Dynamic Profiling and Optimization Methodologies for Sensor Networks

To reduce the complexity associated with application-specific tuning of sensor-based systems, dynamic profiling enables an accurate view of the application behavior, such that the network can be reoptimized at runtime in response to changing application behavior or environmental conditions. However, dynamic profiling must be able to accurately capture application behavior without incurring significant runtime overheads. We present several profiling methods for dynamically monitoring sensor-based platforms and analyze the associated network traffic, energy, and code impacts.

Dynamic program optimization is increasingly important for achieving good runtime performance. A key issue is how to select which code to optimize. One approach is to dynamically detect traces, long sequences of instructions spanning multiple methods, which are likely to execute to completion. Traces are easy to optimize and have been shown to be a good unit for optimization. The paper reports on a new approach for dynamically detecting, creating and storing traces in a Java virtual machine. We first describe four important criteria for a successful trace strategy: good instruction stream coverage, low dispatch rate, cache stability, and optimizability of traces. We then present our approach based on branch correlation graphs. A branch correlation graph stores information about the correlation between pairs of branches, as well as additional state information. We present the complete design for an efficient implementation of the system, including a detailed discussion of the trace cache and profiling mechanisms. We have implemented an experimental framework to measure the traces generated by our approach in a direct-threaded Java VM (SableVM) and we present experimental results to show that the traces we generate meet the design criteria.

Dynamic program optimization is increasingly important for achieving good runtime performance. A key issue is how to select which code to optimize. One approach is to dynamically detect traces, long sequences of instructions spanning multiple methods, which are likely to execute to completion. Traces are easy to optimize and have been shown to be a good unit for optimization. The paper reports on a new approach for dynamically detecting, creating and storing traces in a Java virtual machine. We first describe four important criteria for a successful trace strategy: good instruction stream coverage, low dispatch rate, cache stability, and optimizability of traces. We then present our approach based on branch correlation graphs. A branch correlation graph stores information about the correlation between pairs of branches, as well as additional state information. We present the complete design for an efficient implementation of the system, including a detailed discussion of the trace cache and profiling mechanisms. We have implemented an experimental framework to measure the traces generated by our approach in a direct-threaded Java VM (SableVM) and we present experimental results to show that the traces we generate meet the design criteria.

To reason about programs, dynamic optimizers and analysis tools use sampling to collect a dynamic call graph (DCG). However, sampling has not achieved high accuracy with low runtime overhead. As object-oriented programmers compose increasingly complex programs, inaccurate call graphs will inhibit analysis and optimizations. This paper demonstrates how to use static and dynamic control flow graph (CFG) constraints to improve the accuracy of the DCG. We introduce the frequency dominator (FDOM), a novel CFG relation that extends the dominator relation to expose static relative execution frequencies of basic blocks. We combine conservation of flow and dynamic CFG basic block profiles to further improve the accuracy of the DCG. Together these approaches add minimal overhead (1%) and achieve 85% accuracy compared to a perfect call graph for SPEC JVM98 and DaCapo benchmarks. Compared to sampling alone, accuracy improves by 12 to 36%. These results demonstrate that static and dynamic control-flow information offer accurate information for efficiently improving the DCG.KeywordsBasic BlockCorrection AlgorithmControl Flow GraphCall GraphCall SiteThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A dynamic real-time optimization (D-RTO) methodology has been developed and applied to a batch reactor where polymer grafting reactions take place. The objective is to determine the on-line reactor temperature profile that minimizes the batch time while meeting terminal constraints on the overall conversion rate and grafting efficiency. The methodology combines a constrained dynamic optimization method and a moving horizon state estimator within a closed-loop control. The results show very good performances in terms of state estimation, constraints fulfillment and computation load.

