摘要：The production and use of energy is of great importance to the sustainable development of any society, economy and environment. As a superpower, the total energy consumption of the United States is also among the highest in the world. In 2009, the United States promulgated the clean energy and security act of 2009, aiming to further improve the energy structure and reduce environmental pollution. The policy has had a significant impact on the world energy landscape. First of all, this article collects data from the U.S. Energy Information Administration and obtains data on energy production and consumption in the four states on the US-Mexico border in 2009. The data was artificially analyzed from two aspects of sector and energy. The energy profile for each state was presented in terms of the proportion of energy usage by sector and the proportion of each energy usage. Furthermore, based on the above data analysis, we have established the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) model to determine the four indicators of cleaner, renewable energy. The four evaluation indexes are: cleaner, renewable energy consumption rate; cleaner, renewable energy expenditure rate; carbon dioxide emissions ratio in the United States and biological impact index. The optimal scheme and the worst scheme were determined according to the above four indexes, and then to calculate the clean energy use scheme for relative states converting the distances into scores. The states that have the ‘best’ profile for use of cleaner, renewable energy in 2009 were at last identified. Finally, back propagation (BP) neural network model was established, and the total energy consumption data from 2009 was used to train the network, so as to predict the energy use in 2025. By the same token, the use of cleaner, renewable energy resource in 2025 can be predicted.
关键词：TOPSIS model;BP neural network;renewable energy
