Fault Diagnosis And Performance Evaluation Of Mobile Phone Base Station Based On Crowdsourcing

The continuous development of information technology has led to the rapid development of communication services and smart phones,the smart phones that wireless access to the network,fully functional and easy to carry has become the first choice for people to deal with communications,Internet,entertainment and office services,and further promote the development of mobile communications.In order to meet the needs of users,to realize the mobile phone signal without blind coverage,mobile communications operators to deploy a large number of mobile phone base stations in various places.With the increase of the number of base stations,the number of base stations is also increasing.The operators mainly through remote monitoring,user feedback and manual inspection positioning to locate the fault base station.But the remote monitoring can only check the damage to the base station hardware,can not view the software failure;the way of user feedback is not detailed description;manual inspection will increase the workload of staff,inspection cycle is longer,these methods are unable to meet The requirements of the operator.Therefore,how to effectively use the user information,timely and accurate positioning of the fault base station,has become an urgent problem in the field of communications.By analyzing the principle of mobile phone switching base station,this paper proposes a cheap and efficient method based on crowdsourcing model,in this method,the user's mobile phone is used as the data collection tool,and the fault location of the base station can be realized through the summary,comparison and analysis of the data.The simulation results show that the method can locate the fault base station in time and accurately.In this paper,according to the characteristics of crowdsourcing,the artificial neural network evaluation method is selected to evaluate the performance of the base station,and combines the user evaluation and the aggregation analysis of the data collected by the smartphone to rank the base station performance.Experiments show that this method can realize the effective use of resources,and evaluate the performance of base stations accurately and objectively.The work of this paper includes the following three aspects:(1)Study on how to realize the base station fault diagnosis and performance evaluation of data acquisition by using android platform,including: the packet capture of android platform,speed measurement,the realize of ping function,network mode discrimination,base station information acquisition.(2)According to the criterion of the mobile phone switching base station set by the operator,a new method of locating the faulty base station is proposed.First,according to the distribution of the base station,Tyson polygon is used to divide the city into several regions.In the case of normal operation of the base station,the smartphone within the area covered by the base station signal will connect to the base station.Once the base station fails,according to the mobile phone switching base station criteria that set up by operator,smart phones will automatically connect to other base stations of covering the region.By recording the data of these users,you can determine the location of the faulty base station.(3)Based on the analysis of the characteristics of crowdsourcing,the artificial neural network algorithm is applied to the performance evaluation of the base station.By using the intelligent mobile phone,we can collect some data that reflect the network performance and record the corresponding user score,then we can use the artificial neural network model to train data,finally,according to the other collected network performance data,to predict the user rating.The performance of the base station is evaluated synthetically by collecting the user score and the predicted user score.Finally,the feasibility of the proposed method that locating fault base is verified by the simulation experiment,and the experimental results show that the performance evaluation of the base station has good practicability by using the artificial neural network.