Fifth-generation (5G) wireless technology promises to be the critical enabler of use cases far beyond smartphones and other connected devices. This next-generation 5G wireless standard represents the changing face of connectivity by enabling elevated levels of automation through continuous optimization of several Key Performance Indicators (KPIs) such as latency, reliability, connection density, and energy efficiency. Mobile Network Operators (MNOs) must promote and implement innovative technologies and solutions to reduce network energy consumption while delivering high-speed and low-latency services to deploy energy-efficient 5G networks with a reduced carbon footprint. This research evaluates an energy-saving method using data-driven learning through load estimation for Beyond 5G (B5G) networks. The proposed ‘ECO6G’ model utilizes a supervised Machine Learning (ML) approach for forecasting traffic load and uses the estimated load to evaluate the energy efficiency and OPEX savings. The simulation results demonstrate a comparative analysis between the traditional time-series forecasting methods and the proposed ML model that utilizes learned parameters. Our ECO6G dataset is captured from measurements on a real-world operational 5G base station (BS). We showcase simulations using our ECO6G model for a given dataset and demonstrate that the proposed ECO6G model is accurate within $4.3 million over 100,000 BSs over 5 years compared to three other models that would increase OPEX cost from $370 million to $1.87 billion during varying network load scenarios against other data-driven and statistical learning models.
The data collected from the sensor network is meaningful to most of the wireless sensor network applications if and only if it is coupled with the exact positioning of the node. Mere localisation solves the problem of locating an unknown node, however applications like battlefield surveillance or enemy tracking, rescue-operations as well as monitoring of military facilities demand security and reliability of the location information. Therefore secure localisation of non-reference nodes facilitates the localisation system to be robust and secure in adversarial circumstances. The work targets secure localisation of the node position using least significant bit (LSB) insertion technique of steganography. In order for a node to be aware of its position, it sends a cover-image along with the node-id to the Cluster head (CH). The CH which already knows the node position performs LSB embedding on the cover image to generate a stego-image. The stego-image and the cover-image are then compared to get secure position information. The comparison will yield accurate position information only if the cover image is the same. For an adversarial circumstance (different cover image), the security mechanism is robust, and the information will be conveyed to the intended recipient only.
This paper studies a deep reinforcement learning technique for distributed resource allocation among cognitive radios operating under an underlay dynamic spectrum access paradigm which does not require coordination between agents during learning. The key challenge that is addressed in this work is that of a non-stationary reinforcement learning environment that arises from the uncoordinated and distributed radios operation over a shared wireless environment. This challenge is illustrated by presenting a simulation result where the use of a standard single-agent deep reinforcement learning approach does not achieve convergence because of being applied in the uncoordinated interacting multi-radio scenario. To address this challenge, this work presents the uncoordinated and distributed multi-agent DQL (UDMA-DQL) technique that combines a deep neural network with learning in exploration phases, and with the use of a Best Reply Process with Inertia for the gradual learning of the best policy. Key in the study of UDMA-DQL herein, it is shown by considering aspects specific to deep reinforcement learning, that under an arbitrarily long time the UDMA-DQL technique converges with probability one to equilibrium policies in the non-stationary environment resulting from the distributed and uncoordinated operation of cognitive radios. This analytical study is confirmed through simulation results showing that, in cases when an optimal policy can be identified, UDMA-DQL is able to find such policy in 99% of cases for a sufficiently long learning time. Importantly, further simulations show that the presented UDMA-DQL approach achieves a much faster learning performance compared to an equivalent table-based Q-learning implementation.
Designing a resource allocation technique for a cognitive radio network (CRN) adopting underlay dynamic spectrum access (DSA), requires a cross-layer approach for an acceptable quality of experience (QoE) in view of having differentiated quality-of-service (QoS) classes of traffic. This paper focuses on heterogeneous traffic management in underlay CRNs, where the transmission parameters are optimized to not only satisfy the interference constraint of the primary link but meet the delay requirement of the video traffic. The paper develops a deep reinforcement learning-based resource allocation technique which significantly lowers the queuing delay at the data link layer and maximizes the network average end-to-end mean opinion score (MOS). Simulation results show the effectiveness of the proposed cross-layer technique over a single-layer approach. The cross-layer technique effectively changes the transmission parameters in accordance with the delay requirement of the video traffic and the underlay DSA interference constraint without compromising the MOS.