Methodology for Choosing Datacenter for Cloud Providers in

Methodology for Choosing Datacenter for Cloud Providers in West Africa Region Ahmed Alharthi April 25, 2014 UCCS Master’s Project Report Ahmed- Public Cloud Location in Africa 4/25/2014 1

Agenda • Introduction • Why Africa • The proposed Methodology • Selection Results • Lessons Learned • Future Work • Conclusion Ahmed- Public Cloud Location in Africa 4/25/2014 2

Motivation � Lack of information regarding to data centers in Africa. � Demand of the services � In globalizations movement, Africa was neglected � Cloud provider numbers Ahmed- Public Cloud Location in Africa 4/25/2014 3

Cloud providers Ahmed- Public Cloud Location in Africa 4/25/2014 4

Why Africa ? Number of data centers Ahmed- Public Cloud Location in Africa 4/25/2014 5

Number of Data Centers around the World Ahmed- Public Cloud Location in Africa 4/25/2014 6

Growing Demand from Africa Ahmed- Public Cloud Location in Africa 4/25/2014 7

Research Plan � Research the process for selecting the best locations to build data centers for cloud providers in West Africa. � Main Considerations: Network performance, Costs, Submarine cable. Other factors : Environmental, Economical and Politics stabilities. Ahmed- Public Cloud Location in Africa 4/25/2014 8

Goal � Develop a methodology to suggest the best locations for setting up data centers for cloud providers. � Significance ◦ Connect Africa to the world in efficient way. Ahmed- Public Cloud Location in Africa 4/25/2014 9

Related Work � Mc. Connell A. , Parr G. P. , Mc Clean S. I. , Khan, K [38] � Khosrow Ebrahimi, Gerard F. Jones, and Amy S. Fleischer [11] � In terms of Africa’s network connectivity, M. Zennaro, E. Canessa, K. R. Sreenivasan , A. A. Rehmatullah and R. L. [12] � Sanjay M. Parekh, Robert B. Friedman, Neal K. Tibrewala, and Benjamin Lutch [28] Ahmed- Public Cloud Location in Africa 4/25/2014 10

Geographical & Climate Characteristics of the region � Climate & topography of the continent � Tornados & Hurricanes & Tsunami � Earthquake � Politic Systems on the region � Economic Status Ahmed- Public Cloud Location in Africa 4/25/2014 11

Ahmed- Public Cloud Location in Africa 4/25/2014 12

Africa Submarine Cables Ahmed- Public Cloud Location in Africa 4/25/2014 13

How Intel/HP Select their Data Center Locations � Intel Considerations are : WAN infrastructure, availability of water for cooling, costs workforce, water, power or landscape. � HP Considerations are: quality of the land their size, price and geographic location, the availability of power and communication network in the region, cost of operations including electricity, water, network access, free cooling. Ahmed- Public Cloud Location in Africa 4/25/2014 14

The Proposed Methodology � Methodology is mix of Intel , HP and IBM approaches � Main considerations : ◦ Costs of Powering, Cooling and landscape. ◦ Communication network and their capabilities. Secondary considerations : Politics status � Geographical & Climate location � Submarine cables � Economy � Ahmed- Public Cloud Location in Africa 4/25/2014 15

Decision Process for Selecting Countries to Host Public Cloud Senegal, Guinea, Liberia, Ghana, Togo, Benin, Sierra Leone, Nigeria, Cameron, Cote d'ivoire, Congo, Angola, Democratic Republic of the Congo and Namibia. Ahmed- Public Cloud Location in Africa 4/25/2014 16

Results of Decision Process Ahmed- Public Cloud Location in Africa 4/25/2014 17

Network measurements � Latency � Round Trip Time � Packet loss � Bandwidth Ahmed- Public Cloud Location in Africa 4/25/2014 18

System and Tools for Measurement � Network measurements Amazon Linux AMI 2014. 03. 1 machines In Singapore, Sydney and Sao Paulo Linux commands : Ping and Traceroute � Tool used : ◦ Nmap (Network mapper) ◦ Visual route Ahmed- Public Cloud Location in Africa 4/25/2014 19

Network measurements from North America 300 � From Colorado 128. 198. 49. 171 265 250 220 182 200 182 150 100 50 0 23 Ghana 27 South Africa Latecny Country Latency Ghana 30 27 Senegal Nigeria RTT 23 ms Round trip time 220 ms Packet loss 10 % Number of Hops 17 South Africa 27 ms 265 ms 0% 20 Senegal 30 ms 182 ms 0% 17 Nigeria 27 ms 182 ms 0% 18 Ahmed- Public Cloud Location in Africa 4/25/2014 20

