استخراج رابطه توپولوژيك بين ناحيه‌هاي حفره‌دار در محيط شبكه‌هاي حسگر مكاني بي‌سيم

Extraction of Topological Relations between Regions with Holes in Wireless Geosensor Networks

شبكه­های حسگر مكانی بی­سیم از تعداد زیادی گره تشكیل شده­اند كه هر یك از این گره­ها به صورت كامپیوترهایی با توانمندی حسگر هستند. یكی از موارد مهم كاربرد این شبكه­ها استخراج رابطه توپولوژیك بین ناحیه­ها در برخی پدیده­ها، مانند كشف عوامل ایجاد آتش­سوزی جنگل­ها است، زمانی كه رابطه توپولوژیك توده هوای بسیار گرم، مواد اشتعال­زا و محدوده جنگل از رابطه توپولوژیك «جدا» به «همپوشانی» و «درون» تبدیل می­شود. وجود حفره­ها در پدیده­های محیطی، مانند وجود باتلاق­ها یا كوه­ها در برخی مناطق، مستلزم این است كه این ناحیه­ها در محیط شبكه­های حسگر مكانی بی­سیم به صورت ناحیه­های مكانی حفره‌دار مدل شوند. در این مقاله، ناحیه­های حفره‌دار توسط شبكه حسگر مكانی پایش شده و رابطه توپولوژیك بین آنها استخراج می­شود. به منظور استخراج رابطه توپولوژیك بین ناحیه­های حفره‌دار در محیط شبكه­های حسگر مكانی، الگوریتمی طراحی شد. مدل­های تئوری قبلی مانند 4-اشتراكی، 9-اشتراكی و RCC تنها برای استخراج رابطه توپولوژیك بین ناحیه­های بدون حفره به كار می­روند و قادر به متمایز كردن رابطه­های توپولوژیك گوناگون بین ناحیه­های حفره‌دار نیستند؛ در الگوریتم طراحی شده از مدل 9-اشتراكی توسعه یافته استفاده شده تا بتوان رابطه توپولوژیك بین یك ناحیه بدون حفره و ناحیه حفره‌دار دیگر را استخراج كرد. با توجه به شرایط محیطی شبكه ممكن است تعیین موقعیت گره­ها با استفاده از GPS امكان­پذیر نباشد، لذا الگوریتم به گونه­ای عمل خواهد كرد كه گره­ها بدون داشتن موقعیت مكانی، تنها با تكیه بر اطلاعات همسایگی مجاور خود رابطه توپولوژیك بین دو ناحیه را بدست آورند. در الگوریتم طراحی شده از سیستم محاسبات غیرمتمركز استفاده شده و پیاده­سازی آن در یك محیط شبیه­سازی انجام شده است.

Geosensor networks are constituted from a large number of nodes that each of these nodes are same sensor-enabled computers. Geosensor network can be imagined as microscopy environmental that gives collection and process of environmental information with specified spatial temporal resolution and high detailed in real time. One of the important applications of these networks is the extraction of topological relation between regions in some phenomena, such as discovery of the causes of forest fires creation, when the topological relation between very hot air, flammable materials, and forest region is converted from “disjoint” to “overlap” and “inside”. Due to existence of cavities in environmental phenomena, marshes or mountains in some regions, these regions must be modeled as regions with holes in geosensor networks. In this research, the regions with holes are monitored by geosensor network and the topological relation between them is extracted. In order to extract topological relation between regions with holes in geosensor networks, an algorithm was designed. Theoretical models, for example 4-intersection, 9-intersection, and RCC are used only for extraction of topological relation between regions that have not any holes, and these models cannot distinguish different topological relations between regions with holes; in designed algorithm, the modified 9-intersection model is used to derive topological relation between a region and another region with a hole. To calculate the this 9-intersection model and extracting relations between these two regions, only it is required that topological relation between the region without hole with each of hole and general region elements of region with holes is determined. In this research, in the first step, 4-intersection model is used and then topological relations between two regions are determined by calculating the modified 9-intersection model. Due to the environment conditions of network, it might not possible to carry out positioning the nodes by GPS; hence, the algorithm will act in such a method that nodes without position obtain topological relation between two regions only based on one-hop neighborhood information. In designed algorithm, decentralized computing system is used and its implementation is evaluated in a simulation. For implementation of designed algorithm, it is required that regions, geosensor network, and communication between nodes are modeled in the simulation program. After modeling of the regions, distributing of nodes is modeled randomly on these regions. It is required that communication between nodes to be possible through neighboring structures. The most basic network neighboring structure is unit disk graph which was used as the default structure in this research. Moreover, it is required to have a coverage structure for merging and integrating of information in the network, that a rooted tree structure is used in this research. Based on the rooted tree structure, one of the network nodes is selected as the root node and other nodes send own local information to the root node in path of tree branches. The local processing is done in each of network nodes and topological relation is calculated locally. Then, the local information was integrated with each other across network nodes and sent to root node. Finally, topological relation between two regions is determined in the root node based on the developed 9-intersection model.