Energy Efficient Deployment Research Articles

Deeploy: Enabling Energy-Efficient Deployment of Small Language Models on Heterogeneous Microcontrollers

Deeploy: Enabling Energy-Efficient Deployment of Small Language Models on Heterogeneous Microcontrollers

Enabling Energy-Efficient Deployment of Large Language Models on Memristor Crossbar: A Synergy of Large and Small.

Large language models (LLMs) have garnered substantial attention due to their promising applications in diverse domains. Nevertheless, the increasing size of LLMs comes with a significant surge in the computational requirements for training and deployment. Memristor crossbars have emerged as a promising solution, which demonstrated a small footprint and remarkably high energy efficiency in computer vision (CV) models. Memristors possess higher density compared to conventional memory technologies, making them highly suitable for effectively managing the extreme model size associated with LLMs. However, deploying LLMs on memristor crossbars faces three major challenges. Firstly, the size of LLMs increases rapidly, already surpassing the capabilities of state-of-the-art memristor chips. Secondly, LLMs often incorporate multi-head attention blocks, which involve non-weight stationary multiplications that traditional memristor crossbars cannot support. Third, while memristor crossbars excel at performing linear operations, they are not capable of executing complex nonlinear operations in LLM such as softmax and layer normalization. To address these challenges, we present a novel architecture for the memristor crossbar that enables the deployment of state-of-the-art LLM on a single chip or package, eliminating the energy and time inefficiencies associated with off-chip communication. Our testing on BERT Large showed negligible accuracy loss. Compared to traditional memristor crossbars, our architecture achieves enhancements of up to 39× in area overhead and 18× in energy consumption. Compared to modern TPU/GPU systems, our architecture demonstrates at least a 68× reduction in the area-delay product and a significant 69% energy consumption reduction.

Power-Control-Based Energy-Efficient Deployment for Underwater Wireless Sensor Networks With Asymmetric Links

Power-Control-Based Energy-Efficient Deployment for Underwater Wireless Sensor Networks With Asymmetric Links

Energy-Efficient Deployment and Resource Allocation for O-RAN-Enabled UAV-Assisted Communication

Energy-Efficient Deployment and Resource Allocation for O-RAN-Enabled UAV-Assisted Communication

Energy Efficient Graph-Based Hybrid Learning for Speech Emotion Recognition on Humanoid Robot

This paper presents a novel deep graph-based learning technique for speech emotion recognition which has been specifically tailored for energy efficient deployment within humanoid robots. Our methodology represents a fusion of scalable graph representations, rooted in the foundational principles of graph signal processing theories. By delving into the utilization of cycle or line graphs as fundamental constituents shaping a robust Graph Convolution Network (GCN)-based architecture, we propose an approach which allows the capture of relationships between speech signals to decode intricate emotional patterns and responses. Our methodology is validated and benchmarked against established databases such as IEMOCAP and MSP-IMPROV. Our model outperforms standard GCNs and prevalent deep graph architectures, demonstrating performance levels that align with state-of-the-art methodologies. Notably, our model achieves this feat while significantly reducing the number of learnable parameters, thereby increasing computational efficiency and bolstering its suitability for resource-constrained environments. This proposed energy-efficient graph-based hybrid learning methodology is applied towards multimodal emotion recognition within humanoid robots. Its capacity to deliver competitive performance while streamlining computational complexity and energy efficiency represents a novel approach in evolving emotion recognition systems, catering to diverse real-world applications where precision in emotion recognition within humanoid robots stands as a pivotal requisite.

