In the sixth-generation (6G) cellular networks, hybrid beamforming would be a real-time optimization problem that is becoming progressively more challenging. Although numerical computation-based iterative methods such as the minimal mean square error (MMSE) and the alternative manifold optimization (Alt-Min) can already attain near-optimal performance, their computational cost renders them unsuitable for real-time applications. However, recent studies have demonstrated that machine learning techniques like deep neural networks (DNN) can learn the mapping done by those algorithms between channel state information (CSI) and near-optimal resource allocation and then approximate this mapping in near real-time. In light of this, we investigate various DNN architectures for beamforming challenges in the terahertz (THz) band for ultra-massive multiple-input multiple-output (UM-MIMO) and explore their contextual mathematical modeling. Specifically, we design a sophisticated 1D convolutional neural network, and long short-term memory (1D CNN-LSTM) based fusion-separation scheme, which can approach the performance of the Alt-Min algorithm in terms of spectral efficiency (SE) for fully connected structures and, at the same time, use significantly less computational effort. Simulation results indicate that the proposed system can attain almost the same level of SE as that of the numerical iterative algorithms while incurring a substantial reduction in computational cost. Our DNN-based approach also exhibits exceptional adaptability to diverse network setups and high scalability. Although the current model only addresses the fully connected hybrid architecture, our approach can also be expanded to address a variety of other beamforming topologies.

The widespread proliferation of internet access, affordable wireless gadgets, the user data demand and the corresponding extended cellular networks entailing significant energy consumption and carbon footprints. With the added benefits of renewable energy harvesting (REH) technology, telecom base stations (BSs) are predominantly supplied by green power sources to reduce operational expenditure (OPEX) and atmospheric pollution with guaranteed quality of service (QoS). Accordingly, this paper examines the plausibility of optimal power supply solutions such as standalone solar photovoltaic (PV), hybrid PV/wind turbine (PV/WT), hybrid PV/diesel generator (DG) and hybrid PV/electric grid (PV/EG) to feed the Long Term Evolution (LTE) BSs pertaining to technical, economic and environmental aspects in Bangladesh. An extensive Monte-Carlo based simulations are performed to evaluate wireless network performance in terms of throughput, energy efficiency (EE), energy efficiency gain (EE gain ), average energy savings, radio efficiency varying system bandwidth (B) and BS transmission power (P TX ) considering the dynamic behavior of traffic intensity and renewable energy (RE) generation profile. By leveraging the cell zooming technique and a green traffic steering framework endeavors to minimize the net present cost and maximize the average energy savings as well. The simulation results reveal that the cell zooming technique attained energy savings yielding up to 36% and improvement of EE gain achieved about 23% with effective modeling of REH. Subsequently, a comprehensive comparison of the aforementioned schemes is pledged for further validation.

We propose a distributed cooperative framework among base stations (BS) with load balancing (dubbed as inter-BS for simplicity) for improving energy efficiency of OFDMA-based cellular access networks. Proposed inter-BS cooperation is formulated following the principle of ecological self-organization. Based on the network traffic, BSs mutually cooperate for distributing traffic among themselves and thus, the number of active BSs is dynamically adjusted for energy savings. For reducing the number of inter-BS communications, a three-step measure is taken by using estimated load factor (LF), initializing the algorithm with only the active BSs and differentiating neighboring BSs according to their operating modes for distributing traffic. An exponentially weighted moving average (EWMA)-based technique is proposed for estimating the LF in advance based on the historical data. Various selection schemes for finding the best BSs to distribute traffic are also explored. Furthermore, we present an analytical formulation for modeling the dynamic switching of BSs. A thorough investigation under a wide range of network settings is carried out in the context of an LTE system. Results demonstrate a significant enhancement in network energy efficiency yielding a much higher savings than the compared schemes. Moreover, frequency of inter-BS correspondences can be reduced by over 80%.

The enormous growth in the cellular networks and ubiquitous wireless services has incurred momentous energy consumption, greenhouse gas (GHG) emissions and thereby, imposed a great challenge to the development of energy-efficient sustainable cellular networks. With the augmentation of harvesting renewable energy, cellular base stations (BSs) are progressively being powered by renewable energy sources (RES) to reduce the energy crisis, carbon contents, and its dependency on conventional grid supply. Thus, the combined utilization of renewable energy sources with the electrical grid system is proving to be a more realistic option for developing an energy-efficient as well as an eco-sustainable system in the context of green mobile communications. The ultimate objective of this work is to develop a traffic-aware grid-connected solar photovoltaic (PV) optimal power supply system endeavoring the remote radio head (RRH) enabled heterogeneous networks (HetNets) aiming to minimize grid energy consumption and carbon footprint while ensuring long-term energy sustainability and energy efficiency (EE). Moreover, the load balancing technique is implemented among collocated BSs for better resource blocks (RBs) utilization and thereafter, the performance of the system is compared with an existing cell zooming enabled cellular architecture for benchmarking. Besides, the techno-economic feasibility of the envisaged system has been extensively analyzed using HOMER optimization software considering the dynamic nature of solar generation profile and traffic arrival rate. Furthermore, a thorough investigation is conducted with the help of Monte-Carlo simulations to assess the wireless network performance in terms of throughput, spectral efficiency (SE), and energy efficiency as well under a wide range of design scenarios. The numerical outcomes demonstrate that the proposed grid-tied solar PV/battery system can achieve a significant reduction of grid power consumption yielding up to 54.8% and ensure prominent energy sustainability with the effective modeling of renewable energy harvesting.

Improving energy efficiency, reducing carbon footprint and self-sustainability are key concerns in the design and development of future green communication networks. Therefore, in this paper, a novel energy efficient cellular access network architecture based on the principle of ecological proto-cooperation is proposed. Furthermore, for the first time, the wake-up technology is introduced to cellular access networks for implementing the proposed cooperative architecture. According to our proposal, base transceiver stations (BTSs) cooperatively and dynamically make intelligent decisions for switching between different power modes depending on network traffic conditions. Next, an extensive simulation process under different traffic patterns is carried out for identifying network parameters corresponding to optimal energy savings. The analysis of results reveals that the proposed architecture is capable of substantially reducing the energy consumption. In addition, as a secondary result, the proposed architecture offers an additional level of sustainability to the cellular access network infrastructure.