Rapidly growing and fluctuating traffic demands lead to unbalanced traffic scenarios in optical access networks, which have an impact on network efficiency. Thus, the flexible software-defined reconfigurable passive optical network (PON) architecture has been proposed to handle this challenge. To improve the efficiency of a reconfigurable PON facing unbalanced traffic demands, this paper proposes a global load-balancing (GLB) optical network unit (ONU) assignment method, which aims to achieve load balancing among the optical line terminals (OLTs) in the OLT pool as well as among the aggregation switch ports that connect the OLTs by optimizing the affiliations between the OLTs and the ONUs. For on-line optimization, a greedy GLB algorithm is introduced that regroups the ONUs and generates load-balanced target ONU-OLT affiliations in accordance with dynamic traffic demands. For off-line optimization, bee colony optimization (BCO) is invoked to search for better ONU regrouping solutions for GLB. Simulation results show that the proposed GLB algorithm can significantly improve the throughput and delay performance of an optical access network faced with unbalanced traffic demands, especially when the network load is heavy. Moreover, the proposed BCO technique for GLB can obviously improve the worst delay performance and reduce the migrated traffic of the GLB solution, especially under network conditions with high peer-to-peer traffic proportions and heavy network loads. Thus, the proposed global load-balancing ONU assignment method is effective for helping a software-defined reconfigurable PON to cope with unbalanced traffic demands.

中文翻译：

---

用于软件定义的可重新配置PON的全局负载平衡ONU分配

流量需求的快速增长和波动导致光接入网络中流量情况的不平衡，从而影响网络效率。因此，已经提出了灵活的软件定义的可重配置无源光网络（PON）体系结构来应对这一挑战。为了提高面对不平衡流量需求的可重构PON的效率，提出了一种全局负载均衡（GLB）光网络单元（ONU）分配方法，旨在实现OLT中光线路终端（OLT）之间的负载均衡。通过优化OLT和ONU之间的从属关系，在连接OLT的聚合交换机端口之间以及这些池之间建立连接。为了进行在线优化，引入了贪婪的GLB算法，该算法重新组合ONU，并根据动态流量需求生成负载均衡的目标ONU-OLT联盟。对于离线优化，将调用蜂群优化（BCO）来为GLB搜索更好的ONU重新组合解决方案。仿真结果表明，所提出的GLB算法可以显着提高面对不平衡流量需求的光接入网络的吞吐量和延迟性能，特别是在网络负载较重的情况下。此外，针对GLB提出的BCO技术可以明显改善最差的延迟性能，并减少GLB解决方案的迁移流量，尤其是在点对点流量比例高且网络负载重的网络条件下。从而，