Energy efficient deployment of aerial base stations for mobile users in multi-hop UAV networks

Unmanned aerial vehicles (UAVs) are popularly considered as aerial base stations in a Low-Altitude Platform (LAP) to provide wireless connections to ground users in disaster and digital divide situation. Most of previous studies have investigated energy efficient UAV deployment only for the stationary ground users. Contrarily, we propose an on-line deployment algorithm for ground mobile users (GMUs) who are partially observable in the multi-UAV system. In the framework of Partially Observable Markov Decision Process (POMDP) with large state and action space, we use the Monte Carlo Tree Search (MCTS) algorithm enhanced by the Double Progressive Widening (DPW) and Deep Neural Network (DNN)-based guidance. For online learning of the DNN, simulated samples are used with Proximal Policy Optimization (PPO) that prevents excessive training for a particular belief. From experiment in urban environment, the proposed scheme shows better learning performance than the MCTS with rollout policy and faster convergence than training with environment samples. In addition, it optimizes dual objectives proportionally in a trade-off between energy saving and throughput including prediction error on GMU location.

Energy Efficient Deployment of VLC-Enabled UAV Using Particle Swarm Optimization

Energy Efficient Deployment of VLC-Enabled UAV Using Particle Swarm Optimization

IHBO_CA: an improved honey-badger optimization-based communication approach for energy-efficient deployment of secure flying ad-hoc network (FANET)

IHBO_CA: an improved honey-badger optimization-based communication approach for energy-efficient deployment of secure flying ad-hoc network (FANET)

Energy-Efficient Coverage and Capacity Enhancement With Intelligent UAV-BSs Deployment in 6G Edge Networks

With the development of 5G/6G networks, the number of wireless users is growing exponentially, and the application scenarios are increasingly diversified. Using unmanned aerial vehicles as base stations (UAV-BSs) to serve ground users has become a trend for wide area coverage and capacity enhancement for rapid access of service in 6G networks. However, as UAV-BSs have limited energy or battery storage, solutions to optimize energy efficiency while providing high-quality services are necessary. Therefore, this paper mainly concentrates on the energy-efficient deployment of coverage-aimed UAV-BSs (Co-UAV-BSs) and capacity-aimed UAV-BSs (Ca-UAV-BSs) for the coverage and capacity enhancement of ground communication under disaster areas or burst data traffic. First, Co-UAV-BSs are deployed with DQN algorithm to to get the UAV-BSs’ optimal flight paths, which mainly adopted to detect out of service users in such areas. Then the users are completely clustered based on the detection results. After that, Co-UAV-BSs and Ca-UAV-BSs are deployed hierarchically based on the user distribution and sought to optimize the energy efficiency with acceptable user services. Still, DQN algorithm and the A3C algorithm are used for obtaining all the UAV-BSs’ location deployment and users’ best connections. The simulation results show that the dynamic flying path requires less energy than the fixed path for user detecting. For the coverage and capacity enhancement, it reveals the solution we proposed could provide high-quality service for users with high energy efficiency comparing to traditional algorithms.

ESSENCE: Exploiting Structured Stochastic Gradient Pruning for Endurance-Aware ReRAM-Based In-Memory Training Systems

Processing-in-memory (PIM) enables energyefficient deployment of convolutional neural networks (CNNs) from edge to cloud. Resistive random-access memory (ReRAM) is one of the most commonly used technologies for PIM architectures. One of the primary limitations of ReRAM-based PIM in neural network training arises from the limited write endurance due to the frequent weight updates. To make ReRAM-based architectures viable for CNN training, the write endurance issue needs to be addressed. This work aims to reduce the number of weight reprogrammings without compromising the final model accuracy. We propose the ESSENCE framework with an endurance-aware structured stochastic gradient pruning method, which dynamically adjusts the probability of gradient update based on the current update counts. Experimental results with multiple CNNs and datasets demonstrate that the proposed method can extend ReRAM’s life time for training. For instance, with the ResNet20 network and CIFAR-10 dataset, ESSENCE can save the mean update counts of up to 10.29× compared to the SGD method and effectively reduce the maximum update counts compared with No Endurance method. Furthermore, aggressive tuning method based on ESSENCE can boost the mean update count savings by up to 14.41×.

