Autonomous Vehicle Platoons In Urban Road Networks:A Joint Distributed Reinforcement Learning and Model Predictive Control Approach

In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the aim to put in light the main f eatures of the proposed approach. Moreover, it is important to underline that in different operating scenarios the proposed reinforcement learning scheme is capable of significantly reducing traffic congestion phenomena when compared with well-reputed competitors.

Recurrent neural network decoding of rotated surface codes based on distributed strategy

Quantum error correction is a crucial technology for realizing quantum computers.These computers achieve faulttolerant quantum computing by detecting and correcting errors using decoding algorithms.Quantum error correction using neural network-based machine learning methods is a promising approach that is adapted to physical systems without the need to build noise models.In this paper,we use a distributed decoding strategy,which effectively alleviates the problem of exponential growth of the training set required for neural networks as the code distance of quantum error-correcting codes increases.Our decoding algorithm is based on renormalization group decoding and recurrent neural network decoder.The recurrent neural network is trained through the ResNet architecture to improve its decoding accuracy.Then we test the decoding performance of our distributed strategy decoder,recurrent neural network decoder,and the classic minimum weight perfect matching(MWPM)decoder for rotated surface codes with different code distances under the circuit noise model,the thresholds of these three decoders are about 0.0052,0.0051,and 0.0049,respectively.Our results demonstrate that the distributed strategy decoder outperforms the other two decoders,achieving approximately a 5%improvement in decoding efficiency compared to the MWPM decoder and approximately a 2%improvement compared to the recurrent neural network decoder.

Application of DSAPSO Algorithm in Distribution Network Reconfiguration with Distributed Generation

With the current integration of distributed energy resources into the grid,the structure of distribution networks is becoming more complex.This complexity significantly expands the solution space in the optimization process for network reconstruction using intelligent algorithms.Consequently,traditional intelligent algorithms frequently encounter insufficient search accuracy and become trapped in local optima.To tackle this issue,a more advanced particle swarm optimization algorithm is proposed.To address the varying emphases at different stages of the optimization process,a dynamic strategy is implemented to regulate the social and self-learning factors.The Metropolis criterion is introduced into the simulated annealing algorithm to occasionally accept suboptimal solutions,thereby mitigating premature convergence in the population optimization process.The inertia weight is adjusted using the logistic mapping technique to maintain a balance between the algorithm’s global and local search abilities.The incorporation of the Pareto principle involves the consideration of network losses and voltage deviations as objective functions.A fuzzy membership function is employed for selecting the results.Simulation analysis is carried out on the restructuring of the distribution network,using the IEEE-33 node system and the IEEE-69 node system as examples,in conjunction with the integration of distributed energy resources.The findings demonstrate that,in comparison to other intelligent optimization algorithms,the proposed enhanced algorithm demonstrates a shorter convergence time and effectively reduces active power losses within the network.Furthermore,it enhances the amplitude of node voltages,thereby improving the stability of distribution network operations and power supply quality.Additionally,the algorithm exhibits a high level of generality and applicability.

An Algorithm for Short-Circuit Current Interval in Distribution Networks with Inverter Type Distributed Generation Based on Affine Arithmetic

During faults in a distribution network,the output power of a distributed generation(DG)may be uncertain.Moreover,the output currents of distributed power sources are also affected by the output power,resulting in uncertainties in the calculation of the short-circuit current at the time of a fault.Additionally,the impacts of such uncertainties around short-circuit currents will increase with the increase of distributed power sources.Thus,it is very important to develop a method for calculating the short-circuit current while considering the uncertainties in a distribution network.In this study,an affine arithmetic algorithm for calculating short-circuit current intervals in distribution networks with distributed power sources while considering power fluctuations is presented.The proposed algorithm includes two stages.In the first stage,normal operations are considered to establish a conservative interval affine optimization model of injection currents in distributed power sources.Constrained by the fluctuation range of distributed generation power at the moment of fault occurrence,the model can then be used to solve for the fluctuation range of injected current amplitudes in distributed power sources.The second stage is implemented after a malfunction occurs.In this stage,an affine optimization model is first established.This model is developed to characterizes the short-circuit current interval of a transmission line,and is constrained by the fluctuation range of the injected current amplitude of DG during normal operations.Finally,the range of the short-circuit current amplitudes of distribution network lines after a short-circuit fault occurs is predicted.The algorithm proposed in this article obtains an interval range containing accurate results through interval operation.Compared with traditional point value calculation methods,interval calculation methods can provide more reliable analysis and calculation results.The range of short-circuit current amplitude obtained by this algorithm is slightly larger than those obtained using the Monte Carlo algorithm and the Latin hypercube sampling algorithm.Therefore,the proposed algorithm has good suitability and does not require iterative calculations,resulting in a significant improvement in computational speed compared to the Monte Carlo algorithm and the Latin hypercube sampling algorithm.Furthermore,the proposed algorithm can provide more reliable analysis and calculation results,improving the safety and stability of power systems.

