Register now After registration you will be able to apply for this opportunity online.
Master's Thesis / Semester Project at ETH Zurich: Energy Savings and Load Shifting of Customer Demand under Dynamic Grid-usage Tariffs
Showcasing energy savings and load shifting potential of residential customers' electricity demand under time-dependent grid-usage tariffs.
Keywords: Energy, Smart Meter Data, Data Analysis, Sustainability
The increasing deployment of decentralized renewable energy sources and the electrification of the transport and heating sectors place great demands on the distribution grid. One approach to meet these challenges are time-dependent grid usage tariffs, which are intended to incentivise grid-beneficial behavior. Such price signals can not only influence customers power consumption, but also serve as a steering signal for automated loads (water boilers, heat pumps, and electric vehicles). The OrtsNetz project test different time-dependent grid tariffs in a real-world pilot study with more than 500 participants.
The increasing deployment of decentralized renewable energy sources and the electrification of the transport and heating sectors place great demands on the distribution grid. One approach to meet these challenges are time-dependent grid usage tariffs, which are intended to incentivise grid-beneficial behavior. Such price signals can not only influence customers power consumption, but also serve as a steering signal for automated loads (water boilers, heat pumps, and electric vehicles). The OrtsNetz project test different time-dependent grid tariffs in a real-world pilot study with more than 500 participants.
You will analyze timeseries data from over 3000 smart electricity meters to identify the impact of dynamic tariffs on energy demand and power peaks using methods ranging from simple statistical analysis to advanced machine learning models. This data is furthermore augmented by results from customer surveys and login behavior on an energy monitoring portal.
You will analyze timeseries data from over 3000 smart electricity meters to identify the impact of dynamic tariffs on energy demand and power peaks using methods ranging from simple statistical analysis to advanced machine learning models. This data is furthermore augmented by results from customer surveys and login behavior on an energy monitoring portal.
We are searching for highly motivated students with a strong background in computer science and data analysis. You should be proficient in creating clear and comprehensible Python scripts that can be reused by other parties to explore and analyze large datasets. You should have experience cleaning and organizing data and applying relevant statistical models.
Interested students are invited to send an email with their CV, transcript of records, and other relevant documents to Markus Kreft at mkreft@ethz.ch.
We are searching for highly motivated students with a strong background in computer science and data analysis. You should be proficient in creating clear and comprehensible Python scripts that can be reused by other parties to explore and analyze large datasets. You should have experience cleaning and organizing data and applying relevant statistical models. Interested students are invited to send an email with their CV, transcript of records, and other relevant documents to Markus Kreft at mkreft@ethz.ch.