miniming
Почетный гость
Зарегистрирован: 20.12.2020
Сообщения: 146
|
 Добавлено: Пт Фев 12, 2021 12:38 pm Заголовок сообщения: Weather Analytics Move From Predicting Storms |
 |
|
Weather Analytics Move From Predicting Storms To Predicting Outages For Better Grid Resiliency
Recent weather events including a major Nor’easter, crippling cold from the Polar Vortex, and even rogue tornado events have once again brought into focus the resiliency of utilities. Even though utility companies are continually evaluating their grid systems and investing in resilience measures, extreme events, or in this case a convergence of events, can cause power outages that last days, even weeks, across multiple states and regions. For example, the damage done by Superstorm Sandy in 2012 was unprecedented in its size and scope, with approximately 10 million customers in 24 states losing power and requiring the mutual efforts of over 80 utilities to respond. With the rise in extreme events, it is even more important to prepare for the “unprecedented.”
The ability to forecast and manage weather events has benefited from digital transformation in recent years, giving utilities access to sophisticated, predictive weather analytics. Predictive analytics is collected data to predict what might happen based on historical and real-time data.
In weather, this includes numerous models that consider a number of atmospheric conditions and data from multiple sources to suggest a realm of scenarios or probabilities. These powerful datasets can help prepare for the efficient, effective coordination of storm-related power outages.
PSEG Long Island is one of many utilities that has been refining a prediction system aimed at anticipating a storm system’s impact, based on elements such as storm data, storm track, and vegetation. Using the expansive dataset, the utility has insights to better determine likely damage locations and the scope of future outages. Ultimately, it will help a utility determine the required crews and resources. PSEG can develop a strategic plan to deploy assets prior to a storm’s arrival, rather than reacting in the aftermath.
The quick deployment of crews to respond to outages is always critical, and in large weather events utilities often rely on mutual assistance as part of the restoration process and contingency planning. As COVID continues to be a health and safety risk for additional crews, better outage prediction can prepare utilities or call in crews before the event occurs.
While predictive analytics are a proven advanced decision-making tool, some utilities are testing the advantages of machine learning, or artificial intelligence (AI). While both approaches rely on historical data and multiple data sources, predictive analytics relies on human interaction to create, test, and validate the data. Machine learning takes historical outage data collected and allows a computer to generate predictions for future needs based on forecasted weather conditions. It understands how infrastructure has responded to past storms including learning differences in network hardening, realizing the age of individual infrastructure components and maintenance practices. These datasets will yield a baseline of potential outages from upcoming storms.
Read More : pg slot |
|
FAQ
Поиск
Пользователи
Группы
Регистрация
Профиль
Войти и проверить личные сообщения
Вход
