Abstract
Rapid expansion of smart metering technologies has enabled large-scale collection of electricity consumption data and created the foundation for sensor-based load forecasting on individual buildings or even the household level. With continuously growing energy consumption, the importance of energy management including load forecasting is increasing in order to remedy the energy effect on the environment. Numerous machine learning techniques have been proposed for sensor-based load forecasting but most are offline approaches: the model is trained once and then used to infer future consumption. However, these approaches are not able to adapt to concept drift: for example, their accuracy will degrade when the building use changes or new equipment is installed. Thus, an approach capable of learning from new data as they arrive is needed. This paper proposes adaptive online ensemble learning with Recurrent Neural Network (RNN) and ARIMA for load forecasting under concept drift. The RNN part of the ensembles consists of Online Adaptive RNN as its underlying RNN learner has the ability to model temporal dependencies present in load data while its online nature enables continuous learning from arriving data. The adaptation to the concept drift is improved by adding Rolling ARIMA to the ensemble. The performance of the proposed approach has been examined on the four individual homes with different degrees of concept drift. The results show that the proposed ensemble achieves better accuracy than its constituent algorithms alone and, moreover, the analysis demonstrates the need to examine load forecasting approaches in respect to how they handle concept drift.
Highlights
The proposed AutoRegressive Integrated Moving Average (ARIMA)-Recurrent Neural Network (RNN) ensemble was evaluated on proprietary real-world data from four residential consumers obtained through the Connect My Data (CMD) platform
An example of Online Adaptive RNN performance in presence of the concept drift is shown in Fig. 13: graphs show Mean Squared Error (MSE) values for house High 2, window sizes 200 and 300, with the concept drift indicated with the coloured region
The proposed ensemble achieved the best overall average accuracy in terms of MSE. This average accuracy does not provide a complete picture of the algorithm’s behaviour as the error may vary greatly for different time periods. This can be observed in figures 11, 13, and 17 for Rolling ARIMA, Online Adaptive RNN, and the proposed ARIMA-RNN ensemble when the error values spike during the concept drift and occasionally even outside the drift
Summary
Traditional forecasting techniques need to be examined in respect to how they handle diverse energy consumption patterns present among individual energy consumers as well as changes in patterns over time. For energy forecasting with smart meter data, we need an ML approach capable of learning from new data as they arrive over time without the need to re-train the model or keep historical data [9]. The ’online’ descriptor reflects the fact that this paradigm continuously maintains its model and modifies the model as needed This learn-as-you-go approach alleviates the computational load and removes the need for all data to be present at once [6]. This paper proposes an online ARIMA-RNN ensemble, a load forecasting approach capable of learning from new drifting data as they arrive.
Sign-in/Register to view highlights & summary 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.
