A convergecast is a popular routing in sensor networks. It periodically forwards collected data at every sensor node along a configured routing path to the outside of a sensor network via the base station (BS). To ext...A convergecast is a popular routing in sensor networks. It periodically forwards collected data at every sensor node along a configured routing path to the outside of a sensor network via the base station (BS). To extend the lifetime of energy-limited sensor networks, many previous researches proposed schemes for data compression. However, few researches investigated the relation between packet compression ratio and spanning trees. We propose packet Compression ratio dependent Spanning Tree (CST) which can provide effective routing paths in terms of the tree length for all ranges of compression ratio f. CST is equivalent to the Shortest Path spanning Tree (SPT) which is optimum in the case of no-compression (f = 0) and is equivalent to the Minimum Spanning Tree (MST) in the case of full-compression (f = 1). CST outperforms SPT and MST for any range of f (0 <f <1). Through simulation we show CST provides shorter paths than MST and SPT in terms of the tree length by 34.1% and 7.8% respectively. We confirm CST is very useful in convergecasts.展开更多
文摘A convergecast is a popular routing in sensor networks. It periodically forwards collected data at every sensor node along a configured routing path to the outside of a sensor network via the base station (BS). To extend the lifetime of energy-limited sensor networks, many previous researches proposed schemes for data compression. However, few researches investigated the relation between packet compression ratio and spanning trees. We propose packet Compression ratio dependent Spanning Tree (CST) which can provide effective routing paths in terms of the tree length for all ranges of compression ratio f. CST is equivalent to the Shortest Path spanning Tree (SPT) which is optimum in the case of no-compression (f = 0) and is equivalent to the Minimum Spanning Tree (MST) in the case of full-compression (f = 1). CST outperforms SPT and MST for any range of f (0 <f <1). Through simulation we show CST provides shorter paths than MST and SPT in terms of the tree length by 34.1% and 7.8% respectively. We confirm CST is very useful in convergecasts.
