Smart Sensing of Loads in an Extra Low Voltage DC Pico-Grid Using Machine Learning Techniques

Abstract

Aiming at the rising number of dc appliances and the growing interest in their monitoring systems, this paper describes the injection of intelligence into dc pico-grids that are made up of "dumb" appliances and loads. Due to reality of economic, dc appliances and loads are usually low in cost and lack intelligence and communication features for effective monitoring and management. This paper proposes a smart sensor design for dc pico-grid with the use of a single sensor multiple loads and states detection in monitoring the "dumb" appliances. This eliminates the need to have intelligence and communication features for every appliance. With the smart sensor, several such smart dc pico-grids can be bundled into bigger scale of smart nano-grid or micro-grid. In addition to knowing how much energy or power the pico-grid is using; the smart sensor also provides load disaggregation and state-change detection. The states of the loads can be learnt and detected via the signatures and features obtained from the transient state or the steady state of the entire grid's current waveform. Computational intelligence techniques, k-Nearest Neighbours, K-Means clustering and other algorithms are used in the system for loads classification and state-change detection. Working together with the software in the smart sensor are hardware implementation of low cost operational amplifiers and logic gates; these hardware help to share the burden on the controller and release resources for the controller to perform more advanced processes. Experimental results are presented to demonstrate the operation of the smart sensor in dc pico-grid.

Design of Intelligent Perception Module Based on Wireless Sensor Network and Basketball Sports Attitude

“…Reference [17] proposed an abnormal activity detection means based on a simple transducer, but this means also did not consider the effect of duration on the model establishment, and the accuracy decreased to a certain extent. Reference [18] proposed a detailed classification scheme for the swimming propulsion mode of fish according to the different body parts used for swimming propulsion. Reference [19] proposed the "two-dimensional wave plate theory" through the subsurface flow theory and linearized boundary conditions, which treats fish as a thin plate and is used to analyze the hydrodynamic characteristics of bonito fish.…”

A smart residential security assisted load management system using hybrid cryptography

“…The major problems exist in load management, billing strategies, and security. Detection of load states was executed using the k-means clustering algorithm to group the input signals and then use the k-Nearest Neighbor (k-NN) algorithm for the classification of load states [23]. The conventional procedure was followed for these methods, and the results of classification were based on the clustered data.…”

Load Disaggregation Using One-Directional Convolutional Stacked Long Short-Term Memory Recurrent Neural Network

“…µ in (9) is the computed mean and σ 2 (10) is the computed variance. The largest gradient, igrad,max is computed by finding the largest difference between subsequent data points i̅ (11) and range, R, is the difference between the maximum and minimum values of the window (12).…”

“…q.yang-thee@newcastle.ac.uk, wai.l.woo@northumbria.ac.uk, t.logenthiran@newcastle.ac.uk electrical grids [10,11]. As the ELV dc loads get smaller, the dc power grids are also shrinking from micro to nano to picogrid [12]. There has not been much attention paid on dc, thus motivating the research on state detection and anomalies warning in dc grids.…”