When analyzing power grid reliability, weather has always been one of the most important factors to consider, as it is one of the main causes of failures that happen on this infrastructure. Given its critical impact on the power grid, it is clear that understanding and studying weather-related failures is essential for maintaining a stable and resilient infrastructure. However, analyzing these failures can be very challenging due to the inherent differences and complexities between weather and power grid data. To address this, in our thesis work we developed a data pipeline in order to acquire, prepare, and integrate these diverse datasets into a unified relational database, with the ultimate goal of facilitating analyses of weather-related failures and their correlation with weather events. Once the database was completed, we performed various analyses, with the aim of identifying any potential trends and patterns in weather-related failures, as well as the weather conditions that pose greater risk to the power grid. Overall, from our results, we were able to find significant correlation between these failures and weather events, and revealed insights into how different weather conditions affect power grid reliability, thus demonstrating that the data structure we designed can be used as a solid base for these tasks. Moreover, while in this thesis our primary focus is on analyzing failures caused by weather conditions, the solution we developed is not strictly limited to these kind of analyses, but can be scaled to accommodate additional data and potentially serve as a foundation for conducting broader power grid studies.
Quando si analizza l’affidabilità della rete elettrica, il meteo è da sempre uno dei fattori più importanti da valutare, essendo una delle principali cause dei guasti che avvengono su quest’infrastruttura. Dato il suo impatto sulla rete elettrica, è evidente che comprendere e studiare i guasti dovuti a eventi atmosferici è essenziale per mantenere un’infrastruttura stabile e resiliente. Tuttavia, analizzare questi guasti può essere molto difficile a causa delle inerenti differenze e complessità che esistono tra i dati meteo e quelli della rete elettrica. Per affrontare questo problema, in questa tesi abbiamo sviluppato una data pipeline per acquisire, preparare ed integrare questi diversi dataset in un unico database relazionale, con lo scopo di facilitare analisi riguardanti guasti meteo e la loro correlazione con gli eventi atmosferici. Una volta che il database è stato completato, abbiamo eseguito varie analisi, con l’obiettivo di identificare eventuali trend e pattern legati ai guasti meteo, nonché quali condizioni meteorologiche rappresentino un rischio maggiore per la rete elettrica. Nel complesso, dai nostri risultati, siamo stati in grado di trovare una correlazione significativa tra questi guasti ed eventi meteorologici, e abbiamo raccolto informazioni su come diverse condizioni meteorologiche influenzano l’affidabilità della rete elettrica, dimostrando quindi come la struttura dati che abbiamo sviluppato possa essere usata come una base solida per questi lavori. Inoltre, nonostante in questa tesi ci siamo concentrati soprattutto su analizzare guasti elettrici causati da eventi meteo, la soluzione che abbiamo sviluppato non è strettamente limitata a questo tipo di analisi, ma può essere espansa per includere dati aggiuntivi e potenzialmente fungere da base per condurre studi più ampi sulla rete elettrica.
A Data Preparation Pipeline for the Analysis of the Influence of Weather Events on Power Grid Failures
Moschetti, Andrea;BAROZZI, CARLO
2023/2024
Abstract
When analyzing power grid reliability, weather has always been one of the most important factors to consider, as it is one of the main causes of failures that happen on this infrastructure. Given its critical impact on the power grid, it is clear that understanding and studying weather-related failures is essential for maintaining a stable and resilient infrastructure. However, analyzing these failures can be very challenging due to the inherent differences and complexities between weather and power grid data. To address this, in our thesis work we developed a data pipeline in order to acquire, prepare, and integrate these diverse datasets into a unified relational database, with the ultimate goal of facilitating analyses of weather-related failures and their correlation with weather events. Once the database was completed, we performed various analyses, with the aim of identifying any potential trends and patterns in weather-related failures, as well as the weather conditions that pose greater risk to the power grid. Overall, from our results, we were able to find significant correlation between these failures and weather events, and revealed insights into how different weather conditions affect power grid reliability, thus demonstrating that the data structure we designed can be used as a solid base for these tasks. Moreover, while in this thesis our primary focus is on analyzing failures caused by weather conditions, the solution we developed is not strictly limited to these kind of analyses, but can be scaled to accommodate additional data and potentially serve as a foundation for conducting broader power grid studies.File | Dimensione | Formato | |
---|---|---|---|
Thesis_Moschetti_Andrea_Carlo_Barozzi.pdf
accessibile in internet per tutti
Descrizione: Tesi
Dimensione
3.47 MB
Formato
Adobe PDF
|
3.47 MB | Adobe PDF | Visualizza/Apri |
Executive_Summary_Moschetti_Andrea_Carlo_Barozzi.pdf
accessibile in internet per tutti
Descrizione: Executive Summary
Dimensione
492.72 kB
Formato
Adobe PDF
|
492.72 kB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/222873