Virtual Nodes Research Articles

Distributed Online Voltage Control With Fast PV Power Fluctuations and Imperfect Communication

Coordinated Volt-Var control methods have demonstrated their techno-economic feasibility in voltage regulation of photovoltaic (PV) rich distribution systems. However, fast fluctuating PV power and imperfect communication networks may significantly challenge the effectiveness of these methods. In this paper, a revised dynamic consensus algorithm is proposed to coordinate distributed inverters for Volt-Var control in real time. With this proposed method, Var saturation and overvoltage issues which tend to occur at downstream buses of PV rich distribution systems are significantly mitigated. To quantitatively analyse the algorithm performance in imperfect communication environments, the information delivery between agents is modelled by stochastic state transition processes among finite numbers of virtual nodes so as to quantitatively depict the random time delay and packet dropout in a discrete way. On this basis, the state transition process of the whole system is further depicted by a series of row-stochastic matrices, and the ergodic theory is used to analytically derive the algorithm tracking error in an imperfect communication environment. Our proposed method can also be extended to more complex applications, where both Var compensation and PV curtailment (or EV dispatch) are available for system voltage control. Simulation results verify the superiority of our method over traditional ones.

ABLA: Application-Based Load-Balanced Approach for Adaptive Mapping of Datacenter Networks

Cloud-based services are growing more rapidly than ever, and so does the management challenge on their providers’ side. Cloud-based datacenter networks are built with nodes of huge processing power, connected by high bandwidth capacities to carry their interior traffic requirements. However, such cloud networks still have limits that are imposed not necessarily by their physical components, but by the schemes of resource management being deployed. Traditionally, for an institute to provide services, it needs to have its own datacenter facility that interconnects its servers through a topology that matches its desired administrative policies and scaling objectives. With the theme of cloud-based IaaS, such datacenter topologies can be created virtually over the cloud. Nowadays, a significant part of those institutes who provide us with our daily services have their infrastructures hosted over cloud ones. Therefore, resources of such cloud networks need to be efficiently utilized, in order to keep their performance and hosting prices competitive. A typical datacenter network mainly consists of server nodes and network links. Besides the resources of the server nodes, the network bandwidth resources are considered a crucial key determinant for the whole datacenter performance. Indeed, a server without sufficient bandwidth capacities is almost useless. Proposals in the literature present schemes for resource utilization on either side of the problem at a time: the nodes or the links. Working in isolation can never deliver efficient mapping solutions. ABLA is an Application-Based, and Load balancing Approach for adaptive mapping proposal. ABLA’s methodology tackles both sides of the datacenter, the nodes and links. It starts by (1) breaking down the node’s resource requirement for the requested applications to be hosted over the virtual server machines besides (2) reading the topological connectivity and bandwidth requirements for each virtual node to all other nodes in the virtual datacenter topology. Compared to other models in the literature, the simulation results show that our proposed ABLA model provides for complete mapping services via load-balanced hosting networks. This allows for competitive hosting prices, with higher performance and service satisfaction rates.

Leveraging Minimum Nodes for Optimum Key Player Identification in Complex Networks: A Deep Reinforcement Learning Strategy with Structured Reward Shaping

The problem of finding key players in a graph, also known as network dismantling, or network disintegration, aims to find an optimal removal sequence of nodes (edges, substructures) through a certain algorithm, ultimately causing functional indicators such as the largest connected component (GCC) or network pair connectivity in the graph to rapidly decline. As a typical NP-hard problem on graphs, recent methods based on reinforcement learning and graph representation learning have effectively solved such problems. However, existing reinforcement-learning-based key-player-identification algorithms often need to remove too many nodes in order to achieve the optimal effect when removing the remaining network until no connected edges remain. The use of a minimum number of nodes while maintaining or surpassing the performance of existing methods is a worthwhile research problem. To this end, a novel algorithm called MiniKey was proposed to tackle such challenges, which employs a specific deep Q-network architecture for reinforcement learning, a novel reward-shaping mechanism based on network functional indicators, and the graph-embedding technique GraphSage to transform network nodes into latent representations. Additionally, a technique dubbed ‘virtual node technology’ is integrated to grasp the overarching feature representation of the whole network. This innovative algorithm can be effectively trained on small-scale simulated graphs while also being scalable to large-scale real-world networks. Importantly, experiments from both six simulated datasets and six real-world datasets demonstrates that MiniKey can achieve optimal performance, striking a perfect balance between the effectiveness of key node identification and the minimization of the number of nodes that is utilized, which holds potential for real-world applications such as curbing misinformation spread in social networks, optimizing traffic in transportation systems, and identifying key targets in biological networks for targeted interventions.

