LSM-Tree is a critical data structure designed for write-optimized, user-facing key-value databases. However, LSM-Trees must frequently perform data merge operations to maintain read efficiency and discard obsolete data. These operations generate a considerable amount of write activity on the storage device (e.g., an SSD), which can drastically reduce the device’s lifespan. Often, these merges involve rewriting data that has not changed, a process that could be avoided. Recognizing this, we introduce “Bloom Merge,” an innovative merge strategy for LSM-Trees specifically developed for SSD. Based on the key distribution in LSM-Tree’s SSTables, this method selectively and efficiently perform merges, only when necessary. It also mitigates the potential negative impact on read performance through the strategic use of in-memory Bloom Filters. We present several key insights into determining the optimal conditions for merging and outline strategies that achieve a balanced improvement in both read and write performance. Our evaluation demonstrates that Bloom Merge significantly enhances write efficiency while reducing unnecessary operations.

There are two parameters ought to be evaluated in estimating downlink pole capacity of the WCDMA radio network. One is the downlink interference ratio, which can be precisely calculated with the link quality equation for all covered cells. Another is the downlink orthogonality factor, which is usually unknown for different multipath propagation channels in various clutter environments. When radio signal propagates in multipath channel, the orthogonality is destroyed and varies within 0.2 ~ 0.9. This gives a quite large range in estimating the cell capacity. Once the RMS delay spread of the multipath propagation channel has been measured, we can simulate the local multipath propagation channel by Monte-Carlo method for radio signals concatenating short orthogonal spreading code and long scrambling PN code to propagate. Then, in this paper, we propose a new algorithm to calculate the orthogonality factor for different spreading codes and derive a linear equation for the orthogonality factor with respect to the log-rate of data bit. With that equation, an exact solution of the downlink pole capacity for an isolated cell or a cluster of cells can be estimated when loading distribution for all services are assigned and the downlink interference ratio is calculated as well.

This paper provides a fast and precise dual least-square approach to tune the generally used propagation model, like COST231-Hata model, optimal for the 3G radio network which is in operation already. Different from traditional approach, using CW measured signal, this approach collects the combined pilot aggregate Ec signals of the on-air 3G radio network from different cells at different heights. The operating 3G radio network will not be disturbed while the experiments are taken. With the tuned propagation model, each cell could have its own propagation model depending on its antenna height, which is more optimal for its own propagation environment. These tuned 3G propagation models adapted for local clutter environment are extremely important in the network performance optimization process. The experiments were taking within the Banciao city. The tuned model called Banciao model has been verified in static Monte-Carlo simulation and proved to be more optimal for local environment area