A combination of two 2-D sensor networks is proposed as a dynamic surface profile sensor network for biomimicing applications. A surface acoustic wave device fabricated on a polyvinylidine difluoride substrate has been investigated as the elementary 1-D bending curvature sensor used in the network. The device was tested under an injected signal and it shows the variation in amplitude and phase angle of output signal with respect to the injected signal in response to the bending curvature. These dual outputs provide opportunity to make an intelligent sensor with self error limit determination capability. Finally, a network of such sensors is proposed as a dynamic surface profile sensor

This article presents a new scheme for dynamic data optimization in IoT (Internet of Things)-assisted sensor networks. The various components of IoT assisted cloud platform are discussed. In addition, a new architecture for IoT assisted sensor networks is presented. Further, a model for data optimization in IoT assisted sensor networks is proposed. A novel Membership inducing Dynamic Data Optimization Membership inducing Dynamic Data Optimization (MIDDO) algorithm for IoT assisted sensor network is proposed in this research. The proposed algorithm considers every node data and utilized membership function for the optimized data allocation. The proposed framework is compared with two stage optimization, dynamic stochastic optimization and sparsity inducing optimization and evaluated in terms of reliability ratio, coverage ratio and sensing error. Data optimization was performed based on the availability of cloud resource, sensor energy, data flow volume and the centroid of each state. It was inferred that the proposed MIDDO algorithm achieves an average performance ratio of 76.55%, reliability ratio of 94.74%, coverage ratio of 85.75% and sensing error of 0.154.

Storage management in a rolling horizon Dynamic Real-Time Optimization (DRTO) methodology for a non-concentrating solar thermal plant for low temperature heat production

With the increasing complexity of networked cooperative detection environment, new targets appear and leave in the detection area, and the mobility of targets is increasing. The emergence of sensors makes the sensors in the sensor network have certain motion characteristics. These uncertainties increase the complexity of the problem. At the same time, the dynamic selection of sensor resources needs to consider the needs of different priority tasks, platform survival risk, sensor cost and other factors. In view of these problems to be solved, based on the qualitative synthesis theory of predictive control and stochastic dynamic programming optimization theory, the dynamic sensor selection decision theory and method based on multi-step forward decision are explored. This paper studies the dynamic sensor strategy based on multi-step forward decision scheduling, and carries out the research on the optimization decomposition method of sensor selection under different structural characteristics, the dynamic optimization method of sensor selection under complex and uncertain environment, and the multi-objective optimization method of dynamic sensor selection under heterogeneous targets, so as to explore a new way of dynamic sensor selection algorithm design and performance analysis under networked collaborative tracking A new way. The research of dynamic target tracking algorithm in mobile sensor networks has important theoretical and engineering significance to improve the resource efficient utilization and the overall target tracking performance of sensor networks.

The aim of the paper is to show how dynamic optimization techniques could be used in creating System Dynamics models. There are two possible applications of optimization in the context of System Dynamics methodology. The first application concerns the calibration of System Dynamics models - one can introduce computational technique which is the extension of the Gauss-Newton for the calibration of models described by algebraic equations. The second application is related to the problem of creating proper decision rules which usually are present in System Dynamics models. In that case we substitute original decision rules by control variables and then define an optimal control problem whose performance index is used to verify the effectiveness of a particular decision rule. Having the solution of the optimal control problem we use it to modify the decision rule or its parameters. We show the application of the proposed approach to System Dynamics models describing criminal activities: one model is related to drugs prevalence, the other one is based on relations known from epidemics models and can be treated as a generic model which can be used to describe various criminal activities.

This paper presents a methodology for the dynamic optimization of hybrid processes. The proposed methodology considers the most general class of hybrid dynamic systems consisting of a finite set of dynamic subsystems, in which sequence and duration is not established a priori. The objective is to determine the optimal sequence of dynamic subsystems, the transition times from one subsystem to another, and the optimal profile of the control laws. LARES-PR algorithm for the solution of dynamic optimization problems (Irizarry, R. Chem. Eng. Sci. 2005, 60, 5663-5681) is extended to solve this type of problem. The efficiency and robustness of the method is demonstrated with a set of challenging benchmark problems. The proposed methodology is then applied to a multicomponent nanoparticle alloy synthesis. This prototype model is a very challenging one in which a mechanism switch not changes not only the model structure but also the solution methodology for each mode. For instance, in one phase, the particles grown by coalescence are modeled using discretized population-balance models. When a mechanism switch is induced, a new type of particle is introduced into the system. The subsequent growth of the binary system is modeled using the Monte Carlo method. The proposed methodology can handle this situation effectively. In general, the method is very robust, is simple to implement, and can be used to solve a wide range of hybrid optimization instances with different types of complexities.

