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.

COMBINATION OF DISTRIBUTED KALMAN FILTER AND BP NEURAL NETWORK FOR ESG BIAS MODEL IDENTIFICATION

By combining the distributed Kalman filter （DKF） with the back propagation neural network （BPNN）,a novel method is proposed to identify the bias of electrostatic suspended gyroscope （ESG）. Firstly,the data sets of multi-measurements of the same ESG in different noise environments are ＂mapped＂ into a sensor network,and DKF with embedded consensus filters is then used to preprocess the data sets. After transforming the preprocessed results into the trained input and the desired output of neural network,BPNN with the learning rate and the momentum term is further utilized to identify the ESG bias. As demonstrated in the experiment,the proposed approach is effective for the model identification of the ESG bias.

Analysis and Optimum Design of Differential Inductors Using Distributed Capacitance Model

A distributed capacitance model for monolithic inductors is developed to predict the equivalently parasitical capacitances of the inductor.The ratio of the self-resonant frequency (f SR) of the differential-driven symmetric inductor to the f SR of the single-ended driven inductor is firstly predicted and explained.Compared with a single-ended configuration,experimental data demonstrate that the differential inductor offers a 127% greater maximum quality factor and a broader range of operating frequencies.Two differential inductors with low parasitical capacitance are developed and validated.

Working Condition Real-Time Monitoring Model of Lithium Ion Batteries Based on Distributed Parameter System and Single Particle Model

Lithium ion batteries are complicated distributed parameter systems that can be described preferably by partial differential equations and a field theory. To reduce the solution difficulty and the calculation amount, if a distributed parameter system is described by ordinary differential equations （ODE） during the analysis and the design of distributed parameter system, the reliability of the system description will be reduced, and the systemic errors will be introduced. Studies on working condition real-time monitoring can improve the security because the rechargeable LIBs are widely used in many electronic systems and electromechanical equipment. Single particle model （SPM） is the simplification of LIB under some approximations, and can estimate the working parameters of a LIB at the faster simulation speed. A LIB modelling algorithm based on PDEs and SPM is proposed to monitor the working condition of LIBs in real time. Although the lithium ion concentration is an unmeasurable distributed parameter in the anode of LIB, the working condition monitoring model can track the real time lithium ion concentration in the anode of LIB, and calculate the residual which is the difference between the ideal data and the measured data. A fault alarm can be triggered when the residual is beyond the preset threshold. A simulation example verifies that the effectiveness and the accuracy of the working condition real-time monitoring model of LIB based on PDEs and SPM.

Predicting the probability distribution of Martian rocks mechanical property based on microscale rock mechanical experiments and accurate grain-based modeling

The exploration of Mars would heavily rely on Martian rocks mechanics and engineering technology.As the mechanical property of Martian rocks is uncertain,it is of utmost importance to predict the probability distribution of Martian rocks mechanical property for the success of Mars exploration.In this paper,a fast and accurate probability distribution method for predicting the macroscale elastic modulus of Martian rocks was proposed by integrating the microscale rock mechanical experiments(micro-RME),accurate grain-based modeling(AGBM)and upscaling methods based on reliability principles.Firstly,the microstructure of NWA12564 Martian sample and elastic modulus of each mineral were obtained by micro-RME with TESCAN integrated mineral analyzer(TIMA)and nanoindentation.The best probability distribution function of the minerals was determined by Kolmogorov-Smirnov(K-S)test.Secondly,based on best distribution function of each mineral,the Monte Carlo simulations(MCS)and upscaling methods were implemented to obtain the probability distribution of upscaled elastic modulus.Thirdly,the correlation between the upscaled elastic modulus and macroscale elastic modulus obtained by AGBM was established.The accurate probability distribution of the macroscale elastic modulus was obtained by this correlation relationship.The proposed method can predict the probability distribution of Martian rocks mechanical property with any size and shape samples.

Federated Learning Model for Auto Insurance Rate Setting Based on Tweedie Distribution

In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.

A DISTRIBUTED HYPERMAP MODEL FOR INTERNET GIS

The rapid development of Internet technology makes it possible to integrate GIS with the Internet,forming Internet GIS.Internet GIS is based on a distributed client/server architecture and TCP/IP & IIOP.When constructing and designing Internet GIS,we face the problem of how to express information units of Internet GIS.In order to solve this problem,this paper presents a distributed hypermap model for Internet GIS.This model provides a solution to organize and manage Internet GIS information units.It also illustrates relations between two information units and in an internal information unit both on clients and servers.On the basis of this model,the paper contributes to the expressions of hypermap relations and hypermap operations.The usage of this model is shown in the implementation of a prototype system.

