NeurstrucEnergy:A bi-directional GNN model for energy prediction of neural networks in IoT

A significant demand rises for energy-efficient deep neural networks to support power-limited embedding devices with successful deep learning applications in IoT and edge computing fields.An accurate energy prediction approach is critical to provide measurement and lead optimization direction.However,the current energy prediction approaches lack accuracy and generalization ability due to the lack of research on the neural network structure and the excessive reliance on customized training dataset.This paper presents a novel energy prediction model,NeurstrucEnergy.NeurstrucEnergy treats neural networks as directed graphs and applies a bi-directional graph neural network training on a randomly generated dataset to extract structural features for energy prediction.NeurstrucEnergy has advantages over linear approaches because the bi-directional graph neural network collects structural features from each layer's parents and children.Experimental results show that NeurstrucEnergy establishes state-of-the-art results with mean absolute percentage error of 2.60%.We also evaluate NeurstrucEnergy in a randomly generated dataset,achieving the mean absolute percentage error of 4.83%over 10 typical convolutional neural networks in recent years and 7 efficient convolutional neural networks created by neural architecture search.Our code is available at https://github.com/NEUSoftGreenAI/NeurstrucEnergy.git.

Security-Reliability Analysis and Optimization for Cognitive Two-Way Relay Network with Energy Harvesting

This paper investigates the security and reliability of information transmission within an underlay wiretap energy harvesting cognitive two-way relay network.In the network,energy-constrained secondary network(SN)nodes harvest energy from radio frequency signals of a multi-antenna power beacon.Two SN sources exchange their messages via a SN decode-and-forward relay in the presence of a multiantenna eavesdropper by using a four-phase time division broadcast protocol,and the hardware impairments of SN nodes and eavesdropper are modeled.To alleviate eavesdropping attacks,the artificial noise is applied by SN nodes.The physical layer security performance of SN is analyzed and evaluated by the exact closed-form expressions of outage probability(OP),intercept probability(IP),and OP+IP over quasistatic Rayleigh fading channel.Additionally,due to the complexity of OP+IP expression,a self-adaptive chaotic quantum particle swarm optimization-based resource allocation algorithm is proposed to jointly optimize energy harvesting ratio and power allocation factor,which can achieve security-reliability tradeoff for SN.Extensive simulations demonstrate the correctness of theoretical analysis and the effectiveness of the proposed optimization algorithm.

UAV-Aided Data and Energy Integrated Network: System Design and Prototype Development

Terminal devices deployed in outdoor environments are facing a thorny problem of power supply.Data and energy integrated network(DEIN)is a promising technology to solve the problem,which simultaneously transfers data and energy through radio frequency signals.State-of-the-art researches mostly focus on theoretical aspects.By contrast,we provide a complete design and implementation of a fully functioning DEIN system with the support of an unmanned aerial vehicle(UAV).The UAV can be dispatched to areas of interest to remotely recharge batteryless terminals,while collecting essential information from them.Then,the UAV uploads the information to remote base stations.Our system verifies the feasibility of the DEIN in practical applications.

Energy optimal routing for long chain-type wireless sensor networks in underground mines

Wireless sensor networks are useful complements to existing monitoring systems in underground mines. They play an important role of enhancing and improving coverage and flexibility of safety monitoring systems.Regions prone to danger and environments after disasters in underground mines require saving and balancing energy consumption of nodes to prolong the lifespan of networks.Based on the structure of a tunnel,we present a Long Chain-type Wireless Sensor Network（LC-WSN）to monitor the safety of underground mine tunnels.We define the optimal transmission distance and the range of the key region and present an Energy Optimal Routing（EOR）algorithm for LC-WSN to balance the energy consumption of nodes and maximize the lifespan of networks.EOR constructs routing paths based on an optimal transmission distance and uses an energy balancing strategy in the key region.Simulation results show that the EOR algorithm extends the lifespan of a network,balances the energy consumption of nodes in the key region and effectively limits the length of routing paths,compared with similar algorithms.

Research on the Trusted Energy-Saving Transmission of Data Center Network

According to the high operating costs and a large number of energy waste in the current data center network architectures, we propose a kind of trusted flow preemption scheduling combining the energy-saving routing mechanism based on typical data center network architecture. The mechanism can make the network flow in its exclusive network link bandwidth and transmission path, which can improve the link utilization and the use of the network energy efficiency. Meanwhile, we apply trusted computing to guarantee the high security, high performance and high fault-tolerant routing forwarding service, which helps improving the average completion time of network flow.

