Abstract
In a future Smart Grid context, increasing challenges in managing the stochastic local energy supply and demand are expected. This increased the need of more accurate energy prediction methods in order to support further complex decision-making processes. Although many methods aiming to predict the energy consumption exist, all these require labelled data, such as historical or simulated data. Still, such datasets are not always available under the emerging Smart Grid transition and complex people behaviour. Our approach goes beyond the state-of-the-art energy prediction methods in that it does not require labelled data. Firstly, two reinforcement learning algorithms are investigated in order to model the building energy consumption. Secondly, as a main theoretical contribution, a Deep Belief Network (DBN) is incorporated into each of these algorithms, making them suitable for continuous states. Thirdly, the proposed methods yield a cross-building transfer that can target new behaviour of existing buildings (due to changes in their structure or installations), as well as completely new types of buildings. The methods are developed in the MATLAB® environment and tested on a real database recorded over seven years, with hourly resolution. Experimental results demonstrate that the energy prediction accuracy in terms of RMSE has been significantly improved in 91.42% of the cases after using a DBN for automatically extracting high-level features from the unlabelled data, compared to the equivalent methods without the DBN pre-processing.
Highlights
Prediction of energy consumption as a function of time plays an essential role in the current transition to future energy systems
Deep Belief Networks (DBN) could be a way to naturally decompose the problem into sub-problems associated with different levels of abstraction
For a more comprehensive view of the datasets used in this paper we have shown in Fig. 3 the hourly evolution of the electrical energy consumption for a General Service (G) dataset, including
Summary
Prediction of energy consumption as a function of time plays an essential role in the current transition to future energy systems. E[ · ] ADRSThv Wvh E k M p, P Q t Z learning rate, ∀ ̨ ∈ [0, 1] discount factor, ∀ ∈ (0, 1) expected value operator the set of actions, ∀a ∈ A dataset the reward function the set of states, ∀s ∈ S transition probability matrix vector collecting all the hidden units, hj ∈ {0, 1} vector collecting all visible units, vi ∈ R matrix of all weights connecting v and h total energy function in the RBM model the number of hidden layers building energy consumption model probability value/vector the quality matrix time normalization function comprehensive discussion on the application of energy demand management to [9,14,17,18] They remain at the forefront of academic and applied research, all these methods require labeled data able to faithfully reproduce the energy consumption of buildings. We comprehensively explore and extended two reinforcement learning (RL) methods to predict the energy consumption at the building level using unlabelled historical data, namely State-Action-Reward-State-Action (SARSA) [25] and Qlearning [26].
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.
