Overhead lines Dynamic Line rating based on probabilistic day-ahead forecasting and risk assessment
| Autor: | George Kariniotakis, Andrea Michiorri, Romain Dupin |
|---|---|
| Přispěvatelé: | Centre Procédés, Énergies Renouvelables, Systèmes Énergétiques (PERSEE), MINES ParisTech - École nationale supérieure des mines de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL) |
| Rok vydání: | 2019 |
| Předmět: |
[STAT.AP]Statistics [stat]/Applications [stat.AP]
Computer science 020209 energy [SPI.NRJ]Engineering Sciences [physics]/Electric power 020208 electrical & electronic engineering Probabilistic logic Energy Engineering and Power Technology 02 engineering and technology 7. Clean energy Reliability engineering probabilistic forecasts Smart grid [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] Line (geometry) 0202 electrical engineering electronic engineering information engineering Overhead (computing) Point (geometry) Ampacity Electrical and Electronic Engineering smart grid Risk assessment Dynamic Line Rating Overhead line Numerical Weather Predictions |
| Zdroj: | International Journal of Electrical Power and Energy Systems International Journal of Electrical Power and Energy Systems, Elsevier, 2019, 110, pp.565-578. ⟨10.1016/j.ijepes.2019.03.043⟩ |
| ISSN: | 0142-0615 |
| Popis: | International audience; Dynamic Line Rating is a technology devised to modify an overhead line's current-carrying capacity based on weather observation. The benefits of this modification may include reduced congestion costs, an increased renewable energy penetration rate, and improved network reliability. DLR is already well developed, but few papers in the literature investigate DLR day-ahead forecasting. The latter is central to DLR development since many of the decisions related to grid management are taken at least on a day-ahead basis. In this paper, two problems related to DLR forecasts are dealt with: how to achieve precise, reliable calculations of day-ahead forecasts of overhead line ampacity and how to define a methodology to calculate safe rating values using these forecasts. On the first point, four machine-learning algorithms were evaluated, identifying the best approach for this problem and quantifying the potential performance. On the second point, the developed methodology was tested and compared to the current static line rating approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect