A hierarchical optimization neural network for large-scale dynamic systems

A recurrent neural network for dynamical hierarchical optimization of nonlinear discrete large-scale systems is presented. The proposed neural network consists of hierarchically structured sub-networks: one coordination sub-network at the upper level and several local optimization sub-networks at the lower level. In particular, the coordination sub-network and the local optimization sub-networks work simultaneously. This feature makes the proposed method outperform in computational efficiency the conventional iterative algorithms where there usually exists an alternately waiting time during the coordination and local optimization processes. Moreover, the state equations of the subsystems of the large-scale system are imbedded into their corresponding local optimization sub-networks. This imbedding technique not only overcomes the difficulty in treating the constraints imposed by the state equations, but also leads to significant reduction in the network size. We present stability analysis to prove that the neural network is asymptotically stable and this stable state corresponds to the optimal solution to the original optimal control problem. Finally, we illustrate the performance of the proposed method by an example.     

Two-level hierarchical control in a large-scale stochastic dynamic system

In this paper a two-level hierarchical control for a resource allocation problem is considered. It is assumed that a coordinator on the upper level and local controllers on the lower level have different information. Soft constraints on control and state variables are taken into account. For a dynamic scalar system and a quadratic performance index, two strategies for the local controllers are proposed.     

A new approach for dynamic modelling of energy consumption in the grinding process using recurrent neural networks

Grinding is a critical machining process because it produces parts of high precision and high surface quality. Due to the semi-artisan production of the wheel, it is not possible to know in advance the performance of the wheel. One of the most useful parameters to characterize the grinding process is the specific grinding energy, which varies with the wear of the grinding wheel during its lifecycle. Thus, it would be useful to model the specific grinding energy in order to get information about the performance of the wheel before buying it. Unlike the typical applications of time series forecasting, in this work, a totally different issue is presented: the prediction of new and complete time series bounded in time without initial or historic values. In this context, an analysis of the effect of the time characteristics and the number of points of the time series on the prediction capabilities of the ANN is presented. The results of the analysis show that 200 points are enough to predict a complete time series up to 2000 mm³/mm of specific volume of material removed. Actually, it is shown that modelling the evolution of the grinding specific energy up to 2000 mm³/mm is possible. The net shows good capability to generalize to new grinding conditions, with errors below 23.65 %, and to new wheel characteristics, with errors below 20.01 %, which are satisfactory from the grinding process perspective.     

Tracking approach in hierarchical optimization of large-scale systems

A synthesis of hierarchical optimization methods for large-scale systems formed by interconnected units is presented using the tracking approach. A general decomposition-coordination structure combining various coordination strategies is proposed. The resulting algorithm, which is very efficient, convivial, and applicable to a large class of problems, is illustrated by a numerical example.     

A novel dynamic modelling approach for parallel mechanisms analysis

A novel approach (recursive matrix method), which is used for kinematic and dynamic analysis of a 3-DOF parallel mechanism with revolute actuators, is established in this paper. The active links of the mechanism are actuated by three electric motors and have three independent motions. Knowing the evolution of movable platform, first we develop the positions, velocities and accelerations of all elements of the mechanism. An inverse dynamic problem is solved using the principle of virtual work. Finally, recursive relations and graphs for the torques of three actuators are determined. It showed the efficiency of the proposed method by the example.     

A hierarchical approach to dynamic optimization of power systems

The power production system in The Netherlands is characterized by a relatively large number of thermal power-generating units, the presence of autonomous power stations, a strong national grid and a fluctuating daily load. The calculation of the most economic production policy for one or two days ahead, given all cost functions and the predicted demand for electricity, leads to a nonlinear mixed-integer optimization problem. A real solution can only be found at the expense of rather unrealistic values for computing time and memory. To cope with this problem, a hierarchical approach is described that is able to solve problems with up to 100 units and 24 periods.     

A flexible,object-centric approach for business process modelling

Mainstream business process modelling techniques often promote a design paradigm wherein the activities that may be performed within a case, together with their usual execution order, form the backbone on top of which other aspects are anchored. This Fordist paradigm, while effective in standardised and production-oriented domains, breaks when confronted with processes in which case-by-case variations and exceptions are the norm. We contend that the effective design of flexible processes calls for a substantially different modelling paradigm. Motivated by requirements from the human services domain, we explore the hypothesis that a framework consisting of a small set of coordination concepts, combined with established object-oriented modelling principles, provides a suitable foundation for designing highly flexible processes. Several human service delivery processes have been designed using this framework, and the resulting models have been used to realise a system to support these processes in a pilot environment.     

