<p>Fog computing can process data in real-time, which may minimize network congestion and delays. Load balancing and fault tolerance are critical matrices for allocating resources in a dynamic fog computing environment. They ensure that processes can continue to function even when something goes wrong, and that work is distributed properly. To optimize resource allocation in fog computing settings, this study presents a novel technique, Predictive analysis of Load balancing and Fault Tolerance (PreLoFT). The technique dynamically distributes workloads among fog nodes and forecasts resource requirements using predictive analysis. The method incorporates improved task-splitting to handle resource-intensive tasks. Additionally, it enhances fault tolerance by reallocating workloads when a node fails, enhancing the overall reliability and robustness of the system. PreLoFT’s effectiveness is evaluated and compared to more advanced algorithms like the Honeybee Foraging Algorithm (HFA), Genetic Algorithm (GA), and Load-aware Energy-efficient Scheduling (LECS), as well as traditional methods like Round-Robin (RR) and Least Loaded (LL). PreLoFT considerably enhances several metrics, such as execution time, resource use, load balancing efficiency, fault tolerance, latency, and energy consumption. It is notable for its ability to provide greater resource utilization (90%) by proactive workload management, which guarantees that nodes are not over-utilized and are functioning near their capacity. While high resource utilization maximizes performance and reduces the need to offload tasks to higher-latency cloud resources. The method also maintains energy efficiency by preventing idle resources and minimizing task migrations. The findings demonstrate that PreLoFT outperforms traditional load balancing techniques by providing faster execution times, lower latency, and better energy management, making it a promising approach for real-time fog computing environments.</p>