables necessitates complex multivariate operational strategies for system operation. A compilation of different uncertain and intermittent variables such as load, wind and solar generation, to a single uncertain variable called net load, reduces system operational planning complexity. Net load is the difference between total load and renewable generation. Thus, conventional generation units have to be scheduled for net load. Prior knowledge about net load can help optimum operational planning such as generation scheduling and power system flexibility estimations. There have been significant advancement in load and renewable generation forecasting over the last decades. Still, there is little attention towards net load forecasting (NLF). This study proposes a novel NLF model using Gumbel copula based joint probability distribution for load, wind and solar generation forecasting error aggregation. Gumbel copula covers all extreme forecasting errors due to max‐stable property. Proposed model uses modified Grey index models for forecasting. Results show that proposed model has strong potential in very short‐term NLF.