Coverage and throughput analysis of an energy efficient UAV base station positioning scheme

Recently, the use of unmanned aerial vehicles (UAVs) for wireless communications has attracted much research attention. However, most applications of UAVs for wireless communication provisioning are not feasible as researchers fail to consider some vital aspects of their deployment, especially the energy requirements of both the UAV and communication system. The considerable energy consumption overhead involved in flying or hovering UAVs makes them less appealing for green wireless communications. Therefore, in this work, we examine the feasibility of an alternative energy-efficient deployment scheme where UAVs can be made to land-on designated locations, also known as landing stations (LSs). The idea of LS makes the UAV-based wireless communication more durable and advantageous, since the total energy consumption is reduced by minimizing the flying/hovering energy consumption, which, in turn, enables diverse set of applications including emergency and pop-up networking. We evaluate the impact of the separation distance between these LSs and the Optimal Hovering Position (OHP) on the network performance. Specifically, we develop mathematical frameworks to model the relationship between UAV power consumption, coverage probability, throughput, and separation distance. Numerical results reveal that a significant energy reduction can be achieved when the LS concept is exploited with a slight compromise in coverage probability and throughput. However, the choice of a suitable LS location depends on the users’ service requirements, transmit power, and frequency band utilized.

Digital Twin and Artificial Intelligence for Intelligent Planning and Energy-Efficient Deployment of 6G Networks in Smart Factories

Digital Twin and Artificial Intelligence for Intelligent Planning and Energy-Efficient Deployment of 6G Networks in Smart Factories

Q-learning-based UAV-mounted base station positioning in a disaster scenario for connectivity to the users located at unknown positions.

Due to its flexibility, cost-effectiveness, and quick deployment abilities, unmanned aerial vehicle-mounted base station (UmBS) deployment is a promising approach for restoring wireless services in areas devastated by natural disasters such as floods, thunderstorms, and tsunami strikes. However, the biggest challenges in the deployment process of UmBS are ground user equipment's (UE's) position information, UmBS transmit power optimization, and UE-UmBS association. In this article, we propose Localization of ground UEs and their Association with the UmBS (LUAU), an approach that ensures localization of ground UEs and energy-efficient deployment of UmBSs. Unlike existing studies that proposed their work based on the known UEs positional information, we first propose a three-dimensional range-based localization approach (3D-RBL) to estimate the position information of the ground UEs. Subsequently, an optimization problem is formulated to maximize the UE's mean data rate by optimizing the UmBS transmit power and deployment locations while taking the interference from the surrounding UmBSs into consideration. To achieve the goal of the optimization problem, we utilize the exploration and exploitation abilities of the Q-learning framework. Simulation results demonstrate that the proposed approach outperforms two benchmark schemes in terms of the UE's mean data rate and outage percentage.

Optimized UAV-based data collection from MWSNs

In this paper, we formulate an Energy Efficient (EE) deployment for Mobile Wireless Sensor Networks (MWSNs) that consists of multiple clusters of sensor nodes, one mobile sink in each of them, and an Unmanned Aerial Vehicle (UAV) for the whole MWSN. The UAV receives the collected sensed data from the mobile sinks wirelessly in order to deliver them to various IoT-based users’ devices. Experimental results show that the proposed model can achieve optimization in terms of energy consumption minimization and network lifetime enhancement.

Mobility-Driven and Energy-Efficient Deployment of Edge Data Centers in Urban Environments

Multi-access edge computing (MEC) brings storage and computational capabilities at the edge of the network into so-called edge data centers (EDCs) to better support low-latency applications. In this paper, we tackle the problem of EDC deployment in urban environments. Previous research on mobile phone data has exposed a strong correlation between the demand for mobile communications and the urban tissue. For example, joint analysis of mobile data and vehicle traffic can be extrapolated to estimate demand for transportation and human activities, thereby inferring the land use of the area where such activities take place. Our work takes into account the mobility of citizens and their spatial patterns to estimate the optimal placement of MEC EDCs in urban environments, in order to minimize outages while guaranteeing energy-efficiency. This is achieved by modeling both the energy consumption attributed to network components (e.g., base stations) and computing components (e.g., servers). We propose and compare three heuristics and show that mobility-aware deployments achieve superior performance. The results are obtained with a custom-designed simulator able to operate over large-scale realistic urban environments.

