Main features: AI training framework, novel AI model architecture, Deep Neural Network models, machine learning algorithms, innovative reinforcement learning approach.

Objectives: To improve the State-of-the-art in the corresponding domains, to increase the efficiency of ML models, to achieve near-optimal performance in computational offloading tasks in next generation 5G/6G networks.

What is new: Existing AI models/methodologies consider only a few factors to perform policy optimisation for computation offloading. NANCY’s machine learning models consider a significant amount of parameters to do so and thus, they manage to properly select the optimal policies. To accomplish this, SotA reinforcement learning AI techniques are leveraged and novel AI training methods are employed.

Why is it important: This exploitable result does not only advance the state-of-the-art of the AI models for computational offloading, but also it provides a real solution for next generation 5G/6G networks. The algorithms are designed to achieve near-optimal performance in real-world scenarios with real-world data.