
Multipath solutions have been shown to help improve throughput, reliability and/or load balancing. This paper seeks to understand if and when they benefit rate stability. Rate stability is important to many real-time, interactive applications, e.g., streaming video, but whether multipath solutions can help is unclear. Of relevance is the time-scale at which bandwidth changes are detected and acted upon to rebalance transmissions across paths. Consider two boundary cases: instantaneous detection and rate re-allocation, and a static rate assignment based on long-term path statistics. When transmissions can be instantaneously rebalanced across paths based on real-time link rate information, a multipath solution trivially improves rate stability (it all but eliminates rate variations). In contrast, when rate allocations are static, we find that multipath cannot improve upon the best single-path solution when buffers are large. When buffers are small (and coding is used to overcome losses), a multipath solution can, however, be beneficial even under a static rate allocation. The paper provides insight into when and how multipath solutions can help improve rate stability.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