A distributed runoff model for inland mountainous river basin of Northwest China

In order to predict the futuristic runoff under global warming, and to approach to the effects of vegetation on the ecological environment of the inland river mountainous watershed of Northwest China, the authors use the routine hydrometric data to create a distributed monthly model with some conceptual parameters, coupled with GIS and RS tools and data. The model takes sub-basin as the minimal confluent unit, divides the main soils of the basin into 3 layers, and identifies the vegetation types as forest and pasture. The data used in the model are precipitation, air temperature, runoff, soil weight water content, soil depth, soil bulk density, soil porosity, land cover, etc. The model holds that if the water amount is greater than the water content capacity, there will be surface runoff. The actual evaporation is proportional to the product of the potential evaporation and soil volume water content. The studied basin is Heihe mainstream mountainous basin, with a drainage area of 10,009 km 2 . The data used in this simulation are from Jan. 1980 to Dec. 1995, and the first 10 years' data are used to simulate, while the last 5 years' data are used to calibrate. For the simulation process, the Nash-Sutcliffe Equation, Balance Error and Explained Variance is 0.8681, 5.4008 and 0.8718 respectively, while for the calibration process, 0.8799, -0.5974 and 0.8800 respectively. The model results show that the futuristic runoff of Heihe river basin will increase a little. The snowmelt, glacier meltwater and the evaportranspiration will increase. The air temperature increment will make the permanent snow and glacier area diminish, and the snowline will rise. The vegetation, especially the forest in Heihe mountainous watershed, could lead to the evapotranspiration decrease of the watershed, adjust the runoff process, and increase the soil water content.

GLOBAL STABILITY OF SIRS EPIDEMIC MODELS WITH A CLASS OF NONLINEAR INCIDENCE RATES AND DISTRIBUTED DELAYS

In this article, we establish the global asymptotic stability of a disease-free equilibrium and an endemic equilibrium of an SIRS epidemic model with a class of nonlin- ear incidence rates and distributed delays. By using strict monotonicity of the incidence function and constructing a Lyapunov functional, we obtain sufficient conditions under which the endemic equilibrium is globally asymptotically stable. When the nonlinear inci- dence rate is a saturated incidence rate, our result provides a new global stability condition for a small rate of immunity loss.

Distributed modeling of direct solar radiation on rugged terrain of the Yellow River Basin

Due to the influences of local topographical factors and terrain inter-shielding, calculation of direct solar radiation （DSR） quantity of rugged terrain is very complex. Based on digital elevation model （DEM） data and meteorological observations, a distributed model for calculating DSR over rugged terrain is developed. This model gives an all-sided consideration on factors influencing th a resolution of 1 km × 1 km for thDSR. Using the developed model, normals of annual DSR quantity wie Yellow River Basin was generated, with DEM data as the general characterization of terrain. Characteristics of DSR quantity influenced by geographic and topographic factors over rugged terrain were analyzed thoroughly. Results suggest that： influenced by local topographic factors, i.e. azimuth, slope and so on, and annual DSR quantity over mountainous area has a clear spatial difference; annual DSR quantity of sunny slope （or southern slope） of mountains is obviously larger than that of shady slope （or northern slope）. The calculated DSR quantity of the Yellow River Basin is provided in the same way as other kinds of spatial information and can be employed as basic geographic data for relevant studies as well.

Framework of Distributed Coupled Atmosphere-Ocean-Wave Modeling System

In order to research the interactions between the atmosphere and ocean as well as their important role in the intensive weather systems of coastal areas, and to improve the forecasting ability of the hazardous weather processes of coastal areas, a coupled atmosphere-ocean-wave modeling system has been developed. The agent-based environment framework for linking models allows flexible and dynamic information exchange between models. For the purpose of flexibility, portability and scalability, the framework of the whole system takes a multi-layer architecture that includes a user interface layer, computational layer and service-enabling layer. The numerical experiment presented in this paper demonstrates the performance of the distributed coupled modeling system.

