A Data-Driven Self-Optimization Solution for Inter-Frequency Mobility Parameters in Emerging Networks
A Data-Driven Self-Optimization Solution for Inter-Frequency Mobility Parameters in Emerging Networks
复制标题
DOI：
10.1109/tccn.2022.3152510
复制
发表时间：
2022-06
影响因子：
8.6
通讯作者：
Muhammad Umar Bin Farooq;Marvin Manalastas;W. Raza;Syed Muhammad Asad Zaidi;A. Rizwan;A. Abu-Dayya;A. Imran
中科院分区：
文献类型：
--
作者：
Muhammad Umar Bin Farooq;Marvin Manalastas;W. Raza;Syed Muhammad Asad Zaidi;A. Rizwan;A. Abu-Dayya;A. Imran
密集化和多频段操作意味着频率间切换可能成为新兴蜂窝网络中移动用户体验的瓶颈。由于不存在优化关键异频切换参数（即 A5 触发时间、A5 阈值 1 和 A5 阈值 2）的方法，这一事实加剧了这一挑战。本文提出了第一项研究，分析和优化三个 A5 参数，以共同最大化反映移动用户体验的三个关键性能指标：切换成功率 (HOSR)、参考信号接收功率 (RSRP) 和信号干扰加噪声比 (SINR)。由于分析模型无法捕获系统级的复杂性，因此我们采用数据驱动的方法。为了最大限度地减少训练数据生成时间，我们利用了 shapley 附加解释 (SHAP) 敏感性分析。 SHAP 分析的见解允许有选择地收集训练数据，从而能够更轻松地在实际网络中实施所提出的解决方案。我们证明了 RSRP、SINR 和 HOSR 联合优化问题是非凸的，并使用遗传算法 (GA) 对其进行求解。然后，我们提出了一种针对 GA 的智能突变方案，该方案使解决方案比传统 GA 快 5 倍，比暴力搜索快 21 倍。因此，本文提出了第一个解决方案来实现频率间移动性参数的计算高效的闭环自优化。
Densification and multi-band operation means inter-frequency handovers can become a bottleneck for mobile user experience in emerging cellular networks. The challenge is aggravated by the fact that there does not exist a method to optimize key inter-frequency handover parameters namely A5 time-to-trigger, A5-threshold1 and A5-threshold2. This paper presents a first study to analyze and optimize the three A5 parameters for jointly maximizing three key performance indicators that reflect mobile user experience: handover success rate (HOSR), reference signal received power (RSRP), and signal-to-interference-plus-noise-ratio (SINR). As analytical modeling cannot capture the system-level complexity, we exploit a data-driven approach. To minimize the training data generation time, we exploit shapley additive explanations (SHAP) sensitivity analysis. The insights from SHAP analysis allow the selective collection of the training data thereby enabling the easier implementation of the proposed solution in a real network. We show that joint RSRP, SINR and HOSR optimization problem is non-convex and solve it using genetic algorithm (GA). We then propose an intelligent mutation scheme for GA, which makes the solution 5x times faster than the legacy GA and 21x faster than the brute force search. This paper thus presents first solution to implement computationally efficient closed-loop self-optimization of inter-frequency mobility parameters.