On caching and prefetching of virtual objects in distributed virtual environments

Abstract

ld~~ces in networkg tetiology and the mtabkhtnent of the Morrnation Superhighway have rendered the virtnd Xbrary a concrete possibfi~. ?iTeze currently investigating user &\Terience in _ through a large virtual environment in the contti% of bternet. This provid~users with the abiity to view t+ous virtual objects from tirent & t anca and angles, using common web browsers. To dtiver a good petiorrnance for such applications, we need to addr~s Several issues in Merent resemch discipbes.F&t., we must be able to modd virtual objects tiectivdy. The recently devdoped techniques for mdti-~olution object modting in computer graphics are of great Aue here, since they are capable of sintp~g the object mod-& and therefore reducing the time to render them. Secon& tith the Eted bandwidth constraint of the btemet, we need to reduce the response time by reducing the amount of data requwted over the network One dtemative is to cache object mod& of high -w.Prefetching object mod~by predicting those which~e &dy to be used in the near fnture and dotioading them in advance wiU lead to a Mar improvement. Third, the bt.ernet often tiers from disconnection. A caching mechanism hat dews objects to be cached n?th at least the-mminimum resolution m be wet o provide at least a coarse x<ew of the objects to a disconnected >tiewerfor improved~hd perception. k this paper, m propose a multi-T~*oZutionaching m~hrmtim wd invG tigate its tiectiveness in supporthg virtud w~u~ap-FEcations in the ktemet. environment. The caching mechanism is further complemented with severs object prefetching m echanLms for predicting future acc~ed objects. The performance of our proposed me~and their feasibfities are qnsmtXed via s"mtdat.ed~Terirnents.

Computational Neuroscience Breakthroughs through Innovative Data Management

“…In this experiment we have executed different series of range queries from different applications (visualization, model building) which differ in size of each query (30'000 to 80'000µm 3 ) as well as the length of the series (ranging from 25 to 65). The experiment shows that SCOUT speeds up the analysis considerably: the cache hit rate of SCOUT is 4× higher for the visualization query series resulting in a 7× higher speedup compared to EWMA [22], the fastest stateof-the-art approach (based on polynomial extrapolation). Like FLAT, SCOUT also speeds up the model building process and allows the neuroscientists to build bigger models considerably faster.…”

On error bound estimation for motion prediction

“…They are general predictors and are not designed for any specific objects. In [7], an EWMA scheme was used for object prefetching in a DVE. It assigns different weights to past movement vectors, with higher weights to recent ones.…”

“…In case of a critical application, we may even temporary disallow A to edit the object concurrently if the estimated error bounds are too wide apart. In addition, in some applications where geometry data are dynamically streamed to the clients (e.g., very large dataset [7] and data generated from many remote sources [1]), these data need to be prefetched to the clients before they are accessed. If we know that a particular prediction has a small error, we may adopt an optimistic approach in prefetching to save network bandwidth by not streaming geometry data which are relatively far from the predicted position.…”

Prefetching for visual data exploration

“…This is similar to our focus strategy, in the sense of associating usage values with the object space instead of focussing on user trace analysis. Mean and exponential weight average strategies have been inspired by [2]. Direction strategy is similar to sequential prefetching strategies [3,18].…”