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.

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.

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.

Sparse Adversarial Learning for FDIA Attack Sample Generation in Distributed Smart

False data injection attack(FDIA)is an attack that affects the stability of grid cyber-physical system(GCPS)by evading the detecting mechanism of bad data.Existing FDIA detection methods usually employ complex neural networkmodels to detect FDIA attacks.However,they overlook the fact that FDIA attack samples at public-private network edges are extremely sparse,making it difficult for neural network models to obtain sufficient samples to construct a robust detection model.To address this problem,this paper designs an efficient sample generative adversarial model of FDIA attack in public-private network edge,which can effectively bypass the detectionmodel to threaten the power grid system.A generative adversarial network(GAN)framework is first constructed by combining residual networks(ResNet)with fully connected networks(FCN).Then,a sparse adversarial learning model is built by integrating the time-aligned data and normal data,which is used to learn the distribution characteristics between normal data and attack data through iterative confrontation.Furthermore,we introduce a Gaussian hybrid distributionmatrix by aggregating the network structure of attack data characteristics and normal data characteristics,which can connect and calculate FDIA data with normal characteristics.Finally,efficient FDIA attack samples can be sequentially generated through interactive adversarial learning.Extensive simulation experiments are conducted with IEEE 14-bus and IEEE 118-bus system data,and the results demonstrate that the generated attack samples of the proposed model can present superior performance compared to state-of-the-art models in terms of attack strength,robustness,and covert capability.

Mixed Integer Robust Programming Model for Multimodal Fresh Agricultural Products Terminal Distribution Network Design

The low efficiency and high cost of fresh agricultural product terminal distribution directly restrict the operation of the entire supply network.To reduce costs and optimize the distribution network,we construct a mixed integer programmingmodel that comprehensively considers tominimize fixed,transportation,fresh-keeping,time,carbon emissions,and performance incentive costs.We analyzed the performance of traditional rider distribution and robot distribution modes in detail.In addition,the uncertainty of the actual market demand poses a huge threat to the stability of the terminal distribution network.In order to resist uncertain interference,we further extend the model to a robust counterpart form.The results of the simulation show that the instability of random parameters will lead to an increase in the cost.Compared with the traditional rider distribution mode,the robot distribution mode can save 12.7%on logistics costs,and the distribution efficiency is higher.Our research can provide support for the design of planning schemes for transportation enterprise managers.

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.

Neural network study of the nuclear ground-state spin distribution within a random interaction ensemble

The distribution of the nuclear ground-state spin in a two-body random ensemble(TBRE)was studied using a general classification neural network(NN)model with two-body interaction matrix elements as input features and the corresponding ground-state spins as labels or output predictions.The quantum many-body system problem exceeds the capability of our optimized NNs in terms of accurately predicting the ground-state spin of each sample within the TBRE.However,our NN model effectively captured the statistical properties of the ground-state spin because it learned the empirical regularity of the ground-state spin distribution in TBRE,as discovered by physicists.

Optimal Location and Sizing ofMulti-Resource Distributed Generator Based onMulti-Objective Artificial Bee Colony Algorithm

Distribution generation(DG)technology based on a variety of renewable energy technologies has developed rapidly.A large number of multi-type DG are connected to the distribution network(DN),resulting in a decline in the stability of DN operation.It is urgent to find a method that can effectively connect multi-energy DG to DN.photovoltaic(PV),wind power generation(WPG),fuel cell(FC),and micro gas turbine(MGT)are considered in this paper.A multi-objective optimization model was established based on the life cycle cost(LCC)of DG,voltage quality,voltage fluctuation,system network loss,power deviation of the tie-line,DG pollution emission index,and meteorological index weight of DN.Multi-objective artificial bee colony algorithm(MOABC)was used to determine the optimal location and capacity of the four kinds of DG access DN,and compared with the other three heuristic algorithms.Simulation tests based on IEEE 33 test node and IEEE 69 test node show that in IEEE 33 test node,the total voltage deviation,voltage fluctuation,and system network loss of DN decreased by 49.67%,7.47%and 48.12%,respectively,compared with that without DG configuration.In the IEEE 69 test node,the total voltage deviation,voltage fluctuation and system network loss of DN in the MOABC configuration scheme decreased by 54.98%,35.93%and 75.17%,respectively,compared with that without DG configuration,indicating that MOABC can reasonably plan the capacity and location of DG.Achieve the maximum trade-off between DG economy and DN operation stability.

