the explosive increase in volume, velocity, variety, and veracity of data generated by distributed and heterogeneous nodes such as IoT and other devices, continuously challenge the state of art in big data processing ...
详细信息
A number of models for neural content-based news recommendation have been proposed. However, there is limited understanding of the relative importances of the three main components of such systems (news encoder, user ...
详细信息
the paper proposes an IoT controlled platform to remotely monitor and control appliances in the residential sector. An IP-based synchronized wireless mesh network is implemented through IoT hardware (based on a NodeMC...
详细信息
ISBN:
(纸本)9789897585128
the paper proposes an IoT controlled platform to remotely monitor and control appliances in the residential sector. An IP-based synchronized wireless mesh network is implemented through IoT hardware (based on a NodeMCU) and Google Sheets to monitor and schedule the operation of aggregated domestic refrigerators under a Model Predictive Control (MPC) scheme. Benefits afforded by the proposed technique are investigated through experimental trials from VonShef 13/291 (50W), iGENIX IG 3920 (55W) and Russell Hobbs RHCLRF17B (50W) domestic refrigerators sited in three different domestic locations in the city of Lincoln, UK. Results demonstrate the ability to monitor and control widely distributed networks of refrigerators and adaptively schedule the appliances to reduce peak operational loads and facilitate Demand Side Response (DSR). Further widespread expansion of the proposed technique would allow for a rapidly deployed regional DSR strategy to aid grid stability. Ultimately the underlying principles also could be used for the co-ordinated scheduling of other distributed appliances and equipment, both domestic and industrial.
Nowadays we experience a paradigm shift in our society, where every item around us is becoming a computer facilitating life-changing applications like self-driving cars, tele-medicine, precision agriculture or virtual...
详细信息
ISBN:
(纸本)9781450391436
Nowadays we experience a paradigm shift in our society, where every item around us is becoming a computer facilitating life-changing applications like self-driving cars, tele-medicine, precision agriculture or virtual reality. On one hand, for the execution of such resource demanding applications we need powerful IT facilities. On the other hand, the requirements often include latencies below 100 ms or even below 10 ms - what is called "tactile internet". To facilitate low latency computation has to be placed in the vicinity of the end users by utilizing the concept of Edge Computing. In this talk we explain the challenges of Edge systems in combination with tactile internet. We discuss the recent problems of geographically distributed machine learning applications and novel approaches to balance competing priorities like the energy efficiency and the staleness of the machine learning models. Available failure resilience mechanisms designed for Cloud computing or generic distributedsystems cannot be applied to Edge systems due to timeliness, hyper heterogeneity and resource scarcity. therefore, we discuss a novel machine learning based mechanism that evaluates the failure resilience of a service deployed redundantly on the edge infrastructure. Our approach learns the spatiotemporal dependencies between edge server failures and combines them withthe topological information to incorporate link failures by utilizing the concept of the Dynamic Bayesian Networks (DBNs). eventually, we infer the probability that a certain set of servers fails or disconnects concurrently during service runtime.
In this paper, a data-driven event-triggered output-feedback control approach is proposed to solve the problem of adaptive optimal output regulation for uncertain discrete-time linear systems when only the output info...
详细信息
Blockchain networks use consensus mechanisms so participants can exchange transactions without the need to rely on a trusted third party. Consensus mechanisms using Proof of Work burn significant energy to select a bl...
详细信息
In this work we present a novel genetic programming based iterative improvement approach for hardware/software cosynthesis of distributed embedded systems. the approach starts from a ready solution which is an embryo ...
详细信息
ISBN:
(纸本)9789897584893
In this work we present a novel genetic programming based iterative improvement approach for hardware/software cosynthesis of distributed embedded systems. the approach starts from a ready solution which is an embryo of a genotype. Other nodes in the genotypes are chromosomes. the chromosomes contain system refinement options. the final solution is obtained after evolution process and mapping genotype to phenotype. Unlike existing genetic programming iterative improvement methodologies our algorithm starts from randomly generated system. therefore the search space is not constrained by any initial condition. It is also easier for the algorithm to escape local minima of optimizing parameters.
the proceedings contain 495 papers. the topics discussed include: improved edge detection algorithm for canny operator;overview of spectrum sharing technology;EEG classification based on deep learning;research on topo...
ISBN:
(纸本)9781665422079
the proceedings contain 495 papers. the topics discussed include: improved edge detection algorithm for canny operator;overview of spectrum sharing technology;EEG classification based on deep learning;research on topology control method of dynamic space-based TT&C network based on time-space graph;u-net fundus retinal vessel segmentation method based on multi-scale feature fusion;resolve from flight conflicts at the same flight level;research on information transmission capability evaluation of information processing system based on fuzzy mathematics comprehensive evaluation method;short-term wind power forecasting model based on stacking fusion learning;another algorithm to determine if it is a state transfer matrix;dose nonuniformity estimation method for scientific test of cobalt source device;research on the overall transformation scheme of the first access network of dispatching data network of state grid Weifang power supply company;deep Kalman-based trajectory estimation of moving target from satellite images;adaptive event-triggered cooperative tracking control with full-state constraints for a class of nonlinear time-varying multi-agent systems;and simulation modeling and software implementation of optical fiber and space channel in quantum secure communication.
the use of the Federated Learning paradigm could be disruptive in robotics, where data are naturally distributed among teams of agents and centralizing them would increase latency and break privacy. Unfortunately ther...
详细信息
ISBN:
(纸本)9798400704734
the use of the Federated Learning paradigm could be disruptive in robotics, where data are naturally distributed among teams of agents and centralizing them would increase latency and break privacy. Unfortunately there are a lack of robot oriented framework for federated learning that use state of the art machine learning libraries. ROS2 (Robot Operating systems) is a standard de-facto in robotics for building up teams of robots in a multi-node fully distributed manner. In this paper we presents the integration of ROS2 with PyTorch allowing an easy training of a global machine learning model starting from a set of local datasets. We present the architecture, the used methodology and finally we discuss the experimentation results over a well-known public dataset.
the development of power engineering, under current conditions, is aimed at the use of distributed generation plants in power supply systems located in immediate proximity from power consumers. the article deals with ...
详细信息
ISBN:
(纸本)9789897585128
the development of power engineering, under current conditions, is aimed at the use of distributed generation plants in power supply systems located in immediate proximity from power consumers. the article deals with power supply system with turbo generator plant and high power energy storage unit. Description of a power supply system model with turbo generator plant, energy storage unit and asynchronous load is provided, and modeling results of power supply system transition to the isolated operating mode. the model of the power supply system under study was carried out in the MATLAB environment using the Simul ink and SimPowerSvstems simulation packages. In work is a description of the PSS model used IN ith DG plant and ESU, as well as the simulation results. based on the computer simulation results the conclusion, that use of prognostic controllers turbo generator plant allows improving the damping properties of the system when switching to an isolated mode of operation.
暂无评论