Grid-based energy-aware routing in wireless sensor networks

The model of energy cost in a wireless sensor network （WSN）environment is built, and the energy awareness and the wireless interference mainly due to different path loss models are studied. A special case of a clustering scheme, a twodimensional grid clustering mechanism, is adopted. Clusterheads are rotated evenly among all sensor nodes in an efficient and decentralized manner, based on the residual energy in the battery and the random backoff time. In addition to transmitting and receiving packets within the sensors＇ electrical and amplification circuits, extra energy is needed in the retransmission of packets due to packet collisions caused by severe interference. By analysis and mathematical derivation, which are based on planar geometry, it is shown that the total energy consumed in the network is directly related to the gridstructure in the proposed grid based clustering mechanism. The transmission range is determined by cluster size, and the path loss exponent is determined by nodal separation. The summation of overall interference is caused by all the sensors that are transmitting concurrently. By analysis and simulation, an optimal grid structure with the corresponding grid size is presented, which balances between maximizing energy conservation and minimizing overall interference in wireless sensor networks.

Create Your Own Data and Energy Integrated Communication Network:A Brief Tutorial and a Prototype System

In order to satisfy the ever-increasing energy appetite of the massive battery-powered and batteryless communication devices,radio frequency(RF)signals have been relied upon for transferring wireless power to them.The joint coordination of wireless power transfer(WPT)and wireless information transfer(WIT)yields simultaneous wireless information and power transfer(SWIPT)as well as data and energy integrated communication network(DEIN).However,as a promising technique,few efforts are invested in the hardware implementation of DEIN.In order to make DEIN a reality,this paper focuses on hardware implementation of a DEIN.It firstly provides a brief tutorial on SWIPT,while summarising the latest hardware design of WPT transceiver and the existing commercial solutions.Then,a prototype design in DEIN with full protocol stack is elaborated,followed by its performance evaluation.

Integration and development of energy and information network in the Pan-Arctic region

The Global Energy Interconnection is an important strategic approach used to achieve efficient worldwide energy allocation.The idea of developing integrated power,information,and transportation networks provides increased power interconnection functionality and meaning,helps condense forces,and accelerates the integration of global infrastructure.Correspondingly,it is envisaged that it will become the trend of industrial technological development in the future.In consideration of the current trend of integrated development,this study evaluates a possible plan of coordinated development of fiber-optic and power networks in the Pan-Arctic region.Firstly,the backbone network architecture of Global Energy Interconnection is introduced and the importance of the Arctic energy backbone network is confirmed.The energy consumption and developmental trend of global data centers are then analyzed.Subsequently,the global network traffic is predicted and analyzed by means of a polynomial regression model.Finally,in combination with the current construction of fiber-optic networks in the Pan-Arctic region,the advantages of the integration of the fiber-optic and power networks in this region are clarified in justification of the decision for the development of a Global Energy Interconnection scheme.

Dual Power Allocation Optimization Based on Stackelberg Game in Heterogeneous Network with Hybrid Energy Supplies

In heterogeneous network with hybrid energy supplies including green energy and on-grid energy, it is imperative to increase the utilization of green energy as well as to improve the utilities of users and networks. As the difference of hybrid energy source in stability and economy, thus, this paper focuses on the network with hybrid energy source, and design the utility of each user in the hybrid energy source system from the perspective of stability, economy and environment pollution. A dual power allocation algorithm based on Stackelberg game to maximize the utilities of users and networks is proposed. In addition, an iteration method is proposed which enables all players to reach the Stackelberg equilibrium(SE). Simulation results validate that players can reach the SE and the utilities of users and networks can be maximization, and the green energy can be efficiently used.

Towards Practical Implementation of Data and Energy Integrated Networks

With the rapid development of the mobile internet and the massive deployment of the Internet of Things, mobile devices, including both the consumer electronics and the sensors, become hungrier for the energy than ever before. Conventional cable based charging largely restrict the movement of the mobile devices. Wireless charging hence emerges as an essential technique for enabling our ultimate goal of charging anytime and anywhere. By efficiently exploiting the legacy of the existing communication infrastructure, we propose a nov- el data and energy integrated network （DEIN） in order to re- alise the radio frequency （RF） based wireless charging with- out degrading the information transmission. In this treatise, we focus on the implementation of the DEIN in both the theoretical and practical aspects, concerning the transceiver architecture design and the rectifier circuit design. Furthermore, we also present a Wi-Fi based testbed for demonstrating the availability of the RF based wireless charging.

