-Network elements and their parameters in mobile wireless networks, are largely manually configured. This has been somewhat sufficient; but with the growing data traffic compensated by new and emerging technologies with corresponding larger networks, there is an obvious need to redefine the network operations to achieve optimum performance. A manual configuration approach requires specialized expertise for device deployments, configurations, re-setting network parameters and general management of the network. This process is costintensive, time-consuming and prone to errors. Adoption of this approach in the evolved wireless technologies results in poor network performance. Therefore, the introduction of advanced mobile wireless networks has highlighted the need and essence for automation within the network. Self Organizing Networks (SON) developed by 3GPP, using automation, ensures operational efficiency and next generation simplified network management for a mobile wireless network. The introduction of SON in LTE therefore brings about optimum network performance and higher end user Quality of Experience. This paper highlights the SON techniques relevant within an LTE network, a brief description of SON architecture alternatives and then some information on the evolution of SON activities as LTE evolves towards LTE-A.

Post third generation (3G) broadband mobile networks such as HSPA+, LTE and LTE-Advanced offer improved spectral efficiency and higher data rates using innovative technologies such as relay nodes and femto cells. In addition, these networks are normally deployed for parallel operation with existing heterogeneous networks. This increases the complexity of network management and operations, which reflects in higher operational and capital cost. In order to address these challenges, self-organizing network operations were envisioned for these next generation networks. For LTE in particular, Self-organizing networks operations were built into the specifications for the radio access network. Load balancing is a key self-organizing operation aimed at ensuring an equitable distribution of users in the network. Several iterative techniques have been adopted for load balancing. However, these iterative techniques require precision, rigor and certainty, which carry a computational cost. Retrospect, these techniques use load indicators to achieve load balancing. This paper proposes two neural encoded fuzzy models, developed from network simulation for load balancing. The two models use both load indicators and key performance indicators for a more informed and intuitive load balancing. The result of the model checking and testing satisfactorily validates the model. General TermsAccess Network, Broadband, Models, Soft computing Wireless communication. KeywordsLoad balancing, neural network, fuzzy logic, LDI Model, USU Model.

The wide use of OFDM systems in multiuser environments to overcome problem of communication over the wireless channel has gained prominence in recent years. Cross-layer Optimization technique is aimed to further improve the efficiency of this network. This chapter demonstrates that significant improvements in data traffic parameters can be achieved by applying cross-layer optimization techniques to packet switched wireless networks. This work compares the system capacity, delay time and data throughput of QoS traffic in a multiuser OFDM system using two algorithms. The first algorithm, Maximum Weighted Capacity, uses a cross-layer design to share resources and schedule traffic to users on the network, while the other algorithm (Maximum Capacity) simply allocates resources based only on the users channel quality. The results of the research shows that the delay time and data throughput of the Maximum Weighted Capacity algorithm in cross layer OFDM system is much better than that of the Maximum Capacity in simply based users channel quality system. The cost incurred for this gain is the increased complexity of the Maximum Weighted Capacity scheme.