A dynamic programming approach for finding shortest chains in a fuzzy network

Graph theory has numerous applications to problems in systems analysis, operations research, transportation, and economics. In many cases, however, some aspects of a graph-theoretic problem may be uncertain. For example, the vehicle travel time or vehicle capacity on a road network may not be known exactly. In such cases, it is natural to make use of fuzzy set theory to deal with the uncertainty. Here, we are concerned with finding shortest chains in a graph with fuzzy distance for every edge. We propose a dynamic programming approach to solve the fuzzy shortest chain problem using a suitable ranking method. By using MATLAB, two illustrative examples are worked out to demonstrate the proposed algorithm.     

Neural network modelling and control strategies for a pH process

The control of a pH process using neural networks is examined. The neural network as a universal approximator is used to good effect in this nonlinear problem, as is shown in the simulation results. In the modelling task, the dynamics of the process was carefully examined to determine a suitable structure for the net. In particular, a multilayer net consisting of two single hidden layers was constructed to reflect the Wiener model of the pH process. This led to much simpler training compared to similar modelling attempts by other researchers. For the control task, two schemes were simulated. In one approach, a net was used to deal with the static nonlinearity to achieve control over a wide working range. The dynamic controller used was the PID, with its parameters tuned on a relay auto-tuner. This control design was compared with the strong acid equivalent method. In the second approach, a direct model reference adaptive neural network control scheme was proposed. The training procedure uses the more efficient least squares algorithm developed by Loh and Fong.     

A network flow based approach for network selection in dynamic spectrum access networks

In this paper, we present a network flow based approach for dynamic network and channel selection for secondary users in dynamic spectrum access networks. Most approaches in the current literature on dynamic spectrum access networks do not consider dynamic network and channel selection. We present a network flow framework for network selection. We show that our approach can enable re-assignment of networks to secondary users and also re-assignment of channels to secondary users within the same network. The assignments and re-assignments take into account, the interference caused to primary users, the price each secondary user is willing to pay and the quality of service (QoS) obtained by each secondary user. We obtain a bound for the maximum number of re-assignments.     

Minimax program control for the approach process in a two-level hierarchical discrete dynamical system

We consider a dynamical system consisting of three objects whose dynamics is given by vector linear discrete recurrent equations. The system contains two levels of managerial decision making, basic and secondary, that have different operational criteria and are united by informational and managerial connections defined in advance. For the dynamical system in question, we propose a mathematical formalization in the form of solving a multistage problem of two-level hierarchical minimax program control over the approach process with incomplete information and give a general scheme for its solution.     

A fuzzy-based customer clustering approach with hierarchical structure for logistics network optimization

Customer clustering is an essential step to reduce the complexity of large-scale logistics network optimization. By properly grouping those customers with similar characteristics, logistics operators are able to reduce operational costs and improve customer satisfaction levels. However, due to the heterogeneity and high-dimension of customers’ characteristics, the customer clustering problem has not been widely studied. This paper presents a fuzzy-based customer clustering algorithm with a hierarchical analysis structure to address this issue. Customers’ characteristics are represented using linguistic variables under major and minor criteria, and then, fuzzy integration method is used to map the sub-criteria into the higher hierarchical criteria based on the trapezoidal fuzzy numbers. A fuzzy clustering algorithm based on Axiomatic Fuzzy Set is developed to group the customers into multiple clusters. The clustering validity index is designed to evaluate the effectiveness of the proposed algorithm and find the optimal clustering solution. Results from a case study in Anshun, China reveal that the proposed approach outperforms the other three prevailing algorithms to resolve the customer clustering problem. The proposed approach also demonstrates its capability of capturing the similarity and distinguishing the difference among customers. The tentative clustered regions, determined by five decision makers in Anshun City, are used to evaluate the effectiveness of the proposed approach. The validation results indicate that the clustered results from the proposed method match the actual clustered regions from the real world well. The proposed algorithm can be readily implemented in practice to help the logistics operators reduce operational costs and improve customer satisfaction levels. In addition, the proposed algorithm is potential to apply in other research domains.     

Automated instructional design for CSCL: A hierarchical task network planning approach

In Computer Supported Collaborative Learning (CSCL), one of the most important tasks for instructional designers is to define scenarios that foster group learning. Such scenarios, defined as Units of Learning (UoLs), comprise different components and are organized according to pedagogical approaches to orchestrate group learning processes. Examples of UoL components are learning objects, student roles, student characteristics (e.g., background, preferences, learning styles, etc.), instructional/learning goals, and activities, among others. Thus, the instructional design (ID) of a proper UoL for CSCL is a complex task that requires practice and experience. This is particularly true when designing, developing, adapting, and customizing UoLs, taking into consideration different instructional/learning goals and individual preferences of students. This paper therefore proposes using a Hierarchical Task Network (HTN) planning approach to automate and optimize the tasks of designers. To accomplish that, we define an initial CSCL scenario as “an ID task” and “a set of information related to students and the domain to be taught.” Then we propose a model that formally describes ID for CSCL as HTN planning, where the initial CSCL scenario is adapted and refined according to student needs. In this model, the ID strategies are defined as hierarchical tasks and methods into a planning domain definition, and the initial CSCL scenario is defined as a planning problem definition. To validate our approach, we develop a CSCL courseware generator that (i) helps designers to set up an initial CSCL scenario; (ii) automatically generates a personalized UoL based on a given initial scenario; and (iii) supports the adaptation of UoLs.     

