Demand-side management technology is a key element of the proposed smart grid, which will help utilities make more efficient use of their generation assets by reducing consumers’ energy demand during peak load periods. However, although some modern appliances can respond to price signals from the utility companies, there is a vast stock of older appliances that cannot. For such appliances, utilities must infer what appliances are operating in a home, given only the power signals on the main feeder to the home (i.e., the home’s power consumption must be disaggregated into individual appliances). We report on an in-depth investigation of multi-label classification algorithms for disaggregating appliances in a power signal. A systematic review of this research topic shows that this class of algorithms has received little attention in the literature, even though it is arguably a more natural fit to the disaggregation problem than the traditional single-label classifiers used to date. We examine a multi-label meta-classification framework (RA ${k}$ EL), and a bespoke multi-label classification algorithm (ML ${k}$ NN), employing both time-domain and wavelet-domain feature sets. We test these classifiers on two real houses from the Reference Energy Disaggregation Dataset. We found that the multilabel algorithms are effective and competitive with published results on the datasets.

Toward Non-Intrusive Load Monitoring via Multi-Label Classification

Wireless Sensor Network (WSN) is increasingly popular in the field of micro-environmental monitoring due to its promising capability. However, most systems using WSN for environmental monitoring reported in the literature are developed for specific applications without functions for exploiting user's data processing methods. In this paper, a new system is designed in detail to perform micro-environmental monitoring taking the advantages of the WSN. The application-oriented hardware working style is designed, and the system platform for data acquisition, validation, processing and visualization is systematically presented. Several strategies are proposed to guarantee the system capability in terms of extracting useful information, visualizing events to their authentic time are also described. Moreover, a web-based surveillance subsystem is presented for remote control and monitoring. In addition, the system is extensible for engineers to carry their own data analysis algorithms. Experimental results are to show the path reliability and real-time characteristics, and to display the feasibility and applicability of the developed system into practical deployment.

https://isiarticles.com/bundles/Article/pre/pdf/21633.pdf

Development of an integrated wireless sensor network micro-environmental monitoring system

This essay gives a brief introduction of the Wireless Sensor Network, including its features, application, system structure, the analysis of energy dissipation behavior, the key technologies of the Wireless Sensor Network, and node location methods. What is more, it also analyses existing problems and development orientation in the future.

A survey of Wireless Sensor Networks

Most of the existing medium access control (MAC) protocols for wireless local area networks (WLANs) provide prioritized access by adjusting the contention window sizes or inter-frame spaces for different traffic classes. Those MAC protocols can only provide statistical priority access and limited service differentiation. In this paper, a novel token-based scheduling scheme is proposed for a fully-connected WLAN that supports both voice and data traffic. The proposed scheme can provide guaranteed priority access to voice traffic and, at the same time, provide more precise and quantitative service differentiation for data traffic, which provides great flexibility and facility to the network service provider for service class management. Simulation results demonstrate that the proposed scheme can guarantee a small delay for voice traffic. For data traffic, it can effectively achieve proportional differentiation among different classes, while achieving fair resource sharing within the same class. In addition, compared with a contention based scheme and a centralized polling scheme, the proposed scheme significantly improves the channel utilization by avoiding collisions (in the contention based scheme) and the polling overhead (in the polling scheme). The performance analysis of the proposed scheme is also presented. The accuracy of the analytical results is verified by computer simulations.

/pdf/a-token-based-scheduling-scheme-for-wlans-supporting-voice-2thc05pka0.pdf

A token-based scheduling scheme for WLANs supporting voice/data traffic and its performance analysis

The underdetermined blind source separation (BSS), which based on sparse representation, is discussed in this paper; moreover, some difficulties (or real assumptions) that were left out of consideration before are aimed. For instance, the number of sources, , is unknown, large-scale, or time-variant; the mixing matrix is ill-conditioned. For the proposed algorithm, in order to detect a time-variant mixing matrix, short-time Fourier transform is employed to segment received mixtures. Because is unknown, our algorithm use more estimates to find out the mixing vectors by particle swarm optimizer (PSO); and then, surplus estimates are removed by two proposed processes. However, the estimated accuracy of PSO will affect the correctness of extracting mixing vectors. Consequently, an improved PSO version called the cluster guide PSO (CGPSO) is further proposed according to the character of sparse representation. In simulations, several real assumptions that were less discussed before will be tested. Some representative BSS algorithms and PSO versions are compared with the CGPSO-based algorithm. The advantages of the proposed algorithm are demonstrated by simulation results.

