A Novel Lightweight Dynamic Trust Evaluation Model for Edge Computing

The temporal decay of trust data in dynamic edge computing environments leads to inaccurate evaluation, and the recommended trust values from heterogeneous nodes are affected by subjective bias and are vulnerable to malicious attacks. To address these issues, this paper proposes a novel lightweight dynamic trust evaluation model. First, a time decay function is derived based on Newton’s law of cooling to effectively reflect the impact of trust timeliness on trust evaluation. On this basis, the real value is iteratively calculated and used as the recommended trust value through the truth discovery algorithm, enhancing the accuracy of trust evaluation. Then, the weight of the recommended trust value in the comprehensive trust value is determined based on the standard deviation of the weight of perceived data from each recommending node, balancing the influence of subjective and objective factors on trust evaluation results. Lastly, the comprehensive trust value is dynamically weighted, and an incentive mechanism is employed to update trust data based on feedback, reflecting the dynamic nature of trust. Theoretical analysis demonstrates that the model presented in this paper exhibits low time and space complexities, meeting the lightweight requirements of the edge computing environment. Experimental results indicate high recommendation trust accuracy and interaction success rates, as well as effective resistance against malicious attacks.