Network measurements from East Asia (Singapore) 54. 255. 149. 162 Country Latency Ghana 197. 253. 65. 36 South Africa 41. 74. 178. 82 Senegal 41. 83. 255 Nigeria 41. 222. 211. 58 28 ms 48 ms 24 ms 27 ms Round trip time 270 ms 476 ms 236 ms 274 ms Packet loss 0% 0% Number of Hops 12 20 13 19 476 500 450 400 350 270 300 274 236 250 200 150 100 50 0 28 Ghana 48 South Africa RTT Ahmed- Public Cloud Location in Africa 24 27 Senegal Nigeria Latency 4/25/2014 21

Network measurements from East Asia (Sydney) � 54. 206. 48. 231 Country Latency Round trip time Ghana 197. 253. 65. 36 South Africa 41. 74. 178. 82 Senegal 41. 83. 255 Nigeria 41. 222. 211. 5 44 ms 42 ms 440 ms 493 ms 428 ms 448 ms � Packet loss 0% 0% Number of Hops 17 25 17 23 600 493 500 448 428 400 300 200 100 0 44 Ghana 44 42 South Africa Latency Ahmed- Public Cloud Location in Africa Senegal 42 Nigeria RTT 4/25/2014 22

Network measurements from South America (Brazil) � 54. 255. 149. 162 Country Ghana 197. 253. 65. 36 South Africa 41. 74. 178. 82 Senegal 41. 83. 255 Nigeria 41. 222. 211. 58 Latency 30 ms 36 ms 31 ms 32 ms Round trip time 312 ms 343 ms 281 ms 297 ms Packet loss 0% 0% Number of Hops 14 16 14 12 400 350 343 312 297 281 300 250 200 150 100 50 0 30 Ghana 36 31 South Africa 4 Latency Ahmed- Public Cloud Location in Africa Senegal 32 Nigeria RTT 4/25/2014 23

Detailed Stat Related to Ghana Observation � � � � [aalharth@walrus cs 701]$ ping -c 10 197. 253. 65. 36 PING 197. 253. 65. 36 (197. 253. 65. 36) 56(84) bytes of data. 64 bytes from 197. 253. 65. 36: icmp_seq=1 ttl=43 time=981 ms 64 bytes from 197. 253. 65. 36: icmp_seq=2 ttl=43 time=983 ms 64 bytes from 197. 253. 65. 36: icmp_seq=3 ttl=43 time=973 ms 64 bytes from 197. 253. 65. 36: icmp_seq=4 ttl=43 time=968 ms 64 bytes from 197. 253. 65. 36: icmp_seq=5 ttl=43 time=972 ms 64 bytes from 197. 253. 65. 36: icmp_seq=6 ttl=43 time=960 ms 64 bytes from 197. 253. 65. 36: icmp_seq=7 ttl=43 time=1003 ms core 4. LDNLondon. as 6453. net is the last node connecting to Ghana Goes to WASC submarine cables operated by TATA. 64 bytes from 197. 253. 65. 36: icmp_seq=9 ttl=43 time=967 ms 64 bytes from 197. 253. 65. 36: icmp_seq=10 ttl=43 time=972 ms --- 197. 253. 65. 36 ping statistics --- 10 packets transmitted, 9 received, 10% packet loss, time 8997 ms rtt min/avg/max/mdev = 960. 481/975. 940/1003. 880/11. 900 ms, pipe 2 Ahmed- Public Cloud Location in Africa 4/25/2014 24

Formula for Estimating Costs � Estimating the Coast of Space, Cooling and Powering Data Center � Estimation based on HP “Cost model for planning, development and operation of a data center” � Assumptions Facility size is 30, 000 sq ft � 10 MW datacenter � %50 occupied � Ahmed- Public Cloud Location in Africa 4/25/2014 25

Cost of Renting Spaces Country Average rent (per sq ft) Lagos, Nigeria $6. 48 – 8. 00 Accra, Ghana $5. 7 -10. 5 Dakar, Senegal $ 5. 5 – 9. 5 Space Cost / sqft $60 $41 $38 $36 Cape Town, $ 10 - 14 South Africa Lagos, Nigeria Accra, Ghana Dakar, Senegal Ahmed- Public Cloud Location in Africa 4/25/2014 Cape Town, SA 26

Cost of Power Countr y Power cost KWH Lagos, Nigeria Accra, Ghana Dakar, Senegal Cape Town, SA $ 0. 20 Cost of Power /sqft per unit $0, 17 $0, 15 $ 0. 31 $0, 12 $0. 42 $ 0. 48 $0, 07 Lagos, Nigeria Accra, Ghana Dakar, Senegal Ahmed- Public Cloud Location in Africa 4/25/2014 Cape Town, SA 27

