A Scalable Real-Time Non-Intrusive Load Monitoring System for the Estimation of Household Appliance Power Consumption

Smart-meter technology advancements have resulted in the generation of massive volumes of information introducing new opportunities for energy services and data-driven business models. One such service is non-intrusive load monitoring (NILM). NILM is a process to break down the electricity consumption on an appliance level by analyzing the total aggregated data measurements monitored from a single point. Most prominent existing solutions use deep learning techniques resulting in models with millions of parameters and a high computational burden. Some of these solutions use the turn-on transient response of the target appliance to calculate its energy consumption, while others require the total operation cycle. In the latter case, disaggregation is performed either with delay (in the order of minutes) or only for past events. In this paper, a real-time NILM system is proposed. The scope of the proposed NILM algorithm is to detect the turning-on of a target appliance by processing the measured active power transient response and estimate its consumption in real-time. The proposed system consists of three main blocks, i.e., an event detection algorithm, a convolutional neural network classifier and a power estimation algorithm. Experimental results reveal that the proposed system can achieve promising results in real-time, presenting high computational and memory efficiency.

Download Full-text

NILM techniques applied to a real-time monitoring system of the electricity consumption

ACTA IMEKO ◽

10.21014/acta_imeko.v10i2.1054 ◽

2021 ◽

Vol 10 (2) ◽

pp. 139

Author(s):

Barbara Cannas ◽

Sara Carcangiu ◽

Daniele Carta ◽

Alessandra Fanni ◽

Carlo Muscas ◽

...

Keyword(s):

Power Consumption ◽

Monitoring System ◽

Event Detection ◽

Electricity Consumption ◽

Low Frequency ◽

Detection Algorithm ◽

Detection Approach ◽

Consumption Data ◽

Load Monitoring ◽

Using Data

Non-Intrusive Load Monitoring (NILM) allows providing appliance-level electricity consumption information and decomposing the overall power consumption by using simple hardware (one sensor) with a suitable software. This paper presents a low-frequency NILM-based monitoring system suitable for a typical house. The proposed solution is a hybrid event-detection approach including an event-detection algorithm for devices with a finite number of states and an auxiliary algorithm for appliances characterized by complex patterns. The system was developed using data collected at households in Italy and tested also with data from BLUED, a widely used dataset of real-world power consumption data. Results show that the proposed approach works well in detecting and classifying what appliance is working and its consumption in complex household load dataset.

Download Full-text

A Prototype Quantitative Precipitation Estimation Algorithm for Operational S-Band Polarimetric Radar Utilizing Specific Attenuation and Specific Differential Phase. Part II: Performance Verification and Case Study Analysis

Journal of Hydrometeorology ◽

10.1175/jhm-d-18-0070.1 ◽

2019 ◽

Vol 20 (5) ◽

pp. 999-1014 ◽

Cited By ~ 9

Author(s):

Stephen B. Cocks ◽

Lin Tang ◽

Pengfei Zhang ◽

Alexander Ryzhkov ◽

Brian Kaney ◽

...

Keyword(s):

Real Time ◽

Heavy Precipitation ◽

Estimation Algorithm ◽

Differential Phase ◽

Specific Attenuation ◽

Quantitative Precipitation Estimation ◽

Precipitation Estimation ◽

Bias Ratio ◽

Using Data ◽

Precipitation Events

Abstract The quantitative precipitation estimate (QPE) algorithm developed and described in Part I was validated using data collected from 33 Weather Surveillance Radar 1988-Doppler (WSR-88D) radars on 37 calendar days east of the Rocky Mountains. A key physical parameter to the algorithm is the parameter alpha α, defined as the ratio of specific attenuation A to specific differential phase KDP. Examination of a significant sample of tropical and continental precipitation events indicated that α was sensitive to changes in drop size distribution and exhibited lower (higher) values when there were lower (higher) concentrations of larger (smaller) rain drops. As part of the performance assessment, the prototype algorithm generated QPEs utilizing a real-time estimated and a fixed α were created and evaluated. The results clearly indicated ~26% lower errors and a 26% better bias ratio with the QPE utilizing a real-time estimated α as opposed to using a fixed value as was done in previous studies. Comparisons between the QPE utilizing a real-time estimated α and the operational dual-polarization (dual-pol) QPE used on the WSR-88D radar network showed the former exhibited ~22% lower errors, 7% less bias, and 5% higher correlation coefficient when compared to quality controlled gauge totals. The new QPE also provided much better estimates for moderate to heavy precipitation events and performed better in regions of partial beam blockage than the operational dual-pol QPE.

