Multi-Layer Optimisation of Heterogenous Networks using Grammatical Genetic Programming

Heterogeneous Cellular Networks are comprised of Macro Cells and Small Cells in which all cells occupy the same bandwidth. Provision has been made under the 3GPP-LTE framework for enhanced Inter-Cell Interference Coordination (eICIC) between cell tiers. Expanding on previous works, this paper instruments grammatical Genetic Programming to evolve control heuristics for Heterogeneous Networks. Three aspects of the enhanced Inter-Cell Interference Coordination framework are addressed including setting Small Cell powers and selection biases, Macro Cell duty cycles, and scheduling at Small Cells. The evolved heuristics yield minimum downlink rates four times higher than a baseline method, and 50% in excess of a state-of-the-art benchmark. Furthermore, a greater number of User Equipments receive transmissions under the proposed scheme than in either the baseline or benchmark cases.