Projects

Abstract: With the rise of digital images, content-based image retrieval (CBIR) methods have been extensively studied. CBIR service is computationally and storage-intensive. Thus, outsourcing CBIR to a powerful cloud server is a good idea. The…

Abstract: Service providers (SPs) will struggle to meet resource requests as cloud computing grows. That means two or more SPs may form a federation and share resources to meet cloud users’ demand and gain economic…

Abstract: Cloud computing energy efficiency is being researched because data centers use a lot of energy. However, reducing energy consumption without increasing Service Level Agreement violations is difficult. Most virtual machine (VM) consolidation approaches constrain…

Abstract: Cloud computing deploys network services on geographically distributed cloud platforms, which increases inter-datacenter traffic. CSPs charge cloud users for inter-datacenter transmission services using multi-tier pricing. Cloud users often choose a high service level to…

Abstract: In cloud-deployed distributed data stores, server performance fluctuates. Thus, the reading request replica directly impacts response latency. Key-value stores are latency-critical, making replica selection difficult. Small data stores require clients to choose replicas. Even…

Abstract: We design compressive measurement matrices for time-varying sparse signals adaptively. This is a partially observable Markov decision process. This formulation lets us apply Bellman’s optimality principle to multi-step lookahead compressive measurement designs. We use…

Abstract: Searchable encryption (SE) has gained popularity in encrypted cloud storage due to the high demand for searchability over encrypted data. Most SE-based cloud storage systems assume the cloud server is honest-but-curious and follows the…

Abstract: DCNs enable cloud services. With increased bandwidth and size, DCN energy consumption and cost rise sharply. Topology, addressing, and routing affect DCN energy consumption, complexity, and cost. This paper proposes a new addressing and…

Abstract: Computation offloading reduces smartphone energy consumption and improves performance. We propose and implement a lightweight offloading framework to offload compute-intensive tasks and simplify server deployment to address the heterogeneous architectures of the smartphone and…

Abstract: Due to an exponential rise in demand for eco-friendly environments, the global green city revolution has accelerated for years. Thus, major energy consumers must switch to renewable energy sources (RES). Cloud data centers (DCs)…

Abstract: This project proposes a many-to-many service mechanism for profit optimization between cloud providers and customers. We use game theory to solve this problem, but not like other cloud resource pricing game methods. First, we…

Abstract: Datacenter applications need low-latency data service. Proper data placement in modern distributed storage systems reduces data movement delay, which can greatly reduce service latency. Existing data placement solutions often assumed data request distribution or…