Network function virtualization (NFV) is a concept aiming to achieve telecom grade cloud ecosystem for new generation networks focusing on Capital and Operational expenditure (CAPEX and OPEX) savings. The research in this doctoral dissertation proposes a novel methodology for performance evaluation and modeling based on execution area (EA) distribution by CPU core pinning. EA is defined as a software execution unit that can run isolated on a compute resource (CPU core). EAs are derived from the elements and packet processing principles in NFV infrastructures (NFVIs) and Virtual network functions (VNFs) based on Linux kernel. Performing measurements and observing linearity of the measured results opens the possibility to apply model calibration technique to achieve general VNF and NFVI architecture model with performance prediction and environment setup optimization. The modeling parameters are derived from the cumulative packet processing cost obtained by measurements for collocated EAs on the CPU core hosting the bottleneck EA. The VNF and NFVI architecture model with performance prediction is successfully validated against the measurement results obtained in emulated environment and used to predict optimal system configurations and maximal throughput results for different CPUs. The main contributions to the science from this doctoral dissertation are as follows: (1) VNF and NFVI architecture model with performance prediction and bottleneck determination algorithms for optimal virtual network function performance analysis, (2) an algorithm for generic NFVI requirements definition in the target environment, given the required performance SLAs for the VNFs and (3) a resource allocation algorithm for optimal resource consumption in the physical environment shared by multiple VNFs. Although the VNF and NFVI architecture model with performance prediction does not explicitly consider latency/jitter parameters, high-precision measurements of these parameters are executed in emulated environment in order to present the relative difference between the throughput optimized system configurations. These results can be considered on top of throughput prediction and optimal system configuration derived from the VNF and NFVI architecture model with performance prediction when deciding the system configuration to be applied for latency sensitive traffic.