期刊
FRONTIERS IN ENERGY RESEARCH
卷 10, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fenrg.2022.1021164
关键词
energy consumption intensity; energy demand forecast; particle swarm-genetic hybrid optimization algorithm; clean and low-carbon energy transformation; energy demand regression model
In order to improve the accuracy of rural energy demand prediction, it is necessary to establish a simulation calculation model that is more in line with the actual rural energy endowment and development needs. Through the prediction and analysis of rural energy demand in the context of energy transition, the total rural energy demand can be predicted. The research shows that rural energy demand is influenced by multiple factors, and the traditional single model contains limited information, resulting in a large deviation between the prediction results and the actual situation, thus reducing the prediction accuracy.
It is necessary to build a simulation calculation model that is more in line with the actual rural energy endowment and development needs. Prediction and analysis of the total rural energy demand in the context of energy transition. The rural energy demand is affected by many factors, and the traditional single model contains very limited amount of information, which easily leads to a large deviation between the prediction results and the actual situation, thereby reducing the prediction accuracy. In view of this, in view of the complex and difficult to predict the influencing factors of rural energy demand under the new economic normal, based on the back propagation neural network-particle swarm-genetic hybrid optimization algorithm, a total rural energy demand forecast based on energy consumption intensity was constructed method. Firstly, select the key influencing factors of the total rural energy demand forecast and conduct path analysis to compare the explanation strength of the influencing factors on energy demand; secondly, construct the energy consumption demand regression model, and calculate the parameters based on the back propagation neural network-particle swarm-genetic hybrid optimization algorithm. Estimation results; finally, the scenario is given, and the regional rural energy demand forecast results are obtained by using the regression model. Empirical analysis shows that four aspects of GDP, industrial structure, energy utilization efficiency, and rural energy consumption are strongly correlated with the total rural energy demand. At the same time, the prediction error of this study can reach about 1.35%, which can predict future rural energy demand. The total amount to guide the construction of the rural energy system.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据