On the forwarding capability of mobile handhelds for video streaming over MANETs

Abstract

Despite the importance of real-world experiments, nearly all ongoing research activities addressing video streaming over MANETs are based on simulation studies. Earlier research shows that the limited resources of mobile handhelds, which are not modeled in most network simulators, can be a severe bottleneck. We study the capability of a modern handheld to perform one core task, which is the forwarding of video streams. We present end-to-end video quality and network measurements, along with an analysis of resource consumption. Our studies of the recent handheld Nokia N900 show that it can forward up to 3.70 Mbps. However, subjective video quality is compromised already at 3.35 Mbps, due to excessive delay. Our analysis unveils that direct memory access (DMA) relieves the CPU of forwarding overhead and that, due to the digital signal processor (DSP) support, additional coding overhead does not decrease the forwarding capacity. Finally, we find that power management impacts results considerably. It is possible to increase the forwarding capacity up to 27.4% by increasing the frequency of internal buses. Hence, our results demonstrate that the forwarding capacity is highly dependent on the internal state and activity of the device.

MAC Layer Support for Delay Tolerant Video Transport in Disruptive MANETs

“…This would strengthen the realism of our performance evaluations. As stated in [7], we are aware that mobile hand helds have lower forwarding capability than what the wireless medium supports. Especially, we hope to investigate how to tackle packet loss due to node contention, as opposed to weak signal strength or packet collisions.…”

“…The latter is especially important in highly loaded networks. Results from our experiments with a Nokia N900 as forwarding node in a small MANET [7] reveal a high amount of MAC layer retransmissions when reaching the saturation point in a real wireless ad hoc network setting. The high amount of retransmissions is not only consuming the senders energy and link bandwidth, but also energy and bandwidth of all nodes that are in communication distance to the sender.…”

“…(2) The link towards the destination is down, and there exist no alternative route. (3) The receiving node is not able to forward traffic at the rate received from the link [7]. taildropping in the MAC retransmission queue at the sender side, or rather unlikely, the packet is lost due to collision in all retransmission trials.…”

Towards scalable and realistic node models for network simulators

“…In network technologies such as sensor networks, MANETs, or opportunistic networks, this problem is particularly prominent as nodes might have to work as end-user devices and routers. We recently studied the forwarding capacity of the Nokia N900 smart phone in real-world experiments [2]. Only with the simple task of IP forwarding, the device was not capable of forwarding more than 6 Mbps over a 54 Mbps network.…”

Modeling communication software execution for accurate simulation of distributed systems

“…Therefore, these nodes can have a substantial impact on the network performance. Experiments with the Nokia N900 smartphone [8] show that it is not capable of forwarding more than 6 Mbps over a 54 Mbps network, and that the device introduces 10-40 ms forwarding delay with 2 Mbps traffic load. However, in the network simulator Ns-3, this delay is no more than 6.85 ms, and the throughput in the equivalent experiment is 10Mbps.…”