Database Reference
In-Depth Information
600
Californium
mjCoAP
Californium
mjCoAP
100
500
80
400
60
300
40
200
20
100
0
0
250
500
750
1000
250 500 750 1000 1250 1500 1750 2000 2250 2500
Request Rate [requests/sec]
Request Rate [requests/sec]
(a)
(b)
600
Californium
mjCoAP
500
400
300
200
100
0
250 500 750 1000 1250 1500 1750 2000 2250 2500
Request Rate [requests/sec]
(c)
Fig. 3.
Performance evaluation results with comparison between mjCoAP and Cal-
ifornium. (a) Number of received responses per second at different request rates.
(b) Percentage of responded requests at different request rates. (c) Response time
at different request rates.
the size of its internal buffer (which makes it possible to postpone the moment of
request serving), which causes the request to be served after the end of the obser-
vation time. This does not mean that requests are not served, but that responses
are received after the observation timeout and are therefore not counted.
Figure
3
(b) shows percentage of responded requests at different request rates,
ranging from 1 request/s to 2500 requests/s, and allows to highlight the satura-
tion point. Finally, Fig.
3
(c) shows the delay measured by the client between the
time of transmission of a request and the time of reception of the corresponding
response. In both cases, the delays are low (below
∼
14 ms) until reaching the
saturation point.
7 Conclusions
In this paper, we have introduced and described a novel lightweight and open-
source implementation of the Constrained Application Protocol, called
mjCoAP
.
mjCoAP is a standard-compliant Java-based library supporting several IETF
Search WWH ::
Custom Search