Networks are playing an essential role during this age of digital expansion. Nowadays, to provide extended bandwidth and redundancy for the growing domain of network communication, we are getting accustomed to wireless mesh networks. There have been many different network topologies, such as bus, ring, star, mesh, hybrid, etc. In the area of network communication, wireless mesh networks are becoming more popular. Mesh networks have become one of the most popular options out of these due to their improved connection capabilities, reduced lag, and lack of rigidity. Their key advantages are adaptability, setup, and flexibility, along with increased cost and transmission time efficiency. Traffic prediction refers to forecasting the traffic volumes in a network. The traffic volume includes incoming requests and outgoing data transmitted by the network nodes. Traffic prediction is a crucial aspect owing to being the fundamental block on which the performance of routing and congestion control algorithms is dependent. An accurate estimate of the network traffic can help the network administrator improve the availability and transmission speeds of the network. In this project, we propose a hybrid model consisting of a convolutional neural network and long short-term memory for network traffic prediction in wireless mesh networks. The proposed system makes a strong case for network traffic prediction, where the use of historical data is collected over the wireless mesh network.