MORE Visual Analytics: Unveiling the Power Behind our Energy Analytics Visualization Toolkit
An exclusive webinar where we take you behind the scenes of our Energy Analytics Visualization Toolkit. Discover the inner workings of this tool, including the theory behind the innovative cache system that supercharges its speed and scalability. Learn how our toolkit utilizes state-of-the-art energy analytics to detect issues such as underperformance, soiling, and yaw misalignment in renewable energy systems. Gain a deeper understanding of the technology driving sustainable energy solutions and how you can leverage it for optimized performance.
Discover the Power of MORE's Visualization Platform: A Quick Tutorial
Unleash the potential of our visualization platform in this brief tutorial. Learn how to explore map-based RES data with visually captivating charts and graphs. Gain insights through basic statistical analysis and interact with big geo-located time-series data collected from wind turbines and solar panels.
Incremental machine learning models for highfrequency big data 2nd MORE Webinar
IMLA Colloquium series: Health monitoring challenges in Renewable Energy Sources (RES) sector
Seshu Tirupathi, Giorgos Giannopoulos, Dhaval Patel, Manolis Terrovitis, Dhaval Salwala, Nikos Raftopoulos
Athena RC, INACCESS Netowrks
IT, big data and machine learning challenges in time series data - Renewable Energy Sources (RES) sector | Management of Real-time Energy Data
Dhaval Salwala, Prof. Ioannis Emiris, Dr. Shivkumar Kalyanaraman CTO, Energy & Mobility, Microsoft R&D India (& Azure Global), Dr. Paul Poncet (ENGIE, Head of Data Science for the Darwin Platform), Prof. Themis Palpanas, Dr. George E. Konstantoulakis (Inaccess), Prof. Themis Palpanas, Dr. Seshu Tirupathi (IBM Research Europe)
The first colloquium aims to understand the challenges in handling big data and machine learning algorithms in renewable energy sources sector. Traditionally, data in RES has been aggregated over 5-10 minute intervals and business use cases were built on this aggregated data for the RES sector. However, with lowering cost of sensors and communications, and increasing demand for high frequency updates and use cases, there is an exponential growth in the data generated by the devices. There are natural challenges of persistence and analytics on this data. Privacy and security add an additional layer of complexity. The colloquium will cover the use cases that arise from high frequency data and the technical challenges to handle this data and provide analytics on top.
Keynotes Speakers
The Software- and AI-Driven Future of Renewables (Shivkumar Kalyanaraman)
Deep decarbonization and the rapid electrification of energy will require greater penetration of renewables. As renewables penetration crosses 10-20% of the grid electricity demand (and other supply sources correspondingly adjust), the intermittency and volatility of renewable supply will increasingly dominate. Renewable supply and grid electricity demand matched via a combination of multiple markets, energy storage and an orchestrated portfolio of flexibility resources. The future of renewables will fundamentally be driven by software and AI on the cloud to manage this transition. This talk will unwrap the various challenges and opportunities around this transition.
Easy, Accurate, and Fast Complex Analytics on Big Data Series Collections: Renewable Energy Sources and Beyond (Themis Palpanas)
There is an increasingly pressing need, by several applications in diverse domains, for developing techniques able to manage and analyze very large collections of sequences, or data series. Examples of such applications come from various monitoring applications, including in power utility companies, where we need to apply machine learning techniques for knowledge extraction. It is not unusual for these applications to involve numbers of data series in the order of hundreds of millions to billions, which are often times not analyzed in their full detail due to their sheer size. However, no existing data management solution can offer native support for sequences and the corresponding operators necessary for complex analytics. In this talk, we describe our efforts in designing techniques for indexing and analyzing truly massive collections of data series that enable scientists to run complex analytics on their data. These techniques are orders of magnitude faster than the state of the art, and are applied, among others, on datasets derived from operation monitoring applications (e.g., from sensors on wind turbine farms), as well as remote sensing applications with the purpose of guiding predictive maintenance and operational optimization pipelines.
Optimizing operation and maintenance of renewable energy assets: some machine learning challenges (Paul Poncet)
Relying on the experience we have with Darwin, Engie’s digital platform that provides software solutions on top of time series collected from renewable assets in operation, we shall first give an overview of data science and predictive maintenance use cases we have been facing so far. Then, we shall reflect on the kind of machine learning.