A Routing Optimization Algorithm with Quality of Multi- Service in Wireless Sensor Network

According to the problem of energy consumption in wireless sensor network （WSN）,this paper puts forward a routing optimization algorithm with quality of multi-service, using the function of routing optimization with quality of multi-service and membership function of satisfaction, which integrates the energy consumption of communication and residual and the information of time delay into the membership function of satisfaction to solve the equilibrium factor, so that it can become the optimal routing that balances the network lifetime, transmission delay of data, and node energy consumption of nodes. Simulation experiment shows that adopting the algorithm can make lifecycle of nodes longer and network transmit more data packets at the same time. Experimental results verify the algorithm can effectively balance the network energy, reduce the energy consumption and prolong the network lifetime.

An energy efficiency clustering routing protocol for WSNs in confined area

Wireless sensor networks (WSNs) are important application for safety monitoring in underground coal mines, which are difficult to monitor due to natural conditions. Based on the characteristic of limited energy for WSNs in confined underground area such as coal face and laneway, we presents an energy- efficient clustering routing protocol based on weight (ECRPW) to prolong the lifetime of networks. ECRPW takes into consideration the nodes' residual energy during the election process of cluster heads. The constraint of distance threshold is used to optimize cluster scheme. Furthermore, the protocol also sets up a routing tree based on cluster heads' weight. The results show that ECRPW had better perfor- mance in energy consumption, death ratio of node and network lifetime.

Energy-Performance Tradeoffs in laaS Cloud with Virtual Machine Scheduling

In the cloud data centers,how to map virtual machines(VMs) on physical machines(PMs) to reduce the energy consumption is becoming one of the major issues,and the existing VM scheduling schemes are mostly to reduce energy consumption by optimizing the utilization of physical servers or network elements.However,the aggressive consolidation of these resources may lead to network performance degradation.In view of this,this paper proposes a two-stage VM scheduling scheme:(1) We propose a static VM placement scheme to minimize the number of activating PMs and network elements to reduce the energy consumption;(2) In the premise of minimizing the migration costs,we propose a dynamic VM migration scheme to minimize the maximum link utilization to improve the network performance.This scheme makes a tradeoff between energy efficiency and network performance.We design a new twostage heuristic algorithm for a solution,and the simulations show that our solution achieves good results.

The New Architecture with Time-Spatial Consistency for 5G Networks

While operators have started deploying fourth generation(4G) wireless communication systems,which could provide up to1 Gbps downlink peak data rate,the improved system capacity is still insufficient to meet the drastically increasing demand of mobile users over the next decade.The main causes of the above-mentioned phenomenon include the following two aspects:1) the growth rate of the network capacity is far below that of user's demand,and 2) the relatively deterministic wireless access network(WAN) architecture in the existing systems cannot accommodate the prominent increase of mobile traffic with space-time domain dynamics.In order to address the above-mentioned challenges,we investigate the time-spatial consistency architecture for the future WAN,whilst emphasizing the critical roles of some spectral-efficient techniques such as Massive multiple-input multiple-output(MIMO),full-duplex(FD)operation and heterogeneous networks(HetNets).Furthermore,the energy efficiency(EE)of the HetNets under the proposed architecture is also evaluated,showing that the proposed user-selected uplink power control algorithm outperforms the traditional stochastic-scheduling strategy in terms of both capacity and EE in a two-tier HetNet.The other critical issues,including the tidal effect,the temporal failure owing to the instantaneously increased traffic,and the network wide load-balancing problem,etc.,are also anticipated to be addressed in the proposed architecture.(Abstract)

Evolving Network Model with Local-Area Preference for Mobile Ad Hoc Network

To accurately describe the evolving features of Mobile Ad Hoc Networks (MANETs) and to improve the performance of such networks, an evolving topology model with local-area preference is proposed. The aim of the model, which is analyzed by the mean field theory, is to optimize network structures based on users' behaviors in MANETs. The analysis results indicate that the network generated by this evolving model is a kind of scale-free network. This evolving model can improve the fault-tolerance performance of networks by balancing the connectivity and two factors, i.e., the remaining energy and the distance to nodes. The simulation results show that the evolving topology model has superior performance in reducing the traffic load and the energy consumption, prolonging network lifetime and improving the scalability of networks. It is an available approach for establishing and analyzing actual MANETs.