A Distributed Photovoltaics Ordering Grid-Connected Method for Analyzing Voltage Impact in Radial Distribution Networks

In recent years,distributed photovoltaics(DPV)has ushered in a good development situation due to the advantages of pollution-free power generation,full utilization of the ground or roof of the installation site,and balancing a large number of loads nearby.However,under the background of a large-scale DPV grid-connected to the county distribution network,an effective analysis method is needed to analyze its impact on the voltage of the distribution network in the early development stage of DPV.Therefore,a DPV orderly grid-connected method based on photovoltaics grid-connected order degree(PGOD)is proposed.This method aims to orderly analyze the change of voltage in the distribution network when large-scale DPV will be connected.Firstly,based on the voltagemagnitude sensitivity(VMS)index of the photovoltaics permitted grid-connected node and the acceptance of grid-connected node(AoGCN)index of other nodes in the network,thePGODindex is constructed to determine the photovoltaics permitted grid-connected node of the current photovoltaics grid-connected state network.Secondly,a photovoltaics orderly grid-connected model with a continuous updating state is constructed to obtain an orderly DPV grid-connected order.The simulation results illustrate that the photovoltaics grid-connected order determined by this method based on PGOD can effectively analyze the voltage impact of large-scale photovoltaics grid-connected,and explore the internal factors and characteristics of the impact.

Research on Scheduling Strategy of Flexible Interconnection Distribution Network Considering Distributed Photovoltaic and Hydrogen Energy Storage

Distributed photovoltaic(PV)is one of the important power sources for building a new power system with new energy as the main body.The rapid development of distributed PV has brought new challenges to the operation of distribution networks.In order to improve the absorption ability of large-scale distributed PV access to the distribution network,the AC/DC hybrid distribution network is constructed based on flexible interconnection technology,and a coordinated scheduling strategy model of hydrogen energy storage(HS)and distributed PV is established.Firstly,the mathematical model of distributed PV and HS system is established,and a comprehensive energy storage system combining seasonal hydrogen energy storage(SHS)and battery(BT)is proposed.Then,a flexible interconnected distribution network scheduling optimization model is established to minimize the total active power loss,voltage deviation and system operating cost.Finally,simulation analysis is carried out on the improved IEEE33 node,the NSGA-II algorithm is used to solve specific examples,and the optimal scheduling results of the comprehensive economy and power quality of the distribution network are obtained.Compared with the method that does not consider HS and flexible interconnection technology,the network loss and voltage deviation of this method are lower,and the total system cost can be reduced by 3.55%,which verifies the effectiveness of the proposed method.

Exploration of the efficacy and mechanism of treating head wind disease with the combination change of ginger volatile oil and gingerol by using content-weighted network pharmacology technology