Distributed hydrological models for addressing effects of spatial variability of roughness on overland flow

In this study, we investigated the origin of the overland flow roughness problem and divided the current overland flow roughness research into three types, as follows: the first type of research takes into account the effects of roughness on the volume and velocity of surface runoff, flood peaks, and the scouring capability of flows, but has not addressed the spatial variability of roughness in detail; the second type of research considers that surface roughness varies spatially with different land usage types, land-cover conditions, and different tillage forms, but lacks a quantitative study of the spatial variability; and the third type of research simply deals with the spatial variability of roughness in each grid cell or land type. We present three shortcomings of the current overland flow roughness research, including(1) the neglect of roughness in distributed hydrological models when simulating the overland flow direction and distribution,(2) the lack of consideration of spatial variability of roughness in hydrological models, and(3) the failure to distinguish the roughness formulas in different overland flow regimes. To solve these problems,distributed hydrological model research should focus on four aspects in regard to overland flow: velocity field observations, flow regime mechanisms, a basic roughness theory, and scale problems.

Distributed Fiber Optic Monitoring and Stability Analysis of a Model Slope under Surcharge Loading

In the discipline of geotechnical engineering, fiber optic sensor based distributed monitoring has played an increasingly important role over the past few decades. Compared with conventional sensors, fiber optic sensors have a variety of exclusive advantages, such as smaller size, higher precision, and better corrosion resistance. These innovative monitoring technologies have been successfully applied for performance monitoring of geo-structures and early warning of potential geo- hazards around the world. In order to investigate their ability to monitor slope stability problems, a medium-sized model of soil nailed slope has been constructed in laboratory. The fully distributed Brillouin optical time-domain analysis （BOTDA） sensing technology was employed to measure the horizontal strain distributions inside the model slope. During model construction, a specially designed strain sensing fiber was buried in the soil mass. Afterward, the surcharge loading was applied on the slope crest in stages using hydraulic jacks and a reaction frame. During testing, an NBX-6o5o BOTDA sensing interrogator was used to collect the fiber optic sensing data. The test results have been analyzed in detail, which shows that the fiber optic sensors can capture the progressive deformation and failure pattern of the model slope. The limit equilibrium analyses were also conducted to obtain the factors ofsafety of the slope under different surface loadings. It is found that the characteristic maximum strains can reflect the stability of the model slope and an empirical relationship was obtained, This study verified the effectiveness of the distributed BOTDA sensing technology in performance monitoring of slope.

A distributed dynamic mesh model of a helical gear pair with tooth profile errors

A dynamic model of a helical gear rotor system is proposed.Firstly,a generally distributed dynamic model of a helical gear pair with tooth profile errors is developed.The gear mesh is represented by a pair of cylinders connected by a series of springs and the stiffness of each spring is equal to the effective mesh stiffness.Combining the gear dynamic model with the rotor-bearing system model,the gear-rotor-bearing dynamic model is developed.Then three cases are presented to analyze the dynamic responses of gear systems.The results reveal that the gear dynamic model is effective and advanced for general gear systems,narrow-faced gear,wide-faced gear and gear with tooth profile errors.Finally,the responses of an example helical gear system are also studied to demonstrate the influence of the lead crown reliefs and misalignments.The results show that both of the lead crown relief and misalignment soften the gear mesh stiffness and the responses of the gear system increase with the increasing lead crown reliefs and misalignments.

A Distributed Monthly Water Balance Model for Analyzing Impacts of Land Cover Change on Flow Regimes

The Miyun Reservoir is the most important water source for Beijing Municipality, the capital of China with a population of more than 12 million. In recent decades, the inflow to the reservoir has shown a decreasing trend, which has seriously threatened water use in Beijing. In order to analyze the influents of land use and cover change (LUCC) upon inflow to Miyun Reservoir, terrain and land use information from remote sensing were utilized with a revised evapotranspiration estimation formula; a water loss model under conditions of human impacts was introduced; and a distributed monthly water balance model was established and applied to the Chaobai River Basin controlled by the Miyun Reservoir. The model simulation suggested that not only the impact of land cover change on evapotranspiration, but also the extra water loss caused by human activities, such as the water and soil conservation development projects should be considered. Although these development projects were of great benefit to human and ecological protection, they could reallocate water resources in time and space, and in a sense thereby influence the stream flow.

