The utilization of fifth-generation wireless technology (5G) and artificial intelligence (AI) has opened many paths toward making solar power utility systems run more efficiently. 5G and AI have emerged within the last couple of years as competent technologies that can be used in various settings, including within the field of utility delivery. The main concern about this is how these technologies should be used in renewable energy systems and to what extent they improve operations. This research work is about 5G-enabled solar power systems. One of the models used AI-based implementation, while the other does not. Data for both models pertained to parameters such as power, state of charge, harmonic distortion, and voltage are collected. The results are then compared to determine the effectiveness of using AI with the system. Analysis has shown that implementing AI technology with 5G in a solar power system greatly improves power efficiency by stabilizing the voltage of the model. Furthermore, integrating AI with this model has proven to show unparalleled accuracy compared to a version of the model that does not use AI. It can therefore be inferred that usage of 5G with AI technologies will generally be an improvement over solar power implementations that do not use them.

This research work presents a reinforcement learning (RL)-based algorithm for dynamically modulating schemes in 5G New Radio (NR) downlink transmissions over a Multiple Input Multiple Output (MIMO) channel. By emulating a real scenario of an 8×8 MIMO Physical Downlink Shared Channel (PDSCH) under Additive White Gaussian Noise (AWGN) and 3GPP TDL-C fading, we apply a Deep Q-Network (DQN) agent for adaptively learning to select types of modulation such as QPSK, 16QAM, 64QAM, 256QAM, and 1024QAM from monitored Signal-to-Noise Ratio (SNR) and Channel State Information (CSI). Simulation results show that the RL-based adaptive modulation scheme improves Bit Error Rate (BER) and relative throughput in various Signal Noise Ratio (SNR) conditions, showing better Quality of Service (QoS) than fixed modulation schemes. Compared to general sampling, in preliminary results, the RL model shows a 34% improvement in BER using DQN and about 29% improvement using PPO. For relative throughput, the DQN agent improved by about 6.5%.

The fifth generation (5G) of wireless communication networks uses the advantages of Massive Multiple-Input Multiple-Output (MIMO) technologies to improve network coverage, increase data speeds, and enhance reliability. One of the challenges that has risen from utilizing massive MIMO as a leading technology in the advancement of 5G is the difficulty to model massive MIMO channels due to the high cost of the hardware and the computational complexity. In this research, ray tracing, which is an effective channel modeling method, is employed using the MIMO- Orthogonal frequency division multiplexing (OFDM) technique to simulate the interactions between various IoT devices and the network's access point. The ray tracing evaluation is performed on a 3D model of a conference room which allows for the evaluation of the network's performance in a complex indoor environment. The experiments are run using different surface materials and channel parameters are measured for each experiment to understand the different factors that affect the performance. The power delay and the path loss for an IoT device in the line of sight (LOS) and an IoT device not in LOS are analyzed. The magnitude of the signals propagated to an IoT device in LOS are higher and the path loss is lower. Furthermore, using metal as the surface material results in the least amount of path loss, and using wood results in the highest amount of path loss. The bit error rates when metal, glass, and wood are used are also measured. The use of metal results in the lowest bit error rates and wood results in the highest bit error rates for the IoT devices.