Lihong Ren

An Intelligent Self-Organization Scheme for the Internet of Things

The Internet of Things (IoT) is emerging as the major trend in shaping the development of the next generation of information networks. The challenges of the enormous, dynamic, incredibly diverse and high complexity of the IoT urgently require novel self-organization scheme because most of the existing distributed self-organization schemes cannot be directly applied to it. In this paper, we propose an intelligent self-organizing scheme (ISOS) for the IoT inspired by the endocrine regulating mechanism. For each node in the network, an autonomous area is established, where the node can effectively interact with its peers and perform self-control according to its own status and dynamic circumstance in a decentralized infrastructure. By introducing the hormone mechanism as the medium for information transmission and data sharing, the nodes can collaborate with each other and work in a cooperative way. Through adjusting the release procedure of the hormones, the ability to effectively detect service randomly generated can also be guaranteed in the probabilistic partially-working IoT. Simulation results verify the performance of the proposed mechanism that entitles the IoT to the ability of maintaining its status in a globally stable status, while effectively discovering the random service requests in a resource-critical configuration. The ISOS would be of great significance for the practical implementation of the IoT.

A Bioinspired Multilayered Intelligent Cooperative Controller for Stretching Process of Fiber Production

The stretching process is one of the key sections in fiber production, which is decisive to the quality of the final fiber products. Such a process raises high requirements on the control of the rollers with proper stretching ratios, and the large number of rollers with their special characteristics and the demand for synchronous running usually make the design of a good control scheme difficult. In this paper, a novel bioinspired multilayered intelligent cooperative controller (BMLICC) is proposed to provide a control plan for the interlinked rollers by organizing them into unified stretching units. Based on the multilayer regulation networks of neuroendocrine system in the human body, a networked controller structure is established. It consists of several components like rollers, distributed controllers, communication paths, and conversion units. The rollers in the same unit can exchange the working information rapidly to implement simultaneous response and cooperation. The stretching ratio can be kept stable and has strong resistance against the external disturbances on the stretching system. Both computer-simulation- and device-based experimental results demonstrate that the stretching unit with the proposed BMLICC can maintain its stretching ratio and effectively resist the external disturbances. This is beneficial to improve the performance of the stretched precursors and, furthermore, produce fibers with high quality. The proposed BMLICC can be easily extended to productions with multiple stretching units or industrial processes with similar mechanical structures for better control quality.

Data-Driven Cooperative Intelligent Controller Based on the Endocrine Regulation Mechanism

A data-driven mechanism can achieve effective control by utilizing the online/offline data of the target system, although its performance has not been tuned to a better level. The endocrine regulating mechanism in the human body establishes a rapid responding system to maintain the balance of the body, which can be mathematically derived and therefore provide an inspiration for optimizing the industrial controller. In this paper, a novel data-driven cooperative intelligent controller inspired by the regulating principle of the endocrine system in the human body is proposed. The data-driven component of the proposed controller optimizes the controller parameters by collecting and processing runtime data of the target system. The endocrine regulation-inspired enhancing component tunes the intensity of control signals adaptively. Both the components are further organized by an adaptive distributor so that their behaviors can be regulated dynamically. A dynamic tension control system for acrylic fiber production is taken to verify the performance of the proposed controller. Simulation results show that the proposed controller can realize effective control on systems with unknown or varying models, meanwhile featuring rapid response and effective regulation against external disturbance.

An immune system-inspired rescheduling algorithm for workflow in Cloud systems

Due to the increasing functionality and complexity of Cloud computing systems, the resource failures, including unpredictable crash and performance degradation about resource availability, are inevitable. So a failure-aware resource provisioning algorithm that is capable of offering corresponding strategies immediately after failures happened is paramount. In this paper, an immunological mechanism inspired rescheduling algorithm is proposed for workflow in Cloud systems (IRW). There are four units to imitate the immune system in the IRW algorithm. The surveillance unit monitors possible faults for each Virtual Machine (VM) in resources pool. Once a resource fault is detected, the response unit is triggered to search an appropriate strategy either in the memory unit or in the learning unit for rescheduling the available resources. The available resources are clustered into multiple clusters to narrow the search scope in the learning unit. If none of available VMs can meet the Quality of Services, a new VM is created for the faulty resource. To verify the effectiveness of the proposed IRW, a series of simulation experiments are conducted on both real world workflows with different structures and randomly generated workflows. The results demonstrate that the IRW is able to effectively provide corresponding rescheduling strategies for resource failures and the experiments also highlight the better performance of the proposed approach than that of corresponding algorithms under different situations.

Degeneration Recognizing Clonal Selection Algorithm for Multimodal Optimization

In this paper, a computing speed improvement for the clonal selection algorithm (CSA) is proposed based on a degeneration recognizing (DR) method. The degeneration recognizing clonal selection algorithm (DR-CSA) is designed for solving complex engineering multimodal optimization problems. On each iteration of CSA, there is a large amount of eliminated solutions which are usually neglected. But these solutions do contain the knowledge of the nonoptimal area. By storing and utilizing these data, the DR-CSA is aimed to identify part of the new population as degenerated and eliminate them before the evaluation operation, so that a number of evaluation times can be avoided. This pre-elimination operation is able to save computing time because the evaluation is the main reason for the time cost in the complex engineering optimization problem. Experiments on both test function and a real-world engineering optimization problem (wet spinning coagulating process) are conducted. The results show that the proposed DR-CSA is as accurate as regular CSA and is effective in reducing a considerable amount of computing time.

