Delay-Optimal User Scheduling and Inter-Cell Interference Management in Cellular Network via Distributive Stochastic Learning

TL;DR

This paper introduces a distributive stochastic learning approach for delay-optimal user scheduling and interference management in cellular networks, effectively handling complex POMDP models with low computational complexity.

Contribution

It develops a novel distributive online stochastic learning algorithm for delay-optimal scheduling and interference control, addressing NP-hard POMDP challenges with linear complexity.

Findings

The proposed algorithm converges almost surely.

It achieves significant delay performance gains.

Complexity scales linearly with the number of BSs and users.

Abstract

In this paper, we propose a distributive queueaware intra-cell user scheduling and inter-cell interference (ICI) management control design for a delay-optimal celluar downlink system with M base stations (BSs), and K users in each cell. Each BS has K downlink queues for K users respectively with heterogeneous arrivals and delay requirements. The ICI management control is adaptive to joint queue state information (QSI) over a slow time scale, while the user scheduling control is adaptive to both the joint QSI and the joint channel state information (CSI) over a faster time scale. We show that the problem can be modeled as an infinite horizon average cost Partially Observed Markov Decision Problem (POMDP), which is NP-hard in general. By exploiting the special structure of the problem, we shall derive an equivalent Bellman equation to solve the POMDP problem. To address the distributive requirement and the issue of dimensionality and computation complexity, we derive a distributive online stochastic learning algorithm, which only requires local QSI and local CSI at each of the M BSs. We show that the proposed learning algorithm converges almost surely (with probability 1) and has significant gain compared with various baselines. The proposed solution only has linear complexity order O(MK).