A Coupled Overlapping Finite Element Method for Analyzing Underwater Acoustic Scattering Problems

It is found that the classic finite element method (FEM) requires much time for adequate meshes to acquire satisfactory numerical solutions, and is restricted to acoustic problems with low and middle frequencies. In this work, a coupled overlapping finite element method (OFEM) is employed by combining the overlapping finite element and the modified Dirichlet-to-Neumann (mDtN) boundary condition to solve underwater acoustic scattering problems. The main difference between the OFEM and the FEM lies in the construction of the local field approximation. In the OFEM, virtual nodes are utilized to form the partition of unity functions while no degree of freedom is assigned to these virtual nodes, which suppresses the linear dependence issue in other generalized finite element methods. Moreover, the user-defined enrichment functions can be flexibly utilized in the local field, and thus the numerical dispersions can be significantly mitigated. To truncate the infinite problem domain and satisfy the Sommerfeld radiation condition, an artificial boundary is constructed by incorporating the mDtN technique. Several numerical examples are studied and it is shown that the proposed method can greatly diminish the numerical error and is insensitive to distorted meshes, indicating that the proposed method is promising in predicting underwater acoustic scattering.

PPChain: A Blockchain for Pandemic Prevention and Control Assisted by Federated Learning.

Taking COVID-19 as an example, we know that a pandemic can have a huge impact on normal human life and the economy. Meanwhile, the population flow between countries and regions is the main factor affecting the changes in a pandemic, which is determined by the airline network. Therefore, realizing the overall control of airports is an effective way to control a pandemic. However, this is restricted by the differences in prevention and control policies in different areas and privacy issues, such as how a patient's personal data from a medical center cannot be effectively combined with their passenger personal data. This prevents more precise airport control decisions from being made. To address this, this paper designed a novel data-sharing framework (i.e., PPChain) based on blockchain and federated learning. The experiment uses a CPU i7-12800HX and uses Docker to simulate multiple virtual nodes. The model is deployed to run on an NVIDIA GeForce GTX 3090Ti GPU. The experiment shows that the relationship between a pandemic and aircraft transport can be effectively explored by PPChain without sharing raw data. This approach does not require centralized trust and improves the security of the sharing process. The scheme can help formulate more scientific and rational prevention and control policies for the control of airports. Additionally, it can use aerial data to predict pandemics more accurately.

Temperature Sensor with Buffer-Chain based Time-to-Digital Converter for Ultra-Low Voltage Operation

This paper proposes a Time-to-Digital Converter (TDC) based temperature sensor that aims to operate with an ultra-low voltage electromotive force for IoT applications with energy harvesting. Sub-threshold circuit design was exploited for the operation at ultra-low supply voltage. The proposed circuit uses the characteristics of leakage current for temperature measurement. The virtual ground node in the proposed sensor is charged up by leakage current and the charging time changes with the temperature. To measure the temperature-dependent charging time, we used a buffer-chain based TDC to achieve ultra-low voltage operation. Simulation results demonstrated that the minimum supply voltage for the proposed circuit is 0.15V. The power consumption is 407nW and sensing time is 180ns at 25℃. The measurable temperature range is from -40℃ to 85℃. The proposed circuit was designed with Renesas SOTB 65nm process. Simulation evaluation was conducted using HSPICE.

An efficient medical image encryption algorithm for telemedicine applications

Applications for healthcare execute computations that support various patient diagnostics and save private user data on cloud servers. User data is being held at ransom as a result of increasing cyberattacks on medical systems. Additionally, unreliable external parties who sell private data for profit can access mathematical calculations on data stored in the cloud. In this research, we suggest an efficient Homomorphic medical image encryption algorithm protecting medical plaintext data against unauthorised access via homomorphic encryption. To increase the security level Paillier's encryption scheme (PES) is utilized to select the optimal key. Homomorphic encryption is a method of authentication which helps one to perform observes of the encrypted information through decrypting it. Secret sharing splits up computations among a number of edge virtual nodes and hides all arithmetic operations, preventing unreliable cloud servers from figuring out what was done with the encrypted patient data. Cloud computing resources help virtual edge nodes perform computationally difficult mathematical operations and lower latency in device-edge node data transmission. During the experimental study, different factors including execution time, encryption time, and decryption time are used to evaluate the performance of the suggested approach. The proposed technique's execution time is 2% faster than the currently used HE method and 4% faster than the ECC algorithm.