Cost of Cooling Country Cooling Cost / sqft Rate / sqft/unit Lagos, Nigeria $0. 065/ft Accra, Ghana 0. 0115/ft Dakar, Senegal 0. 171/ft Cape Town, SA 0. 214/ft 0. 214 0. 171 0. 115 0. 065 Lagos, Nigeria Accra, Ghana Dakar, Senegal Ahmed- Public Cloud Location in Africa 4/25/2014 Cape Town, SA 28

Total Cost /sq ft $60, 22 $41, 15 $37, 44 $36, 44 Lagos, Nigeria Accra, Ghana Dakar, Senegal Ahmed- Public Cloud Location in Africa Cape Town, SA 4/25/2014 29

Selection Results Ranking the countries based on RTT Country Nigeria Senegal South Africa Ghana North America Singapore 1 1 4 3 2 1 4 3 Sydney 2 1 4 3 Brazil 2 1 4 3 Ahmed- Public Cloud Location in Africa 4/25/2014 30

Selection Results � Bandwidth Ahmed- Public Cloud Location in Africa 4/25/2014 31

Selection Results � Total Space, Power and Cooling costs Total Cost /sq ft $60, 22 $41, 15 $36, 44 Lagos, Nigeria Accra, Ghana $37, 44 Dakar, Senegal Ahmed- Public Cloud Location in Africa Cape Town, SA 4/25/2014 32

Nigeria is Optimal Location � Network capability among the best and stable � High (5) submarine cables � Cheapest power price per Kwh. � Lowest total cost including space, power and cooling. � #1 Economy in the region. � Largest number of Internet users, 49 M. � Stable politic system. � Center of the region geographically Ahmed- Public Cloud Location in Africa 4/25/2014 33

Lessons Learned � Collecting data ◦ Learn about IT in Africa. ◦ Talk to students, IBM, HP, ISP providers, realtors ◦ Language barrier. ◦ Gathering real estate data ◦ Conflicts data � Technical Challenges ◦ Understanding cables systems ◦ Track packets ◦ Network tools ◦ Web servers ◦ Locating servers Ahmed- Public Cloud Location in Africa 4/25/2014 34

Future Work � Collect additional relevant data to select the best location of data center for a cloud provider. � The data gathered from latency, round trip time and bandwidth should be gained from relevant data center of a cloud provider in real world. � Examine ping and trace utility data multiple times in different times. Ahmed- Public Cloud Location in Africa 4/25/2014 35

Conclusion � Senegal, Nigeria, Ghana and South Africa are the ideal locations to host data center for cloud provider. � Nigeria has the most suitable features to host one. � Africa has a good opportunity to host datacenter for a cloud provide. � Costs of datacenter may be vary from city to other one. Ahmed- Public Cloud Location in Africa 4/25/2014 36

References � � � � � Amazon Web Services. (2014). Global Infrastructure. Retrieved from http: //aws. amazon. com/aboutaws/globalinfrastructure/ Rath, John. DATA CENTER SITE SELECTION. Tech. N. p. : n. p. , n. d. Print. "Black. Swan Zine. " Data Center: 10 Places You Don’t Want to Build. Blackswanzine, 2010. Web. 2 Jan. 2014. [4] Chang, Shin-Jyh Frank, Susmit Harihar Patel, and James Marc Withers. "An optimization model to determine data center locations for the army enterprise. " Military Communications Conference, 2007. MILCOM 2007. IEEE, 2007. [5] Hugos, M. H. , & Hulitzky, D. (2011). Business in the cloud: What every business needs to know about cloud computing. New York: Wiley. [6] Lanier, J. (2013). Who owns the future? . London: Allen Lane. [7] Wang, L. (2012). Cloud computing: Methodology, systems, and applications. Boca Raton, FL: CRC Press. [8] Agrawal, G. P. (2010). Fiber-optic communication systems (Vol. 222). John Wiley & Sons. [9] "How to Meet a Growing Need for More Data Center Capacity. " Http: //www. ibm. com/us/en/. IBM, Sept. 2012. Web. Oct. 2013. [10] Nozick, Linda K. , and Mark A. Turnquist. "A two-echelon inventory allocation and distribution center location analysis. " Transportation Research Part E: Logistics and Transportation Review 37. 6 (2001): 425 -441. [11] Ebrahimi, Khosrow, Gerard F. Jones, and Amy S. Fleischer. "A review of data center cooling technology, operating conditions and the corresponding low-grade waste heat recovery opportunities. " Renewable and Sustainable Energy Reviews 31 (2014): 622 -638. [12] Zennaro, M. , et al. "Scientific Measure of Africa's Connectivity. " Information Technologies & International Development 3. 1 (2006). [13] Nozick, Linda K. , and Mark A. Turnquist. "A two-echelon inventory allocation and distribution center location analysis. " Transportation Research Part E: Logistics and Transportation Review 37. 6 (2001): 425 -441. [14] Cloud Computing in Africa Situation and Perspectives. Tech. ITU, 20 Apr. 2012. Web. Feb. -Mar. 2014. [15] Data Center Map. " - Colocation, Cloud, Managed Hosting Etc. N. p. , n. d. Web. Mar. 2014. <http: //www. datacentermap. com/>. [16] Submarine Telecoms INDUSTRY REPORT. Rep. Terabit Consulting, 2013. Web. [17] African Studies Center, University of Pennsylvania. Web. 15 Feb. 2014. [18] Pappa, Farrah. "The Do's and Dont's of Data Center Planning. " The Do's and Dont's of Data Center Planning. Web. 15 Feb. 2014. [19] Map of Earthquakes Today. " Map of Earthquakes Today. N. p. , n. d. Web. 15 Mar. 2014. [20] Earthquakes. Web. Feb. 2014. <Earthquake Hazards Program>. Ahmed- Public Cloud Location in Africa 4/25/2014 37

