GTGO-driven joint task offloading and resource allocation with explainable AI in vehicular edge computing

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Due to the fast development of intelligent transportation systems and connected vehicles, efficient computation offloading and resource management in vehicular edge computing (VEC) environments have become crucial issues. Low latency, optimality in resource usage, and clarity in decision-making is an open research issue. This paper presents a framework based on GTGO to jointly offload, schedule and allocate resources to different tasks and augment it with an integrated explainable AI (XAI) module. The proposed method enhances system welfare by approximately 15-25 percent and decreases the average task delay by 10-20 percent compared to the baseline approaches as the number of task vehicles increases. The GTGO algorithm converges rapidly and it will stabilize after 30-50 iterations hence guaranteeing computational efficiency. Also, the XAI module is a way of quantitatively understanding the contribution of decision variables to the interpretation of the results, without affecting optimization performance. These findings indicate that the suggested framework is an effective, efficient, and transparent resource management solution in intelligent vehicular edge computing systems.