Piezoelectric MEMS-based physical reservoir computing system without time-delayed feedback

Abstract In this study, a physical reservoir computing system, a hardware-implemented neural network, was demonstrated using a piezoelectric MEMS resonator. The transient response of the resonator was used to incorporate short-term memory characteristics into the system, eliminating commonly used time-delayed feedback. In addition, the short-term memory characteristics were improved by introducing a delayed signal using a capacitance-resistor series circuit. A Pb(Zr,Ti)O3-based piezoelectric MEMS resonator with a resonance frequency of 193.2 Hz was employed as an actual node, and computational performance was evaluated using a virtual node method. Benchmark tests using random binary data indicated that the system exhibited short-term memory characteristics for two previous data and nonlinearity. To obtain this level of performance, the data bit period must be longer than the time constant of the transient response of the resonator. These outcomes suggest the feasibility of MEMS sensors with machine-learning capability.

Explore deep reinforcement learning for efficient task processing based on federated optimization in big data

In recent years, along with the extensive application of consumer electronics, the task execution with cloud computing for big data has become one of the research focuses. Nevertheless, the traditional theories and algorithms are still employed by existing research work to explore the feasible solutions, which takes a beating from low generalization performance, system load imbalance, more response delay, etc. To solve the matter, a task execution method called DROP (Deep Reinforcement network aided Optimization method aiming at task Processing) has been put forward, which is capable of completing task request allocation through virtual network embedding. The prominence of this method is explained by its effect in reducing load balancing degree, minimizing bandwidth resource overhead, and preserving electric energy as well as meeting customer demands. It makes use of Deep Deterministic Policy Gradient (DDPG) instead of depending on tons of iterations for better path selection schemes in previous methods, through continuous environment interaction and trial-and-error evaluation to get better strategy selection for virtual link embedding. To realize the virtual node embedding in the federated optimization based system architecture, the intentional deep feature learning network is applied. Compared with the cutting edge approaches, the performance benefits of DROP can be verified by the experimental results in terms of bringing down the extra cost on resources and energy of the substrate network during the task execution for big data.

Minimum-cost embedding of virtual networks: An iterative decomposition approach

The ossification of the current Internet can be mitigated by network virtualization. The key idea of network virtualization is to abstract a logical service as a virtual network, which is mapped to the physical infrastructure as networked virtual machines. This process, known as virtual network embedding (VNE), entails two components: Node Assignment (NA), where virtual nodes are mapped to physical nodes as virtual machines (i.e., via node virtualization); and Link Mapping (LM), where physical paths are allocated to connect the embedded virtual nodes (i.e., via link virtualization). The existing VNE solutions based on Integer Linear Programming models and heuristic algorithms, unfortunately, fall in short in addressing either one of the two following perspectives: ILP-based models address NA and LM jointly, leading to optimal results but they suffer from extensive computation time; heuristic algorithms simplify the problem computationally but it lacks guaranteed solution quality. A large body of VNE solutions, particularly, adopt strategies like divide-and-conquer: NA and LM are resolved as two independent sub-problems in sequence. This paper is motivated by an important mathematical quest to better leverage this decomposition strategy: how can one identify the inherent link between the NA and LM sub-problems to obtain a decomposition approach without trading off solution quality? The major contributions of this work lie on three facets that fulfill this quest. First, based on a path-based VNE model, our primal–dual analysis reveals the process towards formulations of the NA, and LM sub-problems that preserve the link (as in ILP solutions). Second, we develop an iterative decomposition approach that employs merits from both worlds: the complexity of VNE (structurally and computationally) is simplified by decomposition while optimality or guaranteed closeness to the optimality is attained. Third, our evaluations confirm that the proposed schemes can achieve trade-offs in time and optimality, and outperform benchmark schemes by a large margin.

Meta-Heuristic Device-Free Localization Algorithm under Multiple Path Effect.

In the scenario of device-free localization under multiple effects, the accuracy of localization based on compressed sensing theory is severely affected. Most existing localization techniques directly ignore multiple path effects. However, it is not practical to ignore the multiple path effect due to its high signal strength, which can provide localization information. In this paper, we formulate the sensing matrix optimization problem in compressed sensing for device-free localization scenarios based on multiple reflections. To solve this problem, we model it as a constrained combinatorial optimization problem and propose a hybrid meta-heuristic algorithm. First, smart reflection surfaces and virtual node models are used to construct the desired communication links. Second, we iteratively improve the properties of the measurement matrix by using K-means clustering to obtain reasonable thresholds, and use a meta-heuristic algorithm to optimize the sensing matrix. Finally, the simulation results show that the proposed method efficiently optimizes the sensing matrix and achieves fast and high-precision localization while conserving communication resources.