Background:Exploring the efficacy,potential components,and mechanism of the combination of ginger essential oil and gingerols in the treatment of head wind disease based on network pharmacology technology with content weight.Methods:The experimental groups were divided into:0:10,1:4,1:2,1:1,2:1,4:1,10:0.The relative content(Ri)of the chemical constituents of ginger's volatile oil was determined using gas chromatography-mass spectrometry(GC-MS).Additionally,the physicochemical and biological property parameters(LogP,MDCK,PPB,MW)of the components were considered.To assess the quantitative effect of the components,a grading score was performed,and the quantitative effect index(Ki)was calculated.Subsequently,the target effect index(Ti)was calculated by combining the component-target matching score(Fit score).Using these calculations,the target effect score A was determined under the influence of multiple components targeting different targets.Key targets with A≥1000 were identified.To predict the targets related to head wind disease,the Comparative Toxicogenomics Database(https://ctdbase.org/),Gene Cards(https://www.genecards.org/),and Disgenet database(https://www.disgenet.org/)were utilized.The key targets,obtained from different proportions of ginger's volatile oil and gingerol,were intersected with the predicted targets.This facilitated network pharmacological analysis and verification of the efficacy.Results:The content of volatile oil in ginger demonstrated an impact on key targets associated with the volatile oil group.Each specific combination of volatile oil consistently activated distinct pathways,with variations stemming from changes in content.Experimental testing revealed that different combinations of ginger's volatile oil and gingerol effectively alleviated migraine symptoms in rats.Conclusion:Through the application of content-weighted network pharmacology technology and pharmacodynamic verification,it was determined that altering the ratio between ginger's volatile oil and gingerol leads to variations in potential targets and pathways,consequently impacting its efficacy.

Fully Distributed Learning for Deep Random Vector Functional-Link Networks

In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.

Distributed Nash Equilibrium Seeking for General Networked Games With Bounded Disturbances

This paper is concerned with anti-disturbance Nash equilibrium seeking for games with partial information.First,reduced-order disturbance observer-based algorithms are proposed to achieve Nash equilibrium seeking for games with firstorder and second-order players,respectively.In the developed algorithms,the observed disturbance values are included in control signals to eliminate the influence of disturbances,based on which a gradient-like optimization method is implemented for each player.Second,a signum function based distributed algorithm is proposed to attenuate disturbances for games with secondorder integrator-type players.To be more specific,a signum function is involved in the proposed seeking strategy to dominate disturbances,based on which the feedback of the velocity-like states and the gradients of the functions associated with players achieves stabilization of system dynamics and optimization of players'objective functions.Through Lyapunov stability analysis,it is proven that the players'actions can approach a small region around the Nash equilibrium by utilizing disturbance observerbased strategies with appropriate control gains.Moreover,exponential(asymptotic)convergence can be achieved when the signum function based control strategy(with an adaptive control gain)is employed.The performance of the proposed algorithms is tested by utilizing an integrated simulation platform of virtual robot experimentation platform(V-REP)and MATLAB.

Data-Driven Control of Distributed Event-Triggered Network Systems

The present paper deals with data-driven event-triggered control of a class of unknown discrete-time interconnected systems(a.k.a.network systems).To this end,we start by putting forth a novel distributed event-triggering transmission strategy based on periodic sampling,under which a model-based stability criterion for the closed-loop network system is derived,by leveraging a discrete-time looped-functional approach.Marrying the model-based criterion with a data-driven system representation recently developed in the literature,a purely data-driven stability criterion expressed in the form of linear matrix inequalities(LMIs)is established.Meanwhile,the data-driven stability criterion suggests a means for co-designing the event-triggering coefficient matrix and the feedback control gain matrix using only some offline collected state-input data.Finally,numerical results corroborate the efficacy of the proposed distributed data-driven event-triggered network system(ETS)in cutting off data transmissions and the co-design procedure.

Quality-Aware Massive Content Delivery in Digital Twin-Enabled Edge Networks

Massive content delivery will become one of the most prominent tasks of future B5G/6G communication.However,various multimedia applications possess huge differences in terms of object oriented(i.e.,machine or user)and corresponding quality evaluation metric,which will significantly impact the design of encoding or decoding within content delivery strategy.To get over this dilemma,we firstly integrate the digital twin into the edge networks to accurately and timely capture Quality-of-Decision(QoD)or Quality-of-Experience(QoE)for the guidance of content delivery.Then,in terms of machinecentric communication,a QoD-driven compression mechanism is designed for video analytics via temporally lightweight frame classification and spatially uneven quality assignment,which can achieve a balance among decision-making,delivered content,and encoding latency.Finally,in terms of user-centric communication,by fully leveraging haptic physical properties and semantic correlations of heterogeneous streams,we develop a QoE-driven video enhancement scheme to supply high data fidelity.Numerical results demonstrate the remarkable performance improvement of massive content delivery.

