A Block-based Linear Index Supporting NN Search for Massive Clients

다국어 초록 (Multilingual Abstract)

The convergence of Fourth Industrial Revolution technologies—such as artificial intelligence (AI), the Internet of Things (IoT), big data, cloud computing, blockchain, and 5G—has created an urgent demand for efficient data delivery mechanisms capable of serving massive numbers of clients simultaneously. Wireless data broadcasting has emerged as a promising solution for such environments, particularly in IoT applications. In this paper, we propose a block-based linear index (BLI) to enable efficient nearest neighbor (NN) search in wireless broadcast channels. The proposed method partitions spatial data into irregularly shaped blocks using clustering, and stores block distribution information in a linear table structure. This approach reduces the NN search space, resulting in lower access time and tuning time compared to conventional indexing techniques such as HCI, DSI, and NSPI. Simulation results demonstrate that BLI achieves faster NN retrieval and improved energy efficiency, making it suitable for large-scale, real-time data access in modern wireless computing environments.