5G in healthcare: Matching game-empowered intelligent medical network slicing

Improving the healthcare system is imperative for increasing efficiency and reducing costs. The rapid adoption of Internet of Medical Things (IoMT) has facilitated a broad range of healthcare applications and services, from real-time and critical care monitoring to telemedicine. These services typically have highly distinct quality of service (QoS) requirement for communication networks and thus cannot be served with a uniform network. In such a context, network slicing technologies in 5G can be employed to create virtually independent and customized communication networks for these use cases to meet their QoS requirement. In this wok, we model network slicing for healthcare services as a virtual network embedding (VNE) problem and propose a two-sided matching theory-based virtual network embedding (MT-VNE) solution. In MT-VNE, four novel preference indexes are devised to construct differential preference lists. The deferred acceptance and modified shortest path-based algorithms are utilized to perform the virtual node and link mapping, respectively. Extensive simulations demonstrate that MT-VNE outperforms other baselines in terms of accepting more healthcare services and effectively utilizing physical network resources. Moreover, MT-VNE also significantly reduces service embedding time.

Cloud computing-oriented big data analysis-based intelligent university talent development mechanism

The arrival of big data has changed and affected people's lives. To achieve better development, universities must attach importance to applying big data for talent development. An improved k-nearest neighbors density peak clustering algorithm (iKDPC) combined with principal components is suggested to enhance the impact of hierarchical classification in talent development in universities. For the hybrid wired/wireless data center network, we propose a virtual node fusion-based virtual network embedding with the wireless links assistance method (VnfVNE-WLA). The experimental results show that iKDPC can effectively classify talents in universities and provide scientific and quantitative references for scientifically and rationally exploring the classification issues in developing talents in universities. Moreover, the simulation results demonstrate that the VnfVNE-WLA method can successfully increase the utilization rate of talent resources from the virtual network to the physical network to better support talent development in universities using cloud computing.

Photonic convolutional reservoir computing based on VCSEL with multiple optical injections

In this paper, a photonic convolutional time delay reservoir computing (C-TD-RC) system based on vertical cavity surface emitting laser (VCSEL) with multiple optical injections has been proposed. Here, the convolutional neural networks (CNNs) and the time delay reservoir computing (TD-RC) are combined in the system. Using TD-RC instead of the fully connected layer in the traditional CNNs can solve the problem of gradient vanishing and gradient explosion in CNNs. Two classification tasks including handwritten digits recognition and spoken digits classification are solved by the C-TD-RC system. In addition, in order to achieve better classification performance of RC, a new post-processing method combining ridge regression and winner take all strategy has been adopted. Numerical results demonstrate that the minimum Word Error Rate (WER) can reach 0.0135 for handwritten digits recognition and 0.0213 for spoken digits classification tasks by the C-TD-RC system. Furthermore, the effects of the virtual nodes, the injection paths and the number of convolution kernels applied in the first and second convolution layers on the C-TD-RC system are considered. The proposed C-TD-RC scheme is of great significance to the performance enhancement of RC in the future.

Generic and Dynamic Graph Representation Learning for Crowd Flow Modeling

Many deep spatio-temporal learning methods have been proposed for crowd flow modeling in recent years. However, most of them focus on designing a spatial and temporal convolution mechanism to aggregate information from nearby nodes and historical observations for a pre-defined prediction task. Different from the existing research, this paper aims to provide a generic and dynamic representation learning method for crowd flow modeling. The main idea of our method is to maintain a continuous-time representation for each node, and update the representations of all nodes continuously according to the streaming observed data. Along this line, a particular encoder-decoder architecture is proposed, where the encoder converts the newly happened transactions into a timestamped message, and then the representations of related nodes are updated according to the generated message. The role of the decoder is to guide the representation learning process by reconstructing the observed transactions based on the most recent node representations. Moreover, a number of virtual nodes are added to discover macro-level spatial patterns and also share the representations among spatially-interacted stations. Experiments have been conducted on two real-world datasets for four popular prediction tasks in crowd flow modeling. The result demonstrates that our method could achieve better prediction performance for all the tasks than baseline methods.

