Geometric Monitoring in Action: a Systems Perspective for the Internet of Things

Stylianopoulos, Charalampos; Almgren, Magnus; Papatriantafilou, Marina

doi:10.1109/lcn.2018.8638079

Cited by 3 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiment setup: We run our experiments in two settings, similar to the setup used in [28]: (i) A full-system evaluation on the Flocklab [22] testbed. Flocklab consists of 26 TelosB nodes deployed with a four hop topology.…”

Section: A Experimental Methodologymentioning

confidence: 99%

“…We compare the performance against a baseline (same as GM+Crystal GM+ContikiMac Figure 3: Duty-cycle during runtime when monitoring the variance with T = 2. The figure also includes results of using GM with ContikiMAC taken from [28].…”

Section: B Combining Gm and Crystal: Overall Performancementioning

confidence: 99%

“…in [26], [28]) that does not run GM and instead sends all measurements to the sink. However, in our case, the baseline uses Crystal as the underlying protocol.…”

Section: B Combining Gm and Crystal: Overall Performancementioning

confidence: 99%

“…We have simulated one of the above experiments in Cooja (we chose the one with T = 2) and continuously report the average dutycycle in Figure 3. To highlight the benefits of using GM with Crystal, compared to other network stacks, the figure also includes the equivalent results from [28] where GM is applied on top of ContikiMac [4], a mainstream network stack. The figure shows that, regardless of the protocol stack, 1 2 3 4 5 6 7ID buffer size (aggregation factor) GM exhibits a highly dynamic behavior, with periods of low activity where most of the communication is suppressed and periods of high activity (usually when the monitored value is close to the threshold) where GM communicates more.…”

Section: B Combining Gm and Crystal: Overall Performancementioning

confidence: 99%

“…Moreover, the actual energy savings on the nodes depend on the underlying communication stack and the way it interacts with GM. Previous work [28] studied the performance of GM in an applied IoT context and showed that the energy overhead of mainstream network stacks limits the effectiveness of the algorithm in practice. Thus, it is interesting to study how to close the gap between the requirements of GM and appropriate protocols that can support them.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Continuous Monitoring meets Synchronous Transmissions and In-Network Aggregation

Stylianopoulos

Almgren

Papatriantafilou

2019

2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS)

Self Cite

View full text Add to dashboard Cite

Continuously monitoring sensor readings is an important building block for many IoT applications. The literature offers resourceful methods that minimize the amount of communication required for continuous monitoring, where Geometric Monitoring (GM) is one of the most generally applicable ones. However, GM has unique communication requirements that require specialized network protocols to unlock the full potential of the algorithm. In this work, we show how application and protocol codesign can improve the real-life performance of GM, making it an application of practical value for real IoT deployments. We orchestrate the communication of GM to utilize the properties of a state-of-the-art wireless protocol (Crystal) that relies on synchronous transmissions and is designed for aperiodic traffic, as needed by GM. We bridge the existing gap between the capabilities of the protocol and the requirements of GM, especially in the case of periods of heavy communication. We do so by introducing an in-network aggregation technique relying on latent opportunities for aggregation that we exploit in Crystal's design, allowing us to reliably monitor duplicatesensitive aggregate functions, such as sum, average or variance. Our results from testbed experiments with a publicly available dataset show that the combination of GM and Crystal results in a very small duty-cycle, a 2.2x-3.2x improvement compared to the baseline and up to 10x compared to previous work. We also show that our in-network aggregation technique reduces the duty-cycle by up to 1.38x.

show abstract

Section: A Experimental Methodologymentioning

confidence: 99%

Section: B Combining Gm and Crystal: Overall Performancementioning

confidence: 99%

“…in [26], [28]) that does not run GM and instead sends all measurements to the sink. However, in our case, the baseline uses Crystal as the underlying protocol.…”

Section: B Combining Gm and Crystal: Overall Performancementioning

confidence: 99%

Section: B Combining Gm and Crystal: Overall Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations