This document compares the performance of the AODV and DSR routing protocols through simulation. It describes the simulation environment setup in NS2 including network size, node speeds, traffic sources, and performance metrics measured. Graphs of throughput, delay, and routing overhead under different pause times and node densities are presented. DSR is shown to have higher routing overhead than AODV, while AODV has shorter delays and performs better with higher node mobility. The conclusion is that AODV has advantages for networks with fast node movement.
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...inside-BigData.com
In this deck from PASC18, Hatem Ltaief from KAUST presents: Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outside our Solar System.
"The real-time correction of telescopic images in the search for exoplanets is highly sensitive to atmospheric aberrations. The pseudo-inverse algorithm is an efficient mathematical method to filter out these turbulences. We introduce a new partial singular value decomposition (SVD) algorithm based on QR-based Diagonally Weighted Halley (QDWH) iteration for the pseudo-inverse method of adaptive optics. The QDWH partial SVD algorithm selectively calculates the most significant singular values and their corresponding singular vectors. We develop a high performance implementation and demonstrate the numerical robustness of the QDWH-based partial SVD method. We also perform a benchmarking campaign on various generations of GPU hardware accelerators and compare against the state-of-the-art SVD implementation SGESDD from the MAGMA library. Numerical accuracy and performance results are reported using synthetic and real observational datasets from the Subaru telescope. Our implementation outperforms SGESDD by up to fivefold and fourfold performance speedups on ill-conditioned synthetic matrices and real observational datasets, respectively. The pseudo-inverse simulation code will be deployed on-sky for the Subaru telescope during observation nights scheduled early 2018."
Watch the video: https://wp.me/p3RLHQ-iWN
Learn more: https://pasc18.pasc-conference.org/program/schedule/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
Routing Protocols for Ad-Hoc Networks. This is a book for Ad-hoc On-Demand Distance Vector Routing
&
DSR: The Dynamic Source Routing Protocol for Multi-Hop Wireless Ad Hoc Networks. November 2011,
Authors : Giorgos Papadakis & Manolis Surligas
SPICE MODEL of TPCP8204 (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TPCP8204 (Professional+BDP Model) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of TK8A50D (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TK8A50D (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
Candidate Core Selection for Load-Balanced Multicore Shared Tree MulticastingKoushik Sinha
Multicasting can be done in two different ways: source based tree approach and shared tree approach. Protocols such as Core Based Tree (CBT), Protocol Independent Multicasting Sparse Mode (PIM-SM) use shared tree approach. Shared tree approach is preferred over source-based tree approach because in the later construction of minimum cost tree per source is needed unlike a single shared tree in the former approach. We present a candidate core selection approach for shared tree multicasting so that in a multicast session different senders can select different cores from the candidate core set based on the senders’ physical locations to allow an efficient multicore multicasting approach.
Paper reference link: https://www.researchgate.net/publication/303993360_Locality_based_Core_Selection_for_Multicore_Shared_Tree_Multicasting?ev=prf_pub
SPICE MODEL of TK8A50D (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TK8A50D (Professional+BDP Model) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of SSM3K320T (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of SSM3K320T (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of 2SK3934 (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of 2SK3934 (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of TK10A50D (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TK10A50D (Professional+BDP Model) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of TPCP8205-H (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TPCP8205-H (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...inside-BigData.com
In this deck from PASC18, Hatem Ltaief from KAUST presents: Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outside our Solar System.
"The real-time correction of telescopic images in the search for exoplanets is highly sensitive to atmospheric aberrations. The pseudo-inverse algorithm is an efficient mathematical method to filter out these turbulences. We introduce a new partial singular value decomposition (SVD) algorithm based on QR-based Diagonally Weighted Halley (QDWH) iteration for the pseudo-inverse method of adaptive optics. The QDWH partial SVD algorithm selectively calculates the most significant singular values and their corresponding singular vectors. We develop a high performance implementation and demonstrate the numerical robustness of the QDWH-based partial SVD method. We also perform a benchmarking campaign on various generations of GPU hardware accelerators and compare against the state-of-the-art SVD implementation SGESDD from the MAGMA library. Numerical accuracy and performance results are reported using synthetic and real observational datasets from the Subaru telescope. Our implementation outperforms SGESDD by up to fivefold and fourfold performance speedups on ill-conditioned synthetic matrices and real observational datasets, respectively. The pseudo-inverse simulation code will be deployed on-sky for the Subaru telescope during observation nights scheduled early 2018."