E2HRL: An Energy-efficient Hardware Accelerator for Hierarchical Deep Reinforcement Learning

Recently, Reinforcement Learning (RL) has shown great performance in solving sequential decision-making and control in dynamic environment problems. Despite its achievements, deploying Deep Neural Network (DNN)-based RL is expensive in terms of time and power due to the large number of episodes required to train agents with high dimensional image representations. Additionally, at the interference the large energy footprint of deep neural networks can be a major drawback. Embedded edge devices as the main platform for deploying RL applications are intrinsically resource-constrained and deploying deep neural network-based RL on them is a challenging task. As a result, reducing the number of actions taken by the RL agent to learn desired policy, along with the energy-efficient deployment of RL, is crucial. In this article, we propose Energy Efficient Hierarchical Reinforcement Learning (E2HRL), which is a scalable hardware architecture for RL applications. E2HRL utilizes a cross-layer design methodology for achieving better energy efficiency, smaller model size, higher accuracy, and system integration at the software and hardware layers. Our proposed model for RL agent is designed based on the learning hierarchical policies, which makes the network architecture more efficient for implementation on mobile devices. We evaluated our model in three different RL environments with different level of complexity. Simulation results with our analysis illustrate that hierarchical policy learning with several levels of control improves RL agents training efficiency and the agent learns the desired policy faster compared to a non-hierarchical model. This improvement is specifically more observable as the environment or the task becomes more complex with multiple objective subgoals. We tested our model with different hyperparameters to achieve the maximum reward by the RL agent while minimizing the model size, parameters, and required number of operations. E2HRL model enables efficient deployment of RL agent on resource-constraint-embedded devices with the proposed custom hardware architecture that is scalable and fully parameterized with respect to the number of input channels, filter size, and depth. The number of processing engines (PE) in the proposed hardware can vary between 1 to 8, which provides the flexibility of tradeoff of different factors such as latency, throughput, power, and energy efficiency. By performing a systematic hardware parameter analysis and design space exploration, we implemented the most energy-efficient hardware architectures of E2HRL on Xilinx Artix-7 FPGA and NVIDIA Jetson TX2. Comparing the implementation results shows Jetson TX2 boards achieve 0.1 ∼ 1.3 GOP/S/W energy efficiency while Artix-7 FPGA achieves 1.1 ∼ 11.4 GOP/S/W, which denotes 8.8× ∼ 11× better energy efficiency of E2HRL when model is implemented on FPGA. Additionally, compared to similar works our design shows better performance and energy efficiency.

Energy-Efficient Deployment in Static and Mobile Heterogeneous Multi-Hop Wireless Sensor Networks

We study a heterogeneous wireless sensor network (WSN) where <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> heterogeneous access points (APs) gather data from densely deployed sensors and transmit their sensed information to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$M$ </tex-math></inline-formula> heterogeneous fusion centers (FCs) via multi-hop wireless communication. The heterogeneous optimal deployment of APs and FCs is modeled as an optimization problem with total wireless communication power consumption of the network as its objective function. We consider both static WSNs, where APs and FCs retain their deployed position, and mobile WSNs where APs and FCs can move from their initial deployment to their optimal locations. Based on the derived necessary conditions for the optimal deployment in static WSNs, we propose an iterative algorithm to deploy APs and FCs. In addition, we study the necessary conditions of the optimal movement-efficient deployment in mobile WSNs with constrained movement energy and present iterative algorithms to find such deployments, accordingly. Simulation results show that our proposed deployment algorithms outperform the existing methods in the literature, and achieve a lower total wireless communication power in both static and mobile WSNs.