Operation Control Method of Relay Protection in Flexible DC Distribution Network Compatible with Distributed Power Supply

A novel operation control method for relay protection in flexible DC distribution networks with distributed power supply is proposed to address the issue of inaccurate fault location during relay protection,leading to poor performance.The method combines a fault-tolerant fault location method based on long-term and short-term memory networks to accurately locate the fault section.Then,an operation control method for relay protection based on adaptive weight and whale optimization algorithm(WOA)is used to construct an objective function considering the shortest relay protection action time and the smallest impulse current.The adaptive weight and WOA are employed to obtain the optimal strategy for relay protection operation control,reducing the action time and impulse current.Experimental results demonstrate the effectiveness of the proposed method in accurately locating faults and improving relay protection performance.The longest operation time is reduced by 4.7023 s,and the maximum impulse current is limited to 0.3 A,effectively controlling the impact of large impulse currents and enhancing control efficiency.

Adaptive Load Balancing for Parameter Servers in Distributed Machine Learning over Heterogeneous Networks

In distributed machine learning(DML)based on the parameter server(PS)architecture,unbalanced communication load distribution of PSs will lead to a significant slowdown of model synchronization in heterogeneous networks due to low utilization of bandwidth.To address this problem,a network-aware adaptive PS load distribution scheme is proposed,which accelerates model synchronization by proactively adjusting the communication load on PSs according to network states.We evaluate the proposed scheme on MXNet,known as a realworld distributed training platform,and results show that our scheme achieves up to 2.68 times speed-up of model training in the dynamic and heterogeneous network environment.

Research on Coordinated Development and Optimization of Distribution Networks at All Levels in Distributed Power Energy Engineering

The uncertainty of distributed generation energy has dramatically challenged the coordinated development of distribution networks at all levels.This paper focuses on the multi-time-scale regulation model of distributed generation energy under normal conditions.The simulation results of the example verify the self-optimization characteristics and the effectiveness of real-time dispatching of the distribution network control technology at all levels under multiple time scales.

Decentralized content sharing in mobile ad-hoc networks:A survey

The evolution of smart mobile devices has significantly impacted the way we generate and share contents and introduced a huge volume of Internet traffic.To address this issue and take advantage of the short-range communication capabilities of smart mobile devices,the decentralized content sharing approach has emerged as a suitable and promising alternative.Decentralized content sharing uses a peer-to-peer network among colocated smart mobile device users to fulfil content requests.Several articles have been published to date to address its different aspects including group management,interest extraction,message forwarding,participation incentive,and content replication.This survey paper summarizes and critically analyzes recent advancements in decentralized content sharing and highlights potential research issues that need further consideration.

Cooperative Content Caching and Delivery in Vehicular Networks: A Deep Neural Network Approach

The growing demand for low delay vehicular content has put tremendous strain on the backbone network.As a promising alternative,cooperative content caching among different cache nodes can reduce content access delay.However,heterogeneous cache nodes have different communication modes and limited caching capacities.In addition,the high mobility of vehicles renders the more complicated caching environment.Therefore,performing efficient cooperative caching becomes a key issue.In this paper,we propose a cross-tier cooperative caching architecture for all contents,which allows the distributed cache nodes to cooperate.Then,we devise the communication link and content caching model to facilitate timely content delivery.Aiming at minimizing transmission delay and cache cost,an optimization problem is formulated.Furthermore,we use a multi-agent deep reinforcement learning(MADRL)approach to model the decision-making process for caching among heterogeneous cache nodes,where each agent interacts with the environment collectively,receives observations yet a common reward,and learns its own optimal policy.Extensive simulations validate that the MADRL approach can enhance hit ratio while reducing transmission delay and cache cost.

