To process data from IoTs and wearable devices, analysis tasks are often offloaded to the cloud. As the amount of sensing data ever increases, optimizing the data analytics frameworks is critical to the performance of processing sensed data. A key approach to speed up the performance of data analytics frameworks in the cloud is caching intermediate data, which is used repeatedly in iterative computations. Existing analytics engines implement caching with various approaches. Some use run-time mechanisms with dynamic profiling and others rely on programmers to decide data to cache. Even though caching discipline has been investigated long enough in computer system research, recent data analytics frameworks still leave a room to optimize. As sophisticated caching should consider complex execution contexts such as cache capacity, size of data to cache, victims to evict, etc., no general solution often exists for data analytics frameworks. In this paper, we propose an application-specific cost-capacity-aware caching scheme for in-memory data analytics frameworks. We use a cost model, built from multiple representative inputs, and an execution flow analysis, extracted from DAG schedule, to select primary candidates to cache among intermediate data. After the caching candidate is determined, the optimal caching is automatically selected during execution even if the programmers no longer manually determine the caching for the intermediate data. We implemented our scheme in Apache Spark and experimentally evaluated our scheme on HiBench benchmarks. Compared to the caching decisions in the original benchmarks, our scheme increases the performance by 27% on sufficient cache memory and by 11% on insufficient cache memory, respectively.
<p>One of the ways to increase green areas that are shrinking due to urbanization is to create urban roadside greenery. Among the various ecosystem services of roadside greenery, carbon uptake plays a significant role in reducing CO<sub>2</sub>, the main factor of climate change. Multi-layered planting can enhance carbon uptake, which is focused on as an effective method. Hence, the roadside ecosystem consists of trees, understory shrubs, and soil. Although shrubs are as crucial as trees because of the large number of populations per unit area, only a few studies were focused on shrubs. Therefore, considering shrub carbon uptake is necessary for estimating the accurate carbon exchange on the roadside ecosystem.</p> <p>This study focused on the roadside greenery composed of a tree, shrubs, and soil in the unit 1m x 8m area. The experiment was conducted in Suwon city, the Republic of Korea. The selected tree and shrub are <em>Zelkova serrata</em> and <em>Euonymus japonicus</em>, the most common species in Suwon. Net Ecosystem Exchange(NEE) was calculated by the equation [NEE = NPP<sub>tree</sub> + NPP<sub>shrub</sub> + R<sub>heterotroph</sub>]. NPP<sub>tree</sub> was estimated through the allometric equation. NPP<sub>shrub</sub> and R<sub>heterotroph</sub> were calculated through measurements. To calculate NPP<sub>shrub</sub>, two experiments were conducted. One was field measurement using the closed chamber with LI-820, and another was greenhouse incubation and harvesting. In the field measurement, the closed chamber measured the real-time change of CO<sub>2</sub> concentration including leaf photosynthesis and stem respiration, and the results showed the aboveground NPP<sub>shrub</sub>. Also, environmental factors such as air temperature, PAR (photosynthetically active radiation), and leaf area were collected. In the greenhouse experiment, the results showed the accurate NPP<sub>shrub</sub> without considering field conditions. With those two results, the equation for calculating field shrub NPP was developed considering field conditions and root respiration. However, the closed chamber has a problem with installation, management, and stability, so the leaf chamber would be more adaptable for field measurement than the closed chamber. For accurate measurement of field shrub NPP, this study also did an experiment using Vaseline to block the stomata to calculate the proportion of stem respiration in the aboveground NPP<sub>shrub</sub>. The stem respiration can be measured by comparing the CO<sub>2</sub> concentration change before and after pasting Vaseline on the shrub leaves in the closed chamber. Soil respiration(R<sub>s</sub>) was measured by EGM-5 in the field and used the equation [R<sub>s</sub> = R<sub>root</sub> + R<sub>heterotroph</sub>].</p> <p>The results of these experiments accurately estimated NPP<sub>shrub</sub> and R<sub>heterotroph</sub>, and the NEE of the 1m x 8m roadside greenery section could be quantified as 5.23 kg C/yr. This amount could mitigate 1.09% of annual vehicle carbon emissions in Suwon city if roadside greenery is applied on all roadsides in Suwon.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.