Download Full-text

Malaria elimination in India requires additional surveillance mechanisms

Journal of Public Health ◽

10.1093/pubmed/fdab106 ◽

2021 ◽

Author(s):

Manju Rahi ◽

Payal Das ◽

Amit Sharma

Keyword(s):

Real Time ◽

Malaria Elimination ◽

Surveillance Data ◽

Surveillance Systems ◽

Malaria Surveillance ◽

Aggregated Data ◽

Malaria Burden ◽

The Core ◽

Reporting Systems ◽

Geographic Regions

Abstract Malaria surveillance is weak in high malaria burden countries. Surveillance is considered as one of the core interventions for malaria elimination. Impressive reductions in malaria-associated morbidity and mortality have been achieved across the globe, but sustained efforts need to be bolstered up to achieve malaria elimination in endemic countries like India. Poor surveillance data become a hindrance in assessing the progress achieved towards malaria elimination and in channelizing focused interventions to the hotspots. A major obstacle in strengthening India’s reporting systems is that the surveillance data are captured in a fragmented manner by multiple players, in silos, and is distributed across geographic regions. In addition, the data are not reported in near real-time. Furthermore, multiplicity of malaria data resources limits interoperability between them. Here, we deliberate on the acute need of updating India’s surveillance systems from the use of aggregated data to near real-time case-based surveillance. This will help in identifying the drivers of malaria transmission in any locale and therefore will facilitate formulation of appropriate interventional responses rapidly.

Download Full-text

Real-time 2D–3D door detection and state classification on a low-power device

SN Applied Sciences ◽

10.1007/s42452-021-04588-3 ◽

2021 ◽

Vol 3 (5) ◽

Author(s):

João Gaspar Ramôa ◽

Vasco Lopes ◽

Luís A. Alexandre ◽

S. Mogo

Keyword(s):

Low Power ◽

Real Time ◽

Object Classification ◽

Semantic Segmentation ◽

Detection Algorithm ◽

Power Device ◽

Indoor Environments ◽

State Classification ◽

Segmentation Algorithms ◽

Indoor Spaces

AbstractIn this paper, we propose three methods for door state classification with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work offline, in low-powered computers as the Jetson Nano, in real-time with the ability to differentiate between open, closed and semi-open doors. We use the 3D object classification, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classification networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classification algorithm running in real-time on a low-power device.

Download Full-text

Smart-Building Applications: Deep Learning-Based, Real-Time Load Monitoring

IEEE Industrial Electronics Magazine ◽

10.1109/mie.2020.3023075 ◽

2020 ◽

pp. 0-0

Author(s):

Halil Cimen ◽

Emilio Jose Palacios-Garcia ◽

Morten Kolbaek ◽

Nurettin Cetinkaya ◽

Juan C. Vasquez ◽

...

Keyword(s):

Deep Learning ◽

Real Time ◽

Smart Building ◽

Load Monitoring

Download Full-text

High-precision roll attitude estimation of decoupled canards relative to the projectile body using bipolar hall-effect sensors

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189718 ◽

2021 ◽

pp. 1-9

Author(s):

Tingting Yin ◽

Zhong Yang ◽

Youlong Wu ◽

Fangxiu Jia

Keyword(s):

Hall Effect ◽

Real Time ◽

High Precision ◽

Solution Method ◽

Estimation Method ◽

Estimation Algorithm ◽

Attitude Estimation ◽

Fuzzy Algorithms ◽

Positioning Method ◽

Hall Effect Sensors

The high-precision roll attitude estimation of the decoupled canards relative to the projectile body based on the bipolar hall-effect sensors is proposed. Firstly, the basis engineering positioning method based on the edge detection is introduced. Secondly, the simplified dynamic relative roll model is established where the feature parameters are identified by fuzzy algorithms, while the high-precision real-time relative roll attitude estimation algorithm is proposed. Finally, the trajectory simulations and grounded experiments have been conducted to evaluate the advantages of the proposed method. The positioning error is compared with the engineering solution method, and it is proved that the proposed estimation method has the advantages of the high accuracy and good real-time performance.

Download Full-text

Full-Observable Three-Phase State Estimation Algorithm Applied to Electric Distribution Grids

Energies ◽

10.3390/en12071327 ◽

2019 ◽

Vol 12 (7) ◽

pp. 1327 ◽

Cited By ~ 7

Author(s):

Thiago Soares ◽

Ubiratan Bezerra ◽

Maria Tostes

Keyword(s):

State Estimation ◽

Real Time ◽

Distribution Systems ◽

Phase State ◽

Reactive Power ◽

Estimation Algorithm ◽

Load Flow ◽

Electrical Network ◽

The Real ◽

Three Phase

This paper proposes the development of a three-phase state estimation algorithm, which ensures complete observability for the electric network and a low investment cost for application in typical electric power distribution systems, which usually exhibit low levels of supervision facilities and measurement redundancy. Using the customers´ energy bills to calculate average demands, a three-phase load flow algorithm is run to generate pseudo-measurements of voltage magnitudes, active and reactive power injections, as well as current injections which are used to ensure the electrical network is full-observable, even with measurements available at only one point, the substation-feeder coupling point. The estimation process begins with a load flow solution for the customers´ average demand and uses an adjustment mechanism to track the real-time operating state to calculate the pseudo-measurements successively. Besides estimating the real-time operation state the proposed methodology also generates nontechnical losses estimation for each operation state. The effectiveness of the state estimation procedure is demonstrated by simulation results obtained for the IEEE 13-bus test network and for a real urban feeder.

Download Full-text