Optimal Configuration of Fault Location Measurement Points in DC Distribution Networks Based on Improved Particle Swarm Optimization Algorithm

The escalating deployment of distributed power sources and random loads in DC distribution networks hasamplified the potential consequences of faults if left uncontrolled. To expedite the process of achieving an optimalconfiguration of measurement points, this paper presents an optimal configuration scheme for fault locationmeasurement points in DC distribution networks based on an improved particle swarm optimization algorithm.Initially, a measurement point distribution optimization model is formulated, leveraging compressive sensing.The model aims to achieve the minimum number of measurement points while attaining the best compressivesensing reconstruction effect. It incorporates constraints from the compressive sensing algorithm and networkwide viewability. Subsequently, the traditional particle swarm algorithm is enhanced by utilizing the Haltonsequence for population initialization, generating uniformly distributed individuals. This enhancement reducesindividual search blindness and overlap probability, thereby promoting population diversity. Furthermore, anadaptive t-distribution perturbation strategy is introduced during the particle update process to enhance the globalsearch capability and search speed. The established model for the optimal configuration of measurement points issolved, and the results demonstrate the efficacy and practicality of the proposed method. The optimal configurationreduces the number of measurement points, enhances localization accuracy, and improves the convergence speedof the algorithm. These findings validate the effectiveness and utility of the proposed approach.

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.

Probability Distribution of China Aviation Network Average Degree of Edge Vertices and Its Evolutionary Trace Based on Complex Network

In order to reveal the complex network characteristics and evolution principle of China aviation network, the probability distribution and evolution trace of average degree of edge vertices of China aviation network were studied based on the statistics data of China civil aviation network in 1988, 1994, 2001, 2008 and 2015. According to the theory and method of complex network, the network system was constructed with the city where the airport was located as the network node and the route between cities as the edge of the network. Based on the statistical data, the average degrees of edge vertices in China aviation network in 1988, 1994, 2001, 2008 and 2015 were calculated. Using the probability statistical analysis method and regression analysis approach, it was found that the average degree of edge vertices had the probability distribution of normal function and the position parameters and scale parameters of the probability distribution had linear evolution trace.

Probability Distribution of Ratio of China Aviation Network Edge Vertices Degree and Its Evolutionary Trace Based on Complex Network

In order to reveal the complex network characteristics and evolution principle of China aviation network, the probability distribution and evolution trace of ratio of China aviation network edge vertices degree were studied based on the statistics data of China civil aviation network in 1988, 1994, 2001, 2008 and 2015. According to the theory and method of complex network, the network system was constructed with the city where the airport was located as the network node and the route between cities as the edge of the network. Based on the statistical data, the ratio of edge vertices degree in China aviation network in 1988, 1994, 2001, 2008 and 2015 were calculated. Using the probability statistical analysis method and regression analysis approach, it was found that the ratio of edge vertices degree had linear probability distribution and the two parameters of the probability distribution had linear evolution trace.

Analysis and Research on 10kV Distribution Network Faults

The 10kV distribution network is an essential component of the power system,and its stable operation is crucial for ensuring reliable power supply.However,various factors can lead to faults in the distribution network.In order to enhance the safety and reliability of power distribution,this paper focuses on the analysis of faults in the 10kV distribution network caused by natural factors,operational factors,human factors,and equipment factors.It elucidates the various hazards resulting from distribution network faults and proposes corresponding preventive measures for different types of faults in the 10kV distribution network.The aim is to mitigate or reduce the impact of distribution network faults,ensuring the safe and stable operation of the distribution system.

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.