The electric power system is changing. The changes include the integration of renewable resources, such as wind farms and solar plants, making the grid smarter so that it can react and adapt to changes and increase customer engagement. These changes of the power system have radical effects, which can only be tackled if it is digitized, so digital transformation of the power system is of paramount concern.Electrical energy management systems are therefore an integral part of the digitization process. Such systems typically provide the fundamental information and computation capability to perform real-time network analyses, to provide strategies for controlling system energy flows, and to determine the most economical mix of power generation, consumption, and trades. Currently, the maturity of digitization is at different levels for various parts of the electrical power system. Machine learning has been suggested as a tool for making smart grids that can adapt to sudden changes and long-term distributional shifts and recover from errors. The interest in implementing machine learning methods into energy management systems has grown in recent years, and many companies are taking the first steps.TrønderEnergi is a Norwegian power generation company that does exactly this. It aims at increasing the value of renewable energy and at the same time reducing the cost. In the context of hydropower and wind power, there are several use cases that undergo digital transformation in TrønderEnergi. Examples of such use cases are (1) hydropower trading, (2) wind power trading, and (3) predictive maintenance on wind farms and hydro plants. These use cases as well as the digital transformation processes are introduced in detail in this chapter along with our practical experience. We discuss how machine learning helps to improve the functioning of the existing systems and optimize operations. Inspired by these use cases, we believe digital transformation will continue to make inroads in other applied areas in energy management systems and form the digital electric power ecosystem.
We propose an approach to context-aware advertising in which context is defined by the products currently used by a consumer. Unlike more traditional approaches, consumers are neither identified nor tracked; instead, products are tagged. An interesting use-case scenario for this model is a product-aware outdoor advertising system that dynamically selects a product to advertise based on the products identified for one person or a group of people nearby. For example, RFID tags integrated into clothing of someone passing by a digital billboard could allow for determining preferences regarding style, fashion and brands. This information would be used by a digital billboard with an RFID reader to recommend and advertise complementary and other products. There would be no inherent connection between product information and the identity of the consumer; and therefore the privacy of the consumer would not be violated. Tagging and tracking of consumer products provides opportunities for more personalized and engaging marketing experiences without introducing a privacy risk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.