Data Fusion of Campus Energy Conservation and Emission Reduction Based on CPSONN-BP
With the intensification of global climate change,carbon dioxide emissions and energy consumption have become the focus of international attention.In the context of the"dual-carbon"target,the importance of en-ergy conservation and emission reduction in universities has become increasingly prominent,especially in achie-ving carbon peak and carbon neutrality goals.This paper studies a Chaos Particle Swarm Optimization-based BP Neural Network(CPSONN-BP)model for the effective fusion and analysis of campus energy conservation and e-mission reduction data.Utilizing multi-source heterogeneous data,the model aims to establish a precise and com-prehensive prediction model for university energy conservation and emission reduction and to more effectively address the energy challenges and environmental pressures under the dual-carbon background.By conducting a comprehensive comparative study on the performance of the CPSONN-BP model in the fusion of campus energy conservation and emission reduction data,this paper finds that the model exhibits significant advantages in accu-racy,convergence speed,stability,and the ability to handle complex data.Compared with traditional Excel predic-tion methods and standard BP neural networks,the CPSONN-BP model shows faster convergence speed and high-er prediction accuracy in dealing with multivariate and nonlinear problems.Moreover,the model demonstrates high reliability and consistency in multiple runs,making it particularly suitable for analyzing data with highly nonlinear and multivariate characteristics.This research highlights the superior performance of the CPSONN-BP model in the fusion of campus energy conservation and emission reduction data,which is of great significance for promoting sustainable development and achieving harmonious development of economy,environment,and society.
university energy conservation and emission reductionenergy consumptionprediction modelmulti-source heterogeneous datadata fusion
NETL
NSTL
万方数据
维普