Distributed Modeling of Extraterrestrial Solar Radiation Over the Rugged Terrains of Pakistan

In Pakistan,the solar analogue has been addressed but its surface geographical parameterization has given least attention.Inappropriate density of stations and their spatial coverage particularly in difficult peripheral national territories,little or no solar radiation data,non-satisfactory sunshine hours data,and low quality of ground observed cloud cover data create a situation in which the spatial modeling of Extraterrestrial Solar Radiation(ESR) and its ground parameterization got sufficient scope.The Digital Elevation Model (DEM) input into Geographic Information System (GIS) is a compatible tool to demonstrate the spatial distribution of ESR over the rugged terrains of the study domain.For the first time,distributed modeling of ESR is done over the rugged terrains of Pakistan,based on DEM and ArcGIS..Results clearly depict that the complex landforms profoundly disrupt the zonal distribution of ESR in Pakistan.The screening impact of topography is higher on spatial distribution of ESR in winter and considerably low in summer.The combined effect of topography and latitude is obvious.Hence,the model was further testified by plotting Rb (ratio of ESR quantity over rugged terrain against plane surface) against azimuth at different latitudes with different angled slopes.The results clearly support the strong screening effect of rugged terrain through out the country especially in Himalayas,Karakoram and Hindukush (HKH),western border mountains and Balochistan Plateau.This model can be instrumental as baseline geospatial information for scientific investigations in Pakistan,where substantial fraction of national population is living in mountainous regions.

Resilience Against Replay Attacks:A Distributed Model Predictive Control Scheme for Networked Multi-Agent Systems

In this paper,a resilient distributed control scheme against replay attacks for multi-agent networked systems subject to input and state constraints is proposed.The methodological starting point relies on a smart use of predictive arguments with a twofold aim:1)Promptly detect malicious agent behaviors affecting normal system operations;2)Apply specific control actions,based on predictive ideas,for mitigating as much as possible undesirable domino effects resulting from adversary operations.Specifically,the multi-agent system is topologically described by a leader-follower digraph characterized by a unique leader and set-theoretic receding horizon control ideas are exploited to develop a distributed algorithm capable to instantaneously recognize the attacked agent.Finally,numerical simulations are carried out to show benefits and effectiveness of the proposed approach.

Distributed model predictive control for multiagent systems with improved consistency

This paper addresses an improved distributed model predictive control （DMPC） scheme for multiagent systems with an attempt to improving its consistency. The deviation between what an agent is actually doing and what its neighbors believe that agent is doing is penalized in the cost function of each agent. At each sampling instant the compatibility constraint of each agent is set tighter than the previous sampling instant. Like the traditional approach, the performance cost is utilized as the Lyapunov function to prove closed-looped stability. The closed-loop stability is guaranteed if the weight matrix for deviation in the cost function are sufficiently large. The proposed distributed control scheme is formulated as quadratic programming with quadratic constraints. A numerical example is given to illustrate the effectiveness of the proposed scheme.

Application of Developed Grid-GA Distributed Hydrologic Model in Semi-Humid and Semi-Arid Basin

A grid and Green-Ampt based （Grid-GA）distributed hydrologic physical model was developed for flood simulation and forecasting in semi-humid and semi-arid basin. Based on topographical information of each grid cell extracted fi＇om the digital elevation model （DEM） and Green-Ampt infiltration method, the Grid-GA model takes into consideration the redistribution of water content, and consists of vegetation and root interception, evapotranspiration, runoff generation via the excess infiltration mechanism, runoff concentration, and flow routing. The downslope redis- tribution of soil moisture is explicitly calculated on a grid basis, and water exchange among grids within runoff routing along the river drainage networks is taken into consideration. The proposed model and Xin＇anjiang model were ap- plied to the upper Lushi basin in the Luohe River, a tributary of the Yellow River, with an area of 4 716 km2 for flood simulation. Results show that both models perform well in flood simulation and can be used for flood forecasting in semi-humid and semi-arid region.

Distributed Economic MPC for Synergetic Regulation of the Voltage of an Island DC Micro-Grid

In this paper,distributed model predictive control(DMPC) for island DC micro-grids(MG) with wind/photovoltaic(PV)/battery power is proposed,which coordinates all distributed generations(DG) to stabilize the bus voltage together with the insurance of having computational efficiency under a real-time requirement.Based on the feedback of the bus voltage,the deviation of the current is dispatched to each DG according to cost over the prediction horizon.Moreover,to avoid the excessive fluctuation of the battery power,both the discharge-charge switching times and costs are considered in the model predictive control(MPC) optimization problems.A Lyapunov constraint with a time-varying steady-state is designed in each local MPC to guarantee the stabilization of the entire system.The voltage stabilization of the MG is achieved by this strategy with the cooperation of DGs.The numeric results of applying the proposed method to a MG of the Shanghai Power Supply Company shows the effectiveness of the distributed economic MPC.