Table 4.

Summary of Challenges and Mitigation Techniques in Massive MIMO System.

Challenges	Mitigation Techniques
Pilot Contamination	Pilot based Estimation [58,59], Subspace based Estimation [60], Pilot Reuse [61], Partial Sounding Resource [62], Pilot Contamination Precoding [63], Blind Pilot Decontamination [64,65], Pilot Decontamination [69], Distributed Non-Orthogonal Pilot Design [70].
Channel Estimation	Least Square [74], MMSE [75,76], Improved MMSE [77,78], Blind Estimation [80,81], Compresses Sensing [82,83], MICED [84], Untraind Deep Neural Network [85], Compressed Sensing [86], Convolutional Blind Denoising [87], VAMP [88], Deep Learning based Sparse Estimation [89], CNN based Estimation [150], Machine Learning based Estimate [151,158], Deep Learning based Estimation [153,155]
Precoding	DPP [93], TH [94,95], VP [96], MRC [97], ZF [98,99], WF [100], MMSE [101,102]
User Scheduling	ZF [105], MMSE [106], DPC [92], RR [107], PF [108], Greedy [109], Multi-user Grouping [112], Gibbs Distribution Scheme [114], Pilot Efficient Scheduling [115], Machine Learning based Scheduling [159]
Hardware Impairments	Digital Pre-Distortion [118,119], PAPR [120],
Signal Detection	SD [122], SIC [123], ML [47], ZF [124], MMSE [125], NSA [132], Richardson [133], SOR [74], Jacobi [134], Gauss Siedel [135], Conjugate Gradient [131], Least Square Regression Selection [136], Huber ADMM [137], AMP [138] Compressed Sensing based Adaptive Scheme [86], CNN [140], Gauss Siedel Refinement [143], SSL and SL based Detection [162,163], APRGS [169]