Search

Considering the increasing demand for large-scale MapReduce distributed computing, coded distributed computing (CDC) has become a promising technology to reduce the significant bottleneck of MapReduce computation. Despite its importance, most of the works on CDC have assumed homogeneous environments, where the nodes have the same storage, computing, and communication capacities. However, since many practical scenarios involve heterogeneous environments, heterogeneous CDC design is highly demanded to reduce communication load. Under consideration of full heterogeneity among workers, this paper addresses the joint design of function assignment and coded shuffling to reduce communication load effectively. We first devise a new embedded index coding (EIC) solution for the device-to-device (D2D) environment and prove its optimality. By extending our novel approach, we propose the optimal shuffling design for the MapReduce framework. Then, we figure out the optimal function assignment with the optimal shuffling design. On account of the prohibitive complexity, we propose an efficient greedy search algorithm and analyze how much performance the proposed scheme can guarantee. Numerical simulations show that our proposed algorithm provides the near-optimal communication load with a considerable complexity reduction, while we observe that the function assignment design is vital for heterogeneous CDC by comparing with the well-designed file allocation design. [ABSTRACT FROM AUTHOR]

The freshness and privateness of information in a real-time status updating is mainly investigated in this letter. First, an information freshness and privateness tradeoff is mathematically derived. Then we propose a novel private and communication-efficient framework termed crowded status updating (CSU) which enhances the freshness of information while protecting information privacy. The proposed framework outperforms the unicasting based status updating method by serving multiple clients by multicasting, which results in gaining both higher communication-efficiency and privacy. [ABSTRACT FROM AUTHOR]

Leveraging the idea of group theory, we explore the distributed matrix multiplication problem posed in on-device edge computing. We first revisit how to embed matrix multiplication into group structure and then propose a distributed matrix multiplication scheme using the cyclic group. We identify the condition for the perfect reconstruction with the proposed scheme, and exhibit that the proposed scheme has better error performance than the uncoded scheme in a noisy channel owing to the diversity gain of the proposed scheme. [ABSTRACT FROM AUTHOR]

This paper focuses on the way to protect privacy of clients requesting datasets stored in data servers while keeping communication efficiency. To this end, we introduce a novel communication-efficient and privacy protecting framework termed crowded information acquisition (CIA), well suited to a large number of clients scenario. We investigate the CIA under various conditions addressing possible communication scenarios. Contrary to the conventional belief, the results claim that a large number of clients demanding private services can enhance the privacy protection while providing low latency services and generating a small amount of traffic. [ABSTRACT FROM AUTHOR]

This paper considers a single-input single-output broadcast channel with receiver side information. We find the optimal clique cover index code and the optimal transmission time allocation that minimize outage probability when total transmission time is limited. As our problem is NP-hard, we first find the optimal time allocation for a given index code. Then, we describe a brute-force algorithm that finds the set of all decodable index codes and chooses the optimal one adopting the optimal time allocation. To reduce the computational complexity of the brute-force algorithm, we propose a pruning algorithm which solves the same problem using the Hasse diagram but does not harm the optimality. Our analysis reveals that the optimal index code is dependent on the channel conditions, not simply on the number of required transmissions, which implies that the index coding-channel coupling improves the outage performance. It is also shown that this claim is still valid for general scalar linear index coding. Our simulation results verify that our proposed schemes effectively reduce the outage probability compared to other reference schemes, and our pruning algorithm considerably reduces the computational complexity required for the brute-force algorithm. [ABSTRACT FROM AUTHOR]