Abstract
Abstract
Accurately predicting the energy consumption of embedded devices has important implications for improving system performance and stability, resolving energy consumption anomalies and faults, and developing energy management strategies. In addition, it can promote the rational use of energy, reduce carbon emissions and environmental pollution, and achieve sustainable development. This article establishes an energy consumption prediction model for embedded devices using machine learning algorithms, and adopts a physical verification system to verify the accuracy of the prediction model for embedded devices. Firstly, divide the input and output samples obtained from CFD(Computational Fluid Dynamics, CFD) into training and testing sets, and use the SVM(Support Vector Machines, SVM) algorithm to train the training set to obtain an energy consumption prediction model. Then, the testing set is simulated and validated using the model. Finally, a related embedded hardware circuit system is designed to collect temperature, humidity, air conditioner voltage, and current data using sensor modules, and the energy consumption prediction model is validated using physical verification. The results showed that the relative error percentage between the energy consumption prediction model obtained through SVM and the simulation results was small. The percentage error between the actual energy consumption value and the predicted energy consumption value was also relatively small, verifying the feasibility of the research in this article.
Subject
Computer Science Applications,History,Education
Reference18 articles.
1. Floor heating energy consumption simulation and scheme optimization based on CFD simulation;Sun;Building Energy Efficiency,2019
2. Using artificial neural networks to assess HVAC related energy saving in retrofitted office buildings;Deb;Solar Energy,2018
3. The effective heat transfer coefficient method is used to estimate the heating heat consumption and design the building energy saving;Yang;Building Science,1986
4. Quality elements and testing methods of machine learning systems;Li;Electronic Test,2018
5. Quality elements and testing methods of machine learning systems;Dongm;Heating Ventilating & Air Conditioning,2021