Abstract
Power forecasting is an integral part of the Demand Response design philosophy for power systems, enabling utility companies to understand the electricity consumption patterns of their customers and adjust price signals accordingly, in order to handle load demand more effectively. Since there is an increasing interest in real-time automation and more flexible Demand Response programs that monitor changes in the residential load profiles and reflect them according to changes in energy pricing schemes, high granularity time series forecasting is at the forefront of energy and artificial intelligence research, aimed at developing machine learning models that can produce accurate time series predictions. In this study we compared the baseline performance and structure of different types of neural networks on residential energy data by formulating a suitable supervised learning problem, based on real world data. After training and testing long short-term memory (LSTM) network variants, a convolutional neural network (CNN), and a multi-layer perceptron (MLP), we observed that the latter performed better on the given problem, yielding the lowest mean absolute error and achieving the fastest training time.
Highlights
The evolution of the smart grid and smart metering technology has enabled electricity providers to develop more sophisticated Demand Response (DR) programs in order to influence the consumption patterns of their customers by adjusting pricing signals
In search of greater Demand Response flexibility and optimization as well as better third-party support through automation there is a lot of ongoing research in the field that is focused on the development of more precise load forecasting techniques, in order to obtain even more dynamic price signal adjustments
In order to evaluate the performance of the neural networks we studied in this work, we needed to define the performance metric selected for our machine learning tasks, as well as describe our assumptions towards the baseline performance of each neural network
Summary
The evolution of the smart grid and smart metering technology has enabled electricity providers to develop more sophisticated Demand Response (DR) programs in order to influence the consumption patterns of their customers by adjusting pricing signals. Demand Response programs exploit the dependencies of the information streams that flow between customers and suppliers Customers allow for their load profiles to be created and scrutinized, by providing smart meter data that reflect their consumption patterns; the data are derived from the daily operation of their devices. Suppliers are able to interpret that data, and after identifying the demand trends, they can reflect them on supply expectations via price signal alterations that, in turn, can shift or change consumption patterns. In this way, electricity demand may be handled in a dynamic environment. There is a considerable contribution from the areas of artificial intelligence and machine learning to the energy sector by way of various models and techniques aimed at managing and predicting real-time price and load fluctuations [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
