Evaluation on network optimization model of low-carbon multi-level supply chain based on big data algorithm evaluation

The issue of global climate change has attracted worldwide attention. Many scientific studies have shown that in daily life and industrial production, greenhouse gases such as carbon dioxide are an important cause of climate warming and have an important impact on human survival and development. To effectively control the emission of greenhouse gases such as carbon dioxide, a "low carbon economy" composed of "low energy consumption", "low pollution" and "low emission" has emerged and has gradually become a new economic form. Given the problem that the low-carbon supply chain network computing speed is not fast enough and the cost is high, The purpose of this paper was to explore the use of big data technology to design and optimize a low-carbon supply chain network in China in the context of a low-carbon economy, to seek the optimal balance. In this paper, through the study of the calculation example, the improved genetic algorithm proposed in this paper had obvious advantages in all aspects. For example, its operation speed was fast, which only took 23.15 s. At the same time, it had good convergence and strong stability, which can avoid local optimum. At the same time, it could be found that a good supply chain network could not only reduce carbon emissions, but also reduce costs and bring better benefits to enterprises. Thus, the need to continuously improve the supply chain network is necessary.