English title

---

Nowadays in order to increase the reliability and other special aims, the power networks are exchanged to the large and interconnected networks. In such networks, the relays setting and coordination is complicated and needs to determine break points. Break points are the initial points in coordination process and in pervious works, different methods are proposed to finding them in interconnected networks. In this paper, a method proposed to determine suitable break point set, considering some parameters such as pilot protection, Short circuit level, … This method determines minimum break point set using genetic algorithm. After obtaining the solutions, the coordination is fulfilled using the obtained break point set and the break points are modified considering the coordination criteria.         

---

Network function virtualization (NFV) is an emerging technology. NFV enables networks to use software defined virtual functions such as firewalls, load balancers, and WAN accelerators, conventionally running on dedicated hardware. In order to provide NFV resources and meet SLA (Service Level Agreement) conditions, minimize energy consumption and utilize physical resources efficiently, dynamic resource allocation in cloud is an essential task. Since network traffic is changing rapidly, an optimized resource allocation strategy should consider resource auto-scaling property for NFV services.in order to scale cloud resources, we should predict NFV workload. Existing prediction methods are providing poor results for highly volatile and fluctuating time series such as cloud workloads. So, we propose a multiband decomposed wavelet prediction by GMDH ensemble algorithm for NFV traffic preciction. We evaluate the proposed model with two cloud workload traces. The results show the MAPE of prediction by the wavelet -GMDH method improved by 7.2% in compare to best perevious work in recent papers.