Computer Security Active Defense Technology Based on Bayesian Model

Abstract The existing active defense technology based on game theory is mainly based on static games. This method can not adapt to the dynamic change of the attacker’s attacking intent and tactics. Based on the non-cooperative and non-zero-sum dynamic game theory, a complete Bayesian system of emotional game bodies is established. Use the “virtual node” to transform the attack and defense chart into a tree structure of the attack and defense game. An attack and defense strategy suitable for integrity and incompleteness is given. The experimental simulation results show that the seven comprehensibilities and usability of Nash equilibrium solutions optimized by Bayesian subgames are well obtained

Application of artificial intelligence and communication technology to water and energy balance models

Abstract The precise correction of water and energy balance is a significant difficulty in studying turbulence energy balance and water flow for agricultural purposes. The need for efficient water and energy management is growing as the world struggles to keep up with rising water and energy demands. This research examines artificial intelligence (AI)'s impact on the water flow and energy balance confluence subnetwork of sensing elements from all the original network's nodes. The study proposed an AI-based optimized sensor energy balance model (AI-SEBM) that uses pressure data to maintain energy balance in turbines and save water with the optimized energy source for agriculture usage. This research explores the potential for installing Kalpan hydraulic turbines, which are most effective during half-load operation, and to forecast all loads with little computing effort to balance energy in turbulence. To anticipate daily pressure readings and energy consumption across all nodes in the network, an AI-based optimization wireless sensor network is designed for communication and linked to an energy balance system. Sensors are strategically deployed at the network's nerve centres. The maximum flow algorithm is used for a grid representing the water and energy balance to determine the positions of the virtual nodes.

China-Europe Container Multimodal Transport Path Selection Based on Multi-objective Optimization

With the advancement of the "Belt and Road" initiative, trade between China and Europe has been steadily growing, and China-Europe container transportation has received increasing attention. This study analyzes the influencing factors of China-Europe container transport path selection and, based on the physical network of China-Europe container transport, constructs virtual nodes according to the transport modes that can be transited at different nodes and their own transshipment operations. By reflecting cost, time, and carbon emission factors in the virtual network, we construct a service network for China-Europe container multimodal transport, which in turn forms a multi-objective transport scheme selection model considering transportation cost, time, and carbon emissions. Subsequently, the economic and practical aspects of this transport path selection model are verified through five case studies of container transport from Dalian to Hamburg, Germany. Lastly, the sensitivity of factors, such as cost and time, to the China-Europe container multimodal transport path selection is assessed based on scenario analysis. This analysis offers valuable references for various decision-makers involved in the selection of the China-Europe container transport path.

HA-D3QN: Embedding virtual private cloud in cloud data centers with heuristic assisted deep reinforcement learning

The virtual network embedding problem is embedding virtual networks (VNs) in a substrate network so that revenue or accept ratio is maximized. Previous study usually assumes disclosed communication demand among the virtual nodes in a VN, mismatching real-world cloud computing scenarios. In this paper, we propose a new VN abstraction based on the widely used Virtual Private Cloud model, where internal communication demand is unknown to cloud providers. In contrast with the majority of existing research, we allow the co-location of the virtual nodes belonging to the same VN, and introduce the concept of switching capacity for practical resource reservation. We categorize the substrate resources in cloud data centers into additive and non-additive for the first time, and devise our algorithms accordingly. After formulating the problem, we propose a solution framework named HA-D3QN (Heuristic Assisted Dueling Double Deep Q Network). Essentially, HA-D3QN selects the best responses to different system states by combining the D3QN deep reinforcement learning structure and the candidate actions, which are generated by our proposed heuristic algorithms for addressing the exponentially large action space. Finally, we conduct extensive simulation experiments, the results of which verify the effectiveness of our approach.

Chinese Herbal Medicine Recognition Using a VCSEL-Based Time-Delay Reservoir Computing System

We numerically investigate the performance of Chinese herbal medicine (CHM) recognition using a time delay reservoir computing (TDRC) system consist of a vertical-cavity surface-emitting laser (VCSEL) subjected to optical feedback. A database of 960 images from 12 CHM categories is used to evaluate the recognition performance, most of which contain many CHM samples and have different backgrounds. The CHM image feature vector is masked and optically injected into the VCSEL, and the VCSEL output in two polarization modes are sampled as the virtual node states for readout. After testing the CHM recognition performance of TDRC under injecting the same information into two polarization modes of the VCSEL, we further test the performance of parallel processing by injecting half of the image information into each of the two polarization modes. By concatenating the virtual node states collected from two modes for readout, the recognition speed is doubled. Meanwhile, the influence of key parameters on recognition performance are investigated and the relationship between system idle state and recognition performance is also examined. The results show that, under parallel processing and orthogonal optical feedback, the TDRC achieves the minimum recognition error of 1.7% at a reservoir processing rate of 2×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">9</sup> images per second.