Gaussian process approach for modelling of nonlinear systems

Parametric modelling principals such as neural networks, fuzzy models and multiple model techniques have been proposed for modelling of nonlinear systems. Research effort has focused on issues such as the selection of the structure, constructive learning techniques, computational issues, the curse of dimensionality, off-equilibrium behaviour, etc. To reduce these problems, the use of non-parametrical modelling approaches have been proposed. This paper introduces the Gaussian process (GP) prior approach for the modelling of nonlinear dynamic systems. The relationship between the GP model and the radial basis function neural network is explained. Issues such as selection of the dimension of the input space and the computation load are also discussed. The GP modelling technique is demonstrated on an example of the nonlinear hydraulic positioning system.     

Compromise: An effective approach for the hierarchical design of structural systems

In this paper the use of the compromise decision support problem in hierarchical design of structural systems is described. In the past we had postulated the hierarchical decision support problem for use in hierarchical design. In this paper, for the first time, the mathematical template that supports the underlying precepts of hierarchical design in the context of the Decision Support Problem Technique is presented. A structural example that demonstrates the efficacy of the approach is included.     

具有动态补偿能力的神经网络模型及其在动态系统建模中的应用

本文在多层前馈神经网络模型基础上，引入误差动态反馈环节，从而形成一种新的具有动态补偿能力的神经网络模型。新模型的训练利用反向传播原理实现。采用该模型对非线性动态系统进行建模时，能显著提高建模精度，特别是在网络模型工作时，对新出现的输出误差具有动态补偿能力，文中给出了新网络模型的结构和学习算法，最后是仿真实例。     

StreamTune: dynamic resource scheduling approach for workload skew in video data center

Video surveillance applications need video data center to provide elastic virtual machine (VM) provisioning. However, the workloads of the VMs are hardly to be predicted for online video surveillance service. The unknown arrival workloads easily lead to workload skew among VMs. In this paper, we study how to balance the workload skew on online video surveillance system. First, we design the system framework for online surveillance service which consists of video capturing and analysis tasks. Second, we propose StreamTune, an online resource scheduling approach for workload balancing, to deal with irregular video analysis workload with the minimum number of VMs. We aim at timely balancing the workload skew on video analyzers without depending on any workload prediction method. Furthermore, we evaluate the performance of the proposed approach using a traffic surveillance application. The experimental results show that our approach is well adaptive to the variation of workload and achieves workload balance with less VMs.     

A neural network-based approach for dynamic quality prediction in a plastic injection molding process

This paper presents an innovative neural network-based quality prediction system for a plastic injection molding process. A self-organizing map plus a back-propagation neural network (SOM-BPNN) model is proposed for creating a dynamic quality predictor. Three SOM-based dynamic extraction parameters with six manufacturing process parameters and one level of product quality were dedicated to training and testing the proposed system. In addition, Taguchi’s parameter design method was also applied to enhance the neural network performance. For comparison, an additional back-propagation neural network (BPNN) model was constructed for which six process parameters were used for training and testing. The training and testing data for the two models respectively consisted of 120 and 40 samples. Experimental results showed that such a SOM-BPNN-based model can accurately predict the product quality (weight) and can likely be used for various practical applications.     

Calibration and validation of a simulation-based dynamic traffic assignment model for a large-scale congested network

Deployment of a simulation-based dynamic traffic assignment (DTA) model requires calibration of a large number of demand and supply input parameters. In this paper, we present a data-intensive framework for deployment, calibration, and validation of a simulation-based DTA model of Melbourne, Australia as a large-scale congested network. The model consists of 55,719 links and 24,502 nodes and simulates almost 2.1 million commuters in a 4-h morning peak period. We propose a machine learning based technique to classify and calibrate the traffic flow fundamental diagrams against empirical data obtained from a large number of freeway loop detectors across the network. An optimization framework for estimating the time-dependent origin-destination (TDOD) demand is also presented. To enhance the quality of the TDOD demand estimation, we apply a departure time profiling technique to account for the spatial differences between OD pairs. The paper also demonstrates the impact of adaptive driving on the quality of the DTA calibration. A comparison between the simulated and observed link volumes over 1,250 locations across the entire network shows that the calibration procedure generates an approximately 30% improvement in the root mean square error (RMSE). The impact of pedestrians and cyclists on the vehicular traffic is also implicitly considered in the central business district (CBD) area to improve underestimation of the simulated travel times. Validation results suggest that the calibrated DTA model successfully replicates traffic patterns in the network and support the future applications of the model for various transportation operations and planning purposes.