References � � � � � [21] P&S. "Tsunami Strikes African Coast. " Tsunami Strikes African Coast. N. p. , n. d. Web. 15 Mar. 2014. [22] "Nigeria Economy Set to Leapfrog South Africa on Data Revamp. " Bloomberg. com. Bloomberg, 7 May 2014. Web. 11 Apr. 2014. [23] Nigeria. Official Website. Web. Feb. 2014. <http: //www. nigeria. gov. ng/index. php>. [24] "Selecting A Data Center Site: Intel's Approach. " N. p. , Feb. 2014. Web. Feb. 2014. <http: //connectedsocialmedia. com/intel/7426/it-best-practices-data-center-site-selection/> [25] Selecting a Location for an HPC Data Centre. Tech. N. p. : n. p. , 2013. Web. <http: //webcache. googleusercontent. com/search? q=cache: http: //www. prace-project. eu/IMG/pdf/hpc-centrelocation-whitepaper-2. pdf>. [26] "Africa’s International Bandwidth Growth to Lead the World. " Africa's International Bandwidth Growth to Lead the World. N. p. , n. d. Web. 29 Mar. 2014. [27] Hurricanes VS Tornadoes. Diffen, n. d. Web. Mar. 2014. [28] Parekh, Sanjay M. , et al. "Systems and methods for determining collecting and using geographic locations of Internet users. " U. S. Patent No. 6, 757, 740. 29 Jun. 2004. [29] Nmap Free Security Scannar. Web. Jan. 2014. <http: //nmap. org/>. [30] TATA, n. d. Web. Apr. 2014. <http: //lg. as 6453. net/bin/lg. cgi>. [31] Patel, Chandrakant D. , and Amip J. Shah. "Cost model for planning, development and operation of a data center. " (2005). [32] "Nigeria Becomes Africa's Biggest Economy. " BBC. N. p. , 06 Apr. 2014. Web. 06 Apr. 2014. <www. bbc. com%2 Fnews%2 Fbusiness-26913497%E 2%80%8 E>. [33] "Cloud Uptake Set to Explode Across Africa. " Cisco. Web. 26 Mar. 2014. <http: //www. cisco. com/web/ZA/press/2013/112813. html>. [34] Hanson, Stephanie. "Nigeria’s Creaky Political System. " Council on Foreign Relations, Apr. 2007. Web. <http: //www. cfr. org/nigerias-creaky-political-system/p 13079>. [35] "Top 10 Internet Countries in Africa. " PC Tech Magazine. N. p. , Feb. 2014. Web. Apr. 2014. <http: //pctechmag. com/2014/02/top-10 -internet-countries-in-africa/>. [36] "Political System. " Wikipedia. Web. Mar. 2014. <http: //en. wikipedia. org/wiki/Political_system>. [37] "GLOBAL BROADBAND. " Netindex. N. p. , n. d. Web. Feb. 2014. <www. netindex. com>. [38] Mc. Connell, A. , et al. "Selecting a Data C based Location. " Ahmed- Public Cloud Location in Africa 4/25/2014 38

Ahmed- Public Cloud Location in Africa 4/25/2014 39