Load Balancing Hotspots in Sensor Storage Systems
|Mohamed Aly||University of Pittsburgh|
Notice: hosted by Jeffrey Davitz
Date: 2007-09-25 at 13:00
Location: EJ291 (SRI E building) (Directions)
We consider a sensor network where sensors are deployed in an ad-hoc manner. Users with mobile devices issue ad-hoc queries usually from within, or nearby, the queried area. The emergence of ad-hoc queries has recently increased the popularity of in-network Data-Centric Storage (DCS), where sensor readings are temporarily stored in the sensor caches and directly used to answer ad-hoc queries. Two main problems arising in this network model are: storage hotspots and query hotspots. Storage hotspots are formed when many sensor readings are mapped for storage to a relatively small number of sensors. Query hotspots occur when many user queries target a small number of sensors. Both types of hotspots are hard to expect and result in many problems, such as decreasing the Quality of Data (QoD) of the sensor network and reducing the network lifetime.
In this talk, we will discuss two load-balancing strategies to solve the hotspots problem: the detection and decomposition, and the avoidance. We will first present the Zone Sharing (ZS) algorithm, a local storage hotspot detection and decomposition scheme. To globally avoid hotspots of large sizes, we present the K-D tree based Data-Centric Storage (KDDCS), a fully load-balanced DCS scheme avoiding storage and/or query hotspots. Finally, we will briefly present Zone Partitionig/Zone Partial Replication (ZP/ZPR), which are two local query hotspot detection and decomposition schemes.
Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page.