TY - GEN
T1 - Provisioning low latency, resilient mobile edge clouds for 5G
AU - Ford, Russell
AU - Sridharan, Ashwin
AU - Margolies, Robert
AU - Jana, Rittwik
AU - Rangan, Sundeep
PY - 2017/11/20
Y1 - 2017/11/20
N2 - Network virtualization and SDN-based routing allow carriers to flexibly configure their networks in response to demand and unexpected network disruptions. However, cellular networks, by nature, pose some unique challenges because of user mobility and control/data plane partitioning, which calls for new architectures and provisioning paradigms. In this paper, we address the latter part by devising algorithms that can provision the data plane to create a distributed Mobile Edge Cloud (MEC), which provides opportunities for lower latencies and increased resilience (through placement of network functions at more distributed datacenter locations) and accounts for service disruption that could be incurred because of user mobility between the service areas of different datacenters. Through evaluations with topology and traffic data from a major carriers's network, we show that, compared to static, centralized networks, careful virtualized provisioning can yield significant savings in network costs while still minimizing service disruption due to mobility. We demonstrate that up to a 75% reduction in redundant datacenter capacity over the operator's current topology (while achieving the same level of resilience) is possible by distributing load over many mobile cloud datacenters.
AB - Network virtualization and SDN-based routing allow carriers to flexibly configure their networks in response to demand and unexpected network disruptions. However, cellular networks, by nature, pose some unique challenges because of user mobility and control/data plane partitioning, which calls for new architectures and provisioning paradigms. In this paper, we address the latter part by devising algorithms that can provision the data plane to create a distributed Mobile Edge Cloud (MEC), which provides opportunities for lower latencies and increased resilience (through placement of network functions at more distributed datacenter locations) and accounts for service disruption that could be incurred because of user mobility between the service areas of different datacenters. Through evaluations with topology and traffic data from a major carriers's network, we show that, compared to static, centralized networks, careful virtualized provisioning can yield significant savings in network costs while still minimizing service disruption due to mobility. We demonstrate that up to a 75% reduction in redundant datacenter capacity over the operator's current topology (while achieving the same level of resilience) is possible by distributing load over many mobile cloud datacenters.
UR - http://www.scopus.com/inward/record.url?scp=85041316821&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041316821&partnerID=8YFLogxK
U2 - 10.1109/INFCOMW.2017.8116371
DO - 10.1109/INFCOMW.2017.8116371
M3 - Conference contribution
AN - SCOPUS:85041316821
T3 - 2017 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2017
SP - 169
EP - 174
BT - 2017 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2017
Y2 - 1 May 2017 through 4 May 2017
ER -