Joint Optimization of Computation Offloading, Data Compression, Energy Harvesting, and Application Scenarios in Fog Computing

Fog computing is considered to be an effective method to solve the problem of high latency and high energy consumption of IoT devices. A suitable computation offloading strategy can provide a low offloading cost to the user device. Most researches on computation offloading in fog computing focus on one or two targets to improve system performance, however, the actual system needs to meet a comprehensive demand. Therefore, the joint optimization of multi-objective in multiple scenarios is a very meaningful problem. Inspired by this, the paper highlights the joint optimization research for fog computing, which proposes a Joint Computation offloading, Data compression, Energy harvesting, and Application scenarios (JCDEA) algorithm. The related mathematical model is constructed and the cost expressions of local computing, fog computing, and cloud computing are derived. Through the proposed algorithm, solving the computation offloading strategy is transformed into solving the minimum cost and is simplified by controlling strategy factors. Moreover, five simulation experiments are conducted and the meaningful conclusions are drawn, which contain that (1) the cost of fog computing is lower than that of local and cloud computing in most time slots and cloud computing can compensate for fog computing in complex environments; (2) the cost increases approximately linear with the amount of offloaded data; (3) the number of user devices and the compression ratio affect the fog-to-cloud ratio (FCR), while the FCR affects the cost; and (4) the related offloading strategy distribution and the cost are obtained for different scenarios. The JCDEA algorithm always outperforms than that of the random selection algorithm in all scenarios.