A weighted heteroscedastic Gaussian process modeling via particle swarm optimization

Gaussian process regression (GPR) algorithm has good adaptability to deal with high dimensional, small sample, and nonlinear problems. The standard GPR algorithm assumes constant noise power throughout the sampling process. However, different sample points are often affected by different degrees of noise, which will reduce the modeling accuracy and increase uncertainty of the prediction in the standard GPR algorithm. In this paper, we introduce a weighting strategy to the standard GPR algorithm, and propose a weighted GPR (W-GPR) algorithm. Different from the standard GPR algorithm, the proposed W-GPR algorithm assigns a weight to each observation. In addition, in order to optimize hyper-parameters in the GPR modeling process, the particle swarm optimization (PSO) algorithm is used instead of the traditional gradient method. By means of a numerical example and one chemical process example, the W-GPR algorithm significantly reduces the uncertainty of the prediction, and improves the accuracy of the model. Further, simulation results demonstrate that the W-GPR model optimized by the PSO algorithm achieves a more accurate and reliable estimation result than the traditional gradient method.

Immune-inspired self-adaptive collaborative control allocation for multi-level stretching processes

For multi-level stretching processes in large industrial production lines exhibiting complicated non-linear dynamics and interconnected control variables, a novel immune-based self-adaptive collaborative control allocation (ICCA) method is proposed to deal with the tension output fluctuations and some uncertainties. The allocation strategies for coupled stretching ratios at different levels are implemented in the ICCA to achieve the best stable tension performance. The stretching ratio of single level is determined by minimizing the error between the proposed reference model and the actual stretching plant. Compared with distributed control for individual sub-processes, the reversing dynamic programming on each level is introduced which is operated from the last level sequentially. The gain-tuning strategy is directly driven by the optimization result, namely, the self-adaptive allocation algorithm, is just the execution level for operating the solutions of reversing optimization. The optimization and self-adaptive controller are designed to cope with the presence of actuator imperfections and tension tracking fluctuations in the neighboring non-linear process. In addition, the criterion is an important factor in evaluating the control performance of this system, which consists of the objective function. Simulation results show that the ICCA method exhibits better performances than the centralized PI control and the cytokine network-inspired cooperative control in dealing with the desired tension tracking and fluctuations reducing by the control algorithm.

An Immune System-Inspired Reconfigurable Controller

Based on the biological immune mechanism, a design approach for the immune reconfigurable controller (IRC) is proposed. Using four units to imitate the immune systems surveillance process, response process, memory mechanism, and self-learning process, respectively, the IRC is capable of actuator fault detection and fault-tolerant control for multi-input multioutput systems. Meanwhile, in order to further improve the control performance, an online optimization process with the multiobjective clonal selection algorithm is designed. To verify its effectiveness, the IRC is applied to the coagulation bath of polyacrylonitrile carbon fiber production line. Comparison experiments with conventional PID and reconfigurable model-based predictive controller control schemes are conducted. The simulation results demonstrate that the IRC can rapidly eliminate the fluctuation due to the actuator fault and guarantees the stability of the coagulation bath. In addition, the IRC has the ability of quick response to the same failure as well as unknown faults.

Adaptive Sampling Algorithm with Endocrine Regulation Mechanism for Wireless Sensor Network

Studies in Wireless sensor network (WSN) have been extensively focused on developing different medium access control (MAC) and routing protocols instead of ignoring that on data acquisition and processing. Unfortunately, setting the sampling frequency of nodes in WSN will unreasonably cause low precision, and even result in premature failure of the network. Aimed at solving this problem, an adaptive sampling algorithm based on endocrine regulation mechanism in WSN is proposed. The algorithm uses hormone information to control the nodes in working state or resting state, and adjusts collecting frequency dynamically. When the targets change slowly, the nodes send inhibitory hormone to reduce the collecting frequency and extend lifetime of the network. Conversely, while the targets change rapidly, the nodes send trophic hormone to increase the sampling frequency and ensure the sampling accuracy. Finally, the results of the simulation experiments show that the algorithm can effectively prolong the lifetime of network without losing sampling accuracy.

A weighted Gaussian process regression for multivariate modelling

This paper develops three weighted Gaussian process regression (GPR) approaches for multivariate modelling. Taking into account weighted strategy in the traditional univariate GPR, the heteroscedastic noise problem has been solved. The present paper extends the univariate weighted GPR algorithm to the multivariate case. Considering the correlation and weight between data, as well as the correlation between outputs, the covariance functions of the proposed approaches are formulated. By formulating different process noise mechanisms, the proposed methods can solve different multivariate modelling problems. The effectiveness of the proposed algorithm is demonstrated by a numerical example as well as a six-level drawing of a Carbon fiber example.