Dis-NDVW: Distributed Network Asset Detection and Vulnerability Warning Platform

With the rapid development of Internet technology,the issues of network asset detection and vulnerability warning have become hot topics of concern in the industry.However,most existing detection tools operate in a single-node mode and cannot parallelly process large-scale tasks,which cannot meet the current needs of the industry.To address the above issues,this paper proposes a distributed network asset detection and vulnerability warning platform(Dis-NDVW)based on distributed systems and multiple detection tools.Specifically,this paper proposes a distributed message sub-scription and publication system based on Zookeeper and Kafka,which endows Dis-NDVW with the ability to parallelly process large-scale tasks.Meanwhile,Dis-NDVW combines the RangeAssignor,RoundRobinAssignor,and StickyAssignor algorithms to achieve load balancing of task nodes in a distributed detection cluster.In terms of a large-scale task processing strategy,this paper proposes a task partitioning method based on First-In-First-Out(FIFO)queue.This method realizes the parallel operation of task producers and task consumers by dividing pending tasks into different queues according to task types.To ensure the data reliability of the task cluster,Dis-NDVW provides a redundant storage strategy for master-slave partition replicas.In terms of distributed storage,Dis-NDVW utilizes a distributed elastic storage service based on ElasticSearch to achieve distributed storage and efficient retrieval of big data.Experimental verification shows that Dis-NDVW can better meet the basic requirements of ultra-large-scale detection tasks.

Synergetic optimization operation method for distribution network based on SOP and PV

The integration of distributed generation brings in new challenges for the operation of distribution networks,including out-of-limit voltage and power flow control.Soft open points(SOP)are new power electronic devices that can flexibly control active and reactive power flows.With the exception of active power output,photovoltaic(PV)devices can provide reactive power compensation through an inverter.Thus,a synergetic optimization operation method for SOP and PV in a distribution network is proposed.A synergetic optimization model was developed.The voltage deviation,network loss,and ratio of photovoltaic abandonment were selected as the objective functions.The PV model was improved by considering the three reactive power output modes of the PV inverter.Both the load fluctuation and loss of the SOP were considered.Three multi-objective optimization algorithms were used,and a compromise optimal solution was calculated.Case studies were conducted using an IEEE 33-node system.The simulation results indicated that the SOP and PVs complemented each other in terms of active power transmission and reactive power compensation.Synergetic optimization improves power control capability and flexibility,providing better power quality and PV consumption rate.

Joint Content Caching and Fetching Scheme with Cooperative Transmission in Hierarchical Networks

Concerned with the surge of contentcentric applications,it is challenging to balance network traffic and cater to low-delay requirements.Hierarchical caching architecture of both edge network(EN)and core network(CN)emerges and leverages caching resources to reduce the delivery delay of contents.Most previous work takes an impractical assumption to treat the CN as a content provider,which neglects the collaboration by intermediate CN caches.Most importantly,it is still necessary to thoroughly study the tradeoff between CN delay and edge delay for files delivery so as to minimize the overall delivery delay across the network.In this paper,we consider a hierarchical caching network with distributed CN nodes and edge nodes,where cooperative transmission is enabled for edge nodes to transmit multi-files simultaneously.This poses a joint optimization problem of hierarchical file caching and fetching to minimize the overall delivery delay of requests.Since the problem is NP-hard,we decompose the original problem and design an iterative algorithm to address it.Numerical results validate that the proposed scheme can find a balanced solution between lowering edge delay by utilizing coordinated CN caching and lowering CN delay by solely relying on edge caching.

Identification of Type of a Fault in Distribution System Using Shallow Neural Network with Distributed Generation

A distributed generation system(DG)has several benefits over a traditional centralized power system.However,the protection area in the case of the distributed generator requires special attention as it encounters stability loss,failure re-closure,fluctuations in voltage,etc.And thereby,it demands immediate attention in identifying the location&type of a fault without delay especially when occurred in a small,distributed generation system,as it would adversely affect the overall system and its operation.In the past,several methods were proposed for classification and localisation of a fault in a distributed generation system.Many of those methods were accurate in identifying location,but the accuracy in identifying the type of fault was not up to the acceptable mark.The proposed work here uses a shallow artificial neural network(sANN)model for identifying a particular type of fault that could happen in a specific distribution network when used in conjunction with distributed generators.Firstly,a distribution network consisting of two similar distributed generators(DG1 and DG2),one grid,and a 100 Km distribution line is modeled.Thereafter,different voltages and currents corresponding to various faults(line to line,line to ground)at different locations are tabulated,resulting in a matrix of 500×18 inputs.Secondly,the sANN is formulated for identifying the types of faults in the system in which the above-obtained data is used to train,validate,and test the neural network.The overall result shows an unprecedented almost zero percent error in identifying the type of the faults.