Cluster Guide Particle Swarm Optimization (CGPSO) for Underdetermined Blind Source Separation With Advanced Conditions

Considering the characteristics and location information of nodes in sensor networks, a modified directed transfer model of sensor networks and a new distributed data aggregation model based on "area" are proposed. On the basis of these new models, a novel mixed entropy data compression algorithm based on interval wavelet transforming is proposed for sensor network, according to the characteristics of data in sensor networks and the good performances of wavelet transforming in compression of the data stream. Theoretical analyses and simulation results show that, the above new methods can compress the data stream and reduce the energy costs of nodes in data transferring efficiently for sensor networks. So, it can prolong the lifetime of the whole networks to a greater degree when the above new methods are deployed with those traditional DC (data centric) routing

/pdf/an-algorithm-of-data-aggregation-based-on-data-compression-4iap9j37xo.pdf

An Algorithm of Data Aggregation Based on Data Compression for Sensor Networks

Security schemes of pairwise key establishment, which enable sensors to communicate with each other securely, play a fundamental role in research on security issue in wireless sensor networks. A new kind of cluster deployed sensor networks distribution model is presented, and based on which, an innovative Hierarchical Hypercube model - H(k,u,m,v,n) and the mapping relationship between cluster deployed sensor networks and the H(k,u,m,v,n) are proposed. By utilizing nice properties of H(k,u,m,v,n) model, a new general framework for pairwise key predistribution and a new pairwise key establishment algorithm are designed, which combines the idea of KDC(Key Distribution Center) and polynomial pool schemes. Furthermore, the working performance of the newly proposed pairwise key establishment algorithm is seriously inspected. Theoretic analysis and experimental figures show that the new algorithm has better performance and provides higher possibilities for sensor to establish pairwise key, compared with previous related works.

Researches on scheme of pairwise key establishment for distributed sensor networks

Hypercube multicomputers system has good performances in parallel and distributed computation. With the increasing size of a multicomputers network system, the fault possibility of computers and their links increases. As a result, it becomes very important to seek for better fault-tolerant routing strategies for realizing more effective fault-tolerant routing when lots of faults occur in the multicomputers system. Many significant researches have been done on the fault-tolerant routing design for the hypercube multicomputers system. An innovative fault-tolerant routing algorithm is proposed, in which each node uses a safety path vector (SPV) to record the optimal paths to the other nodes. The safety path vector is an approximate measure of the number and distribution of the faults in the neighborhood and can be setup or updated through the n-1 rounds of information exchanges among neighboring nodes by consuming only n bits storage space. Compared with previous fault-tolerant routing algorithms such as the safety vectors (SVs), extended safety vectors (ESVs), optimal path matrices (OPMs) and extended optimal path matrices (EOPMs), SPVs have stronger ability in tracing optimal paths with equal or less storage cost. Analysis and simulation are given to show the merit of the SPVs.

/pdf/fault-tolerant-routing-based-on-safety-path-vectors-in-19lekjtpe9.pdf

Fault-Tolerant Routing Based on Safety Path Vectors in Hypercube System

DNA Computation for a Category of Special Integer Planning Problem

In this paper, a novel routing algorithm is proposed in which the nodes are clustered into different subnets by their geographical location, and a node with maximum surplus energy is selected as the core node in every subnet. The core node set routes for sensor data by using ant algorithm, which needs only local information to find the optimal path to the sink node distributedly. Analysis and simulation results demonstrate that this new algorithm is of better routing performance for sensor networks compared with previous algorithms such as AC and GITDC.

Wang Lei

Papers

An Algorithm of Data Aggregation Based on Data Compression for Sensor Networks

Researches on scheme of pairwise key establishment for distributed sensor networks

Fault-Tolerant Routing Based on Safety Path Vectors in Hypercube System

DNA Computation for a Category of Special Integer Planning Problem

Subnets based distributed data-centric hierarchical ant routing for sensor networks