Building Energy Efficiency Evaluation Based on Neural Network

At present, many countries and regions have formulated building energy efficiency standards, requiring new and renovated buildings to meet certain energy efficiency requirements. These standards promote energy conservation and emission reduction in the building industry and promote the sustainable development of building energy. Current buildings are increasingly powered by renewable energy sources such as solar and wind power. By installing devices such as solar photovoltaic panels and wind turbines, buildings can generate their own energy and reduce their dependence on traditional energy sources. However, previous building equipment technologies were relatively inefficient, such as traditional air conditioning and heating systems. The extensive use of environmentally unfriendly materials, such as concrete and bricks, in construction puts a lot of pressure on the environment. There is also a widespread waste of energy, such as the use of old equipment and unreasonable building design. Overall, the current development trend of building energy is toward energy conservation, sustainable development, and the use of renewable energy to reduce energy consumption, reduce environmental impact, and improve building comfort and sustainability. In this paper, the BP neural network is used to evenly distribute the search space, which can effectively improve the efficiency of the algorithm, and then, the seagull algorithm is used to generate the initial population with better diversity, and the BPOA model is proposed. The model can accurately predict the evaluation index of building energy efficiency through experimental comparison, and the proposed model can significantly improve the reliability of building energy.