Mobile Ad-hoc Network (MANET) is a self-organizing wireless network that communicates without infrastructure and suffering from low power-battery. The challenges of under-optimization have received a great amount of attention from researchers, and Energy Consumption (EC) is the most important of those challenges for them in this field. Therefore, the main objective in finding a route from source to destination is to minimize node EC. Integer Linear Programming (ILP) and Ant Colony Optimization (ACO) are two algorithms that enhance EC and processing time, which are Quality of Service (QoS) requirements. In our paper, we proposed the two algorithms, which are evaluated regarding two criteria: EC and processing time using an experimental study. The optimal route of the proposed ILP is chosen from all possible routes using the minimum EC as an objective function and a set of constraints. The second algorithm is a proposed ACO version, based on ants’ behaviour Looking for a path from their colony to their food source. The two proposed algorithms were implemented and compared according to different criteria (route selection, EC and processing time).

MIMO: multiple-input multiple-output technology uses multiple antennas to use reflected signals to provide channel robustness and throughput gains. It is advantageous in several applications like cellular systems, and users are distributed over a wide coverage area in various applications such as mobile systems, improving channel state information (CSI) processing efficiency in massive MIMO systems. This chapter proposes two channel-based deep learning methods to enhance the performance in a massive MIMO system and compares our proposed technique to the previous methods. The proposed technique is based on the channel state information network combined with the gated recurrent unit’s technique CsiNet-GRUs, which increases recovery efficiency. Besides, a fair balance between compression ratio (CR) and complexity is given using correlation time in training samples. The simulation results show that the proposed CsiNet-GRUs technique fulfills performance improvement compared with the existing literature techniques, namely CS-based methods Conv-LSTM CsiNet, LASSO, Tval3, and CsiNet.