Dynamic path optimization of cold chain logistics based on improved ant colony algorithm from a low-carbon perspective

Cold chain logistics face challenges such as high energy consumption, high carbon emissions, and high rates of cargo spoilage during transportation. These issues increase the operating costs of enterprises and also negatively affect the ecological environment. Therefore, this study constructs a cold chain logistics distribution path optimization model that comprehensively considers time window constraints, carbon emission costs, and cargo damage costs. Based on this, an I-ACO algorithm is proposed to achieve low-carbon and efficient distribution path planning. The I-ACO algorithm enhances the accuracy and adaptability of path selection by introducing dynamic time warping technology and chaos theory, thereby improving the search ability and solution quality of the algorithm. The results indicated that the I-ACO had a very high overall sample fitting degree, with a correlation coefficient of 0.99 between the actual output value and the expected value. Its accuracy reached 95.2 %, with fast convergence speed and a carbon emission of only 0.04 kg, significantly lower than other algorithms. The I-ACO could effectively reduce logistics costs, decrease carbon emissions, and improve delivery efficiency and customer satisfaction. The research algorithm provides an efficient, accurate, and environmentally friendly solution for optimizing the distribution path of cold chain logistics. This is beneficial for cold chain logistics enterprises to achieve economic benefits and better fulfill social responsibilities, and promote the sustainable development of the industry.