Deep convolutional Ritz method: parametric PDE surrogates without labeled data

The parametric surrogate models for partial differential equations(PDEs)are a necessary component for many applications in computational sciences,and the convolutional neural networks(CNNs)have proven to be an excellent tool to generate these surrogates when parametric fields are present.CNNs are commonly trained on labeled data based on one-to-one sets of parameter-input and PDE-output fields.Recently,residual-based deep convolutional physics-informed neural network(DCPINN)solvers for parametric PDEs have been proposed to build surrogates without the need for labeled data.These allow for the generation of surrogates without an expensive offline-phase.In this work,we present an alternative formulation termed deep convolutional Ritz method(DCRM)as a parametric PDE solver.The approach is based on the minimization of energy functionals,which lowers the order of the differential operators compared to residualbased methods.Based on studies involving the Poisson equation with a spatially parameterized source term and boundary conditions,we find that CNNs trained on labeled data outperform DCPINNs in convergence speed and generalization abilities.The surrogates generated from the DCRM,however,converge significantly faster than their DCPINN counterparts,and prove to generalize faster and better than the surrogates obtained from both CNNs trained on labeled data and DCPINNs.This hints that the DCRM could make PDE solution surrogates trained without labeled data possibly.

Energy internet or comprehensive energy network?

What needs to be developed from the concept of"Smart Grid"is that:when renewable energy sources are absolutely prevailing in power generation,distributed power generation and distributed energy storage systems are widespread across the grid,and electric vehicle charging loads are prevailing in power load demands,how can the power grid support electric power as a core secondary energy source,undertake the role of a bridge between primary energy and end-use energy,and achieve the coordination and the optimization in macro energy perspective;how to guarantee the security of both macro energy and environment as well as the reliability of electricity.If a new term is needed,it should be Comprehensive Energy Network,not Energy Internet.

Security Analysis of a Park-level Agricultural Energy Network Considering Agrometeorology and Energy Meteorology

China’s industrial manufacturing industry is well developed,but its agriculture is primitive.The only way to solve this problem is to improve through modern agriculture.The cross integration of new energy development and modern agriculture is becoming more and more critical.However,the research on the interaction between the meteorological disaster of facility agriculture and the power supply security of the integrated energy supply system has not formed a systematic theoretical system,which challenges the collaborative security of the facility agriculture and energy system.In this paper,energy meteorology and agrometeorology are considered and modeled,and the static security of a park-level agricultural energy network is simulated and analyzed under different weather conditions.

Energy Sharing and Frequency Regulation in Energy Network via Mixed H_(2)/H_(∞) Control with Markovian Jump

In this paper,the problem of mixed optimization for energy sharing and frequency regulation in a typical energy network scenario where energy routers(ERs)interconnected AC microgrids(MGs)is investigated.Continuous-time Markov chains are introduced to describe the switching paths in the power dynamics of MGs.Such that the modelling of considered energy network system could be closer to the real-world engineering practice.Advanced parameter estimation techniques are integrated into the proposed method to achieve better modelling accuracy and controlling performance.Based on the parameters of MG power dynamics,the mixed H_(2)/H_(∞) controllers are obtained via stochastic control theory.The feasibility and efficacy of the proposed approach are evaluated in numerical examples.

An Overview of the Smart Grid in Great Britain

This paper presents an overview of the current status of the development of the smart grid in Great Britain(GB).The definition,policy and technical drivers,incentive mechanisms,technological focus,and the industry's progress in developing the smart grid are described.In particular,the Low Carbon Networks Fund and Electricity Network Innovation Competition projects,together with the rollout of smart metering,are detailed.A more observable,controllable,automated,and integrated electricity network will be supported by these investments in conjunction with smart meter installation.It is found that the focus has mainly been on distribution networks as well as on real-time flows of information and interaction between suppliers and consumers facilitated by improved information and communications technology,active power flow management,demand management,and energy storage.The learning from the GB smart grid initiatives will provide valuable guidelines for future smart grid development in GB and other countries.