The rapidly evolving scenario around cellular networks, Internet of Things (IoT), and the associated services ecosystem has generated a wide range of expectations for the future networks. However, the unavailability of sufficient bandwidth and severe interference prohibit the existing commercially used radio-frequency (RF) bands from supporting some of these services. In this respect, the millimeter wave (mmWave)-based systems are seen as promising alternatives for supporting various high data rate enhanced mobile broadband (eMBB) services. Nevertheless, the adverse wave propagation characteristics in these bands and the resulting media access control (MAC) layer problems of beam blockage restrict these systems from operating in a reliable manner. Therefore, in this article, we propose a MAC layer-based approach of control delegation to tackle the problem of beam blockage. The mechanism uses policy-based relinquishment of access point (AP) control from the default AP to other AP capable member nodes to improve node visibility and alleviate the blockage scenario without requiring any additional network infrastructure. To account for the dynamic behavior of the network, a discrete-time Markov decision process (MDP)-based model is proposed. It uses a dynamic optimization methodology to accommodate multiple reconfigurable performance metrics, which can then be adjusted to cater to different performance criteria. Using computer simulations, we evaluate the effectiveness of our proposed solution for some alternate static and dynamic control policies. Our simulation results show that our proposed solution can significantly reduce the blockage in a network while satisfying a variety of performance objectives over different classes of indoor IoT scenarios.

In this paper, passive wireless sensor network technology is used to conduct in‐depth research and analysis on the monitoring of the in‐transit health status of railway transportation. Safety detection sensors, train communication networks, and other onboard devices organically constitute a train sensor network with comprehensive state sensing, information aggregation, and business collaboration. First, this paper analyzes the three‐layer architecture of the sensing layer, network layer, and application layer of the train operation status safety detection sensor network. Based on analyzing the feasibility of Ethernet application in an onboard communication network, ring, multiring, and ladder‐type sensor network structure schemes are designed. Next, the real‐time performance and reliability of various sensor network structures are analyzed. First, the characteristics of bandwidth demand, priority, and importance of information transmission of each monitoring object are analyzed; then, the system utility function is established according to the bandwidth usage efficiency and communication demand of information transmission of each monitoring object; finally, the bandwidth allocation optimization model is solved by using a particle swarm optimization algorithm, and the remaining bandwidth resources are dynamically rationed on demand while ensuring the complete transmission of basic information of each monitoring object. Rail transit technology has profoundly affected and changed the travel and lifestyle of residents in the new era and will provide strong infrastructure support for the smooth advancement of new urbanization construction and development strategies. The remaining bandwidth resources are dynamically allocated on the premise of ensuring the complete transmission of basic information of each monitoring object. In summary, this paper presents a complete study on the optimal allocation of resources for wireless sensor networks dedicated to rail transit condition monitoring, starting from the perspectives of routing protocol optimization, data fusion rate optimization, and bandwidth dynamic allocation optimization to achieve the efficient use of limited resources. The achieved research results enrich the research content in the field of wireless monitoring of rail transit system conditions at home and abroad in a certain sense and will also provide theoretical and empirical support for practical practitioners, managers, and scholars of service condition monitoring of rail transit systems.

Contributors

Important topics in Land-Atmosphere (L-A) feedback research are water and energy balances and heterogeneities of fluxes at the land-surface and in the atmospheric booundary layer. To target these questions, the Land-Atmosphere Feedback Observatory (LAFO) has been installed in Southwest Germany. The instrumentation allows comprehensive and high-resolution measurements from the bedrock to the lower free troposphere. Grouped in three components: atmosphere, soil and land-surface and vegetation, the LAFO observation strategy aims for simultaneous measurements in all three compartments. For that the LAFO sensor synergy contains lidar systems to measure the atmospheric key variables humidity, temperature and wind. At the land-surface eddy covariance stations operated to record the energy distribution of radiation, sensible, latent and ground heat fluxes. With a water and temperature sensor network the soil water and temperature is monitored in the agricultural investigation area. The observations in LAFO are organized in operational measurements and intensive observation periods (IOPs). Operational measurements aim for long timeseries dataset to investigate statistics as we present as example the correlation between mixing layer height and surface fluxes. The potential of IOPs is demonstrated with a 24 hour case study with dynamic and thermodynamic profiles with lidar as well as a surface layer observation with the scanning differential absorption lidar to relate atmospheric humidity patterns to soil water structures. Both long-term observations and IOPs are important for improving the representation of L-A feedbacks in climate and numerical weather prediction models.