Xinzhou Cheng

Mobility load balancing aware radio resource allocation scheme for LTE-Advanced cellular networks

Mobility load balancing (MLB) is widely used to address the uneven load distribution problem. The basic idea is that a hot-spot cell selects less-loaded neighbouring cells as assistant cells, and thenshiftsitsedge users to assistant cells via the handover region adjustment. However, shifted users receive the reduced signal power after MLB, which may result in the poor link quality problem for shifted users. In order to deal with this problem, this paper proposes a mobility load balancing aware radio resource allocation (MLBRRA) scheme. In the MLBRRA scheme, the assistant cell jointly considers the MLB factor of the shifted user and that of the hot-spot cell, as well as the proportional fairness scheduling factor. More specifically, the assistant cell preferentially allocates radio resources to shifted users, which are suffering poor link quality or previously served by a hot-spot cell with large handover region. Simulation results show that the proposed MLBRRA scheme can effectively deal with the poor link quality problem in terms of handover failure and call dropping. The proposed scheme can also reduce the call blocking probability.

Self-optimised Coordinated Traffic Shifting Scheme for LTE Cellular Systems

Mobility load balancing is widely used in LTE cellular systems to deal with the uneven load distribution. Its basic idea is to shift traffic from a hot-spot cell to less-loaded neighbouring cells, called partners. Conventional schemes focus on the hot-spot cell’s load reduction and pay less attention to the performance of partners. This paper proposes a self-optimised coordinated traffic shifting scheme. In the proposed scheme, the coordination among partners is considered. Meanwhile, the shifted traffic is adjusted dynamically according to the load balancing (LB) performance. Simulation results show the proposed scheme can keep low call blocking probability of partners. It can also keep the number of Ping-Pong LB and the LB handover dropping probability at low levels.

Telecom Big Data Based User Offloading Self-Optimisation in Heterogeneous Relay Cellular Systems

This paper proposes a telecom big data based user offloading self-optimisation TBDUOS scheme. Its aim is to assist telecom operators to effectively balancing the load distribution with achieving good service performance and customer management in heterogeneous relay cellular systems. To achieve these objectives, in the cell-level offloaded traffic analysis stage, the optimal offloaded traffic is calculated to minimise the total blocking probability. In the user-level offloading stage, the user portrait is drawn and the K-MEANS algorithm is employed to manage the users clustering in the heavily loaded cell, and finally shifting users to assistant cells. Simulation results show the TBDUOS scheme can effectively reduce the handover failure and call dropping of specific users, especially voice/stream users, high consumption users, high level users. The TBDUOS scheme can also reduce the blocking probability.

Self-optimised joint traffic offloading in heterogeneous cellular networks

Traffic offloading is a widely used technique to address the unbalanced traffic distribution between pico cells and macro cells in heterogeneous cellular networks. However, the shifted users may result in the macro cell receiving large traffic from multiple pico cells and then becoming heavily loaded. This phenomenon is called the exacerbation problem in this paper. In order to address this problem and balance load effectively, this paper proposes a self-optimised joint traffic offloading (JTO) scheme. The JTO scheme jointly employs two traffic offloading techniques, including cell biasing technique to offload traffic between pico cell and macro cell, and mobility load balancing among macro cells. Simulation results show the JTO scheme can effectively deal with the cell exacerbation problem, in terms of handover failure and call dropping. The JTO scheme can also reduce the call blocking probability.

A survey of security and privacy in big data

Big data has been arising a growing interest in both scientific and industrial fields for its potential value. However, before employing big data technology into massive applications, a basic but also principle topic should be investigated: security and privacy. In this paper, the recent research and development on security and privacy in big data is surveyed. First, the effects of characteristics of big data on information security and privacy are described. Then, topics and issues on security are discussed and reviewed. Further, privacy-preserving trajectory data publishing is studied due to its future utilization, especially in telecom operation.

An interference management algorithm using big data analytics in LTE cellular networks

Recently, a series of approaches have been developed to mitigate the interference and improve the system capacity in LTE networks. However, due to the diversity of data source, existing approaches have their own limitations in supervised and unsupervised learning. To deal with the downlink inter-cell interference which is caused by the frequency reuse and the characteristics of the OFDMA, an interference management algorithm using big data is proposed. Since big data analytics has become more and more popular in wireless optimization, it is a very effective approach to mitigate the interference and the outage probability by analyzing the huge amount of wireless network measurements and diagnosis data. By obtaining and analyzing the measurement report (MR) and counters (records of the performance indicators of networks) from existing networks, an interference management algorithm (IMA) is proposed based on big data analytics. The numerical results show that the interference management process is low cost and high-efficiency for telecom operators.

Big data assisted customer analysis and advertising architecture for real estate

Advertising delivery is the key in the real estate industry. This paper proposes a big data assisted customer analysis and advertising (BDCAA) architecture. Its aim is to precisely seek potential users and improve the efficiency of advertisement delivery. The proposed BDCAA architecture consists of three stages, including user 360-degree portrait and users segmentation, potential customer mining, precise advertising delivery. Experiment shows the BDCAA architecture can reach high advertising arrival rate, as well as superior advertising exposure/click conversion rate.

A novel cluster algorithm for telecom customer segmentation

With the rapid development of the telecom market, telecom customer gradually shows the characteristics of differentiation and diversification. Telecom customer clustering is an effective method for marketing and retention. In this paper, we propose a cluster algorithm based on k-means and Multivariable Quantum Shuffled Frog Leaping Algorithm (MQSFLA), called MQSFLA-k, which can be used as a customer segmentation method in telecom customers marketing. Simulation results show that the proposed MQSFLA has advantages of both convergence rate and convergence accurate value compared with other intelligent algorithms. In addition, the proposed MQSFLA based MQSFLA-k has the advantage of convergence rate compared with k-means. Furthermore, MQSFLA-k can solve the problem of telecom customer segmentation effectively, which provides target customers for retention.

Mining target users for mobile advertising based on telecom big data

The mobile advertising industry in China has developed rapidly in recent years. Many companies and brands tend to employ mobile advertising in order to reach the target customers accurately. However, the conversion rates associated with the advertising campaigns are usually quite low due to the low quality of the datasets and impropriate predictive model. In this paper, we propose a novel mobile advertising system architecture based on telecom big data analytics. The defined multi-dimensional user portrait is introduced for user label oriented ad display strategy or as the basic database for the further user classification algorithm. We also adopt the widely used logistic regression algorithm in this paper to improve the target accuracy. The result of use case, which is calculated from the real-time collected cellular network data, also shows the superior performance of the proposed mobile advertising system.

A novel precision marketing model based on telecom big data analysis for luxury cars

Traditional marketing approach mainly adopts advertising and telemarketing method to attract potential consumers. It will need a lot of manpower and resources, but cannot position the targeted consumers accurately. In this paper, a novel precision automotive marketing model based on telecom big data mining is proposed to predict the potential high-end luxury car buyers. Initially, both logistic regression algorithm and neural network mining algorithm are applied to build the prediction model. A comprehensive understanding of existing high-end luxury car owners and telecom users are also analyzed deeply before modeling. Then, we derive the key attributes from four dimensions, including user characteristics, communication behavior, terminal attribute and social circle. Based on the evaluation of correlation matrix, eight clever attributes are selected as input variables of the proposed model. Finally, the analysis results demonstrate that the proposed prediction model can achieve superior performance and match the pre-analysis conclusions better.