Watch the video: https://wp.me/p3RLHQ-iWN
Learn more: https://pasc18.pasc-conference.org/program/schedule/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
Routing Protocols for Ad-Hoc Networks. This is a book for Ad-hoc On-Demand Distance Vector Routing
&
DSR: The Dynamic Source Routing Protocol for Multi-Hop Wireless Ad Hoc Networks. November 2011,
Authors : Giorgos Papadakis & Manolis Surligas
SPICE MODEL of TPCP8204 (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TPCP8204 (Professional+BDP Model) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of TK8A50D (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TK8A50D (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
Candidate Core Selection for Load-Balanced Multicore Shared Tree MulticastingKoushik Sinha
Multicasting can be done in two different ways: source based tree approach and shared tree approach. Protocols such as Core Based Tree (CBT), Protocol Independent Multicasting Sparse Mode (PIM-SM) use shared tree approach. Shared tree approach is preferred over source-based tree approach because in the later construction of minimum cost tree per source is needed unlike a single shared tree in the former approach. We present a candidate core selection approach for shared tree multicasting so that in a multicast session different senders can select different cores from the candidate core set based on the senders’ physical locations to allow an efficient multicore multicasting approach.
Paper reference link: https://www.researchgate.net/publication/303993360_Locality_based_Core_Selection_for_Multicore_Shared_Tree_Multicasting?ev=prf_pub
SPICE MODEL of TK8A50D (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TK8A50D (Professional+BDP Model) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of SSM3K320T (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of SSM3K320T (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of 2SK3934 (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of 2SK3934 (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of TK10A50D (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TK10A50D (Professional+BDP Model) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
SPICE MODEL of TPCP8205-H (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
SPICE MODEL of TPCP8205-H (Standard+BDS) in SPICE PARK. English Version is http://www.spicepark.net. Japanese Version is http://www.spicepark.com by Bee Technologies.
2. 2
Outline
Review DSR and AODV
Simulation Environment
Simulation Graph
Simulation Result
Conclusion
3. 3
DSR Route Discovery
A
B
C
D
E G
F H
[A,G,ID,A]
[A,G,ID,AB] [A,G,ID,ABE]
[A,G,ID,AC]
Node E drop the
packet because it has
forward the same ID
packet
Source A forward
data to destination G
4. 4
DSR Route Reply
A
B
C
D
E G
F H
[A,B,E]
[A,B,E][A,B,E]
[A,B,E]
Node A stores the route
from A to G in its route
cache
11. 11
Simulation Environment
Simulation Range
1500*300 meters
Number of node in the range
Random creating 50 nodes
Number of source node in the range
Random 20 sources
Random 40 sources
12. 12
Simulation Environment
Node radio range
250 meters
Traffic source
CBR (Content Bit-Rate)
Node radio bandwidth
2Mb/sec
14. 14
Simulation Environment
Random create 50 nodes in 1500*300
meters
Random select 20(40) nodes to deliver
packets
Each node starts its journey from a
random location to a random location
with a randomly chosen speed 0~20
m/s
15. 15
Simulation Environment
Each node move in 50 seconds, then
move again after pause 20(40 or 60 or
80) seconds
Total Run Time: 300 seconds
21. 21
Performance Matrics
Throughput
The ratio of the data packets delivered to the
destinations to those generated by the CBR
sources.
received packets / sent packets
24. 24
Performance Matrics
Average Delay
For each packet with id of trace level (AGT)
and type (CBR), calculate the send(s) time(s)
and the receive(r) time(t) and average it
33. 33
Conclusion
DSR have triple numbers of control
messages than AODV
AODV has difficult when the nodes are
moving fast
AODV has the shortest end-to-end
delay
DSR has higher routing overhead than
AODV