Mobile Cloud Computing (MCC) integrates cloud computing into the mobile environment, effectively tackling performance, environmental, and security constraints. However, the proliferation of clouds and applications introduces complexities in offloading decisions. Mobile Edge Computing (MEC) has emerged as a solution to bolster MCC performance, capitalizing on the proximity to edge devices. However, optimizing computation offloading remains paramount for heterogeneous smart (mobile phones, wearables, and IoT) devices, necessitating efficient utilization of network resources and computational offloading. To address these challenges, this paper introduces NSANNOM (Network and Device Resources Utilization through Smart ANN-based Offloading Mechanism), an expert system designed for optimal computational offloading decision-making and efficient network resource allocation mechanisms. NSANNOM employs Artificial Neural Networks (ANN) for precise decision-making by validating real-world datasets, underscoring ANN’s superiority over existing algorithms, and showcasing enhanced energy savings, cost efficiency, and latency response. Experimental evaluations demonstrate that the proposed ANN model for the offloading decision-making algorithm achieves a training accuracy of 97 and a validation accuracy of 99. The system consumes minimal energy (10 MJ) for task scheduling and exhibits remarkable accuracy in resource utilization across multiple tasks (10–50) ranging in size (from 1 to 16 GB). Additionally, it minimizes time delays (in milliseconds) during the offloading process.

中文翻译：

---

异构 MEC-MCC 环境中混合边缘到云计算卸载的专家系统

移动云计算（MCC）将云计算集成到移动环境中，有效解决性能、环境和安全约束。然而，云和应用程序的激增给卸载决策带来了复杂性。移动边缘计算 (MEC) 已成为一种利用边缘设备的邻近性来增强 MCC 性能的解决方案。然而，优化计算卸载对于异构智能（手机、可穿戴设备和物联网）设备仍然至关重要，因此需要有效利用网络资源和计算卸载。为了应对这些挑战，本文介绍了 NSANNOM（通过基于智能 ANN 的卸载机制实现网络和设备资源利用），这是一种专为优化计算卸载决策和高效网络资源分配机制而设计的专家系统。 NSANNOM 采用人工神经网络 (ANN) 通过验证真实世界数据集来进行精确决策，强调 ANN 相对于现有算法的优越性，并展示增强的节能、成本效率和延迟响应。实验评估表明，所提出的卸载决策算法的 ANN 模型达到了 97 的训练精度和 99 的验证精度。该系统在任务调度上消耗最少的能量（10 MJ），并且在多个任务的资源利用率方面表现出卓越的准确性(10–50) 大小不等（从 1 到 16 GB）。此外，它还可以最大限度地减少卸载过程中的时间延迟（以毫秒为单位）。