In Wireless Networks, optimal resource allocation and higher Quality of Service is a much needed requirement. A good prediction of network traffic at each access point helps in early allocation of network resources as well as guaranteed quality of service. The traffic load on an access point varies with time and this variation depends on the number of nodes that are attached with that access point. Initially the traffic load at an Access Point (AP) is analyzed with respect to time and it uses Hidden Markov Model (HMM) and Neural Network Model prediction techniques to predict the number of wireless devices that are connected to a specific Access Point at a specific instant of time. Finally, the performance evaluations of the two models are compared for traffic load state in wireless network and the best prediction model is chosen, there by optimal resource allocation and higher Quality of Service is being achieved.