DL-RSIM: A Reliability and Deployment Strategy Simulation Framework for ReRAM-based CNN Accelerators

Memristor-based deep learning accelerators provide a promising solution to improve the energy efficiency of neuromorphic computing systems. However, the electrical properties and crossbar structure of memristors make these accelerators error-prone. In addition, due to the hardware constraints, the way to deploy neural network models on memristor crossbar arrays affects the computation parallelism and communication overheads. To enable reliable and energy-efficient memristor-based accelerators, a simulation platform is needed to precisely analyze the impact of non-ideal circuit/device properties on the inference accuracy and the influence of different deployment strategies on performance and energy consumption. In this paper, we propose a flexible simulation framework, DL-RSIM, to tackle this challenge. A rich set of reliability impact factors and deployment strategies are explored by DL-RSIM, and it can be incorporated with any deep learning neural networks implemented by TensorFlow. Using several representative convolutional neural networks as case studies, we show that DL-RSIM can guide chip designers to choose a reliability-friendly design option and energy-efficient deployment strategies and develop optimization techniques accordingly.

5G Hybrid System Design and Energy Efficient Resource Allocation Deployment

5G communication provide a promising platform for new, innovative and diverse enhanced mobile broadband (eMBB) and massive device connectivity applications, such as streaming media, machine vision and Internet of Things (IoT), real-time and dynamic data processing, intensive computation. However, 5G multimedia devices deployment relies on the coverage of base stations, which is inefficient and costly in wide-area coverage and physical penetration. In this paper, a 5G and wide-area Ad Hoc network fusion architecture is proposed to flexibly provide scalable 5G and extensible low-power devices interconnection liberated from geographical restriction, which consists of a low-power wide-area network and an edge processing gateway. Moreover, the intelligent edge gateway near a specific base station can support real-time ultra-high-definition video streams access and achieve traffic optimization by compressing, intelligent identification and preprocessing of the video streams to alleviate traffic congestion. The coverage capacity efficiency of wide-area Ad Hoc networks is restricted by the "funnel effect" in multihop cascading, and adaptive resource allocation strategies will present a promising approach to realize energy-efficient deployment. A non-convex optimization problem is formulated to maximize the energy-efficient deployment of Ad Hoc network. Then, a coordination and optimization strategy of internal resource allocation in deployed multihop nodes based on Lagrange relaxation algorithm was presented to solve the optimization problem. The actual system deployment and real measurement proved that the system function is running normally and stably. The experimental simulation test results show that the proposed 5G wide-area Ad Hoc network can effectively make up for the adaptive streaming needs of 5G coverage blind spots. Compared with static resource allocation, the proposed resource allocation and deployment scheme reduces energy consumption by 42.31%.

Energy efficient and effective node deployment for wireless sensor network

SummaryThe development of tiny sensor nodes (SNs) has incarnated numerous applications in the field of wireless sensor networks (WSN). These devices became much popular in multidisciplinary research area such as the internet of things (IoT). However, the use of these devices has been restricted due to some constraints like SN energy, data aggregation, quality of service (QoS), reliability, SN deployment, scalability, energy consumption, and many more. Among all these constraints, we focus on SN energy, SN deployment, and energy consumption of the network. Because if the consumption of SN energy is less, network lifetime automatically increases. So, we propose active–passive node topology on deployed SNs which enhance the network lifetime. With the help of the proposed mechanism, the lifetime and stability have increased by 60% and 3%, respectively, as compared with directed diffusion protocol in Experiment 1. In another experiment, the lifetime has increased by 67%, 64%, and 62% as compared with LEACH, NEAP, and DREEP, respectively, in homogeneous environment. The proposed scheme also performed significant improvement in heterogeneous environment. The simulation performance shows that the proposed protocol increases the network lifetime and stability of the network.