Abstract
This paper presents a detailed description of data predictive control (DPC) applied to a demand-side energy management system. Different from traditional model-based predictive control (MPC) algorithms, this approach introduces two model-free algorithms of artificial neural network (ANN) and random forest (RF) to make control strategy predictions on system operation, while avoiding the huge cost and effort associated with learning a grey/white box model of the physical system. The operating characteristics of electrical appliances, system energy consumption, and users’ comfort zones are also considered in the selected energy management system based on a real-time electricity pricing system. Case studies consisting of two scenarios (0% and 15% electricity price fluctuation) are delivered to demonstrate the effectiveness of the proposed approach. Simulation results demonstrate that the DPC controller based on ANN pays only 0.18% additional bill cost to maintain users’ comfort zones and system economy standardization while using only 0.096% optimization time cost compared with the MPC controller.
Highlights
According to a report from the United States Energy Information Administration (EIA), about 39%of total US electricity was consumed by residential buildings in 2018 [1]
Rule-based control (RBC) method proposed in [5] outperformed robust model predictive control (RMPC) with regard to energy-comfort trade-off when the model uncertainty is less than 30% or more than 67%
Compared with the root-mean-square error (RMSE) of artificial neural network (ANN)-data predictive control (DPC) with 15% fluctuation, the value of RMSE in random forest (RF)-DPC increases by 32.9%, which reveals the poor performance of RF in dealing with uncontrollable random noise like electricity price fluctuation
Summary
According to a report from the United States Energy Information Administration (EIA), about 39%. Two model-free algorithms of ANN and RF are selected to make control strategy predictions for a system operation, while avoiding the huge cost and effort associated with learning a grey/white box model of the physical system. Due to the difficulty in obtaining original system operation data and the lack of sensors to provide real-time measurements, a model-based predictive control method is selected as a classical and practical benchmark to produce previous information of electrical appliances in the energy management system [23]. An MPC method using a precise dynamic model based on a design code for civil buildings of China is utilized to produce the original system operation data, which serve as the training data for the machine learning algorithms, while avoiding the costs and efforts of system measurements.
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.
