Empirical Characterization, Modeling, and Analysis of Smart Meter Data

Barker, Sean; Kalra, Sandeep; Irwin, David; Shenoy, Prashant

doi:10.1109/jsac.2014.2332107

Cited by 27 publications

(20 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature [10] discusses the experience of smart meter data based on the characterization, modeling and data analysis based model. [11] introduces that by using clustering algorithm to deals the smart meter data realizes the resolution of load.…”

Section: The Methods Of Forecasting Power Loadmentioning

confidence: 99%

On the Research of the Smart Grid Load Forecasting Cloud Platform Architecture

Zhai¹

2017

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract. Load forecasting is making calculations or predictions of a future event or condition based on analysis or study of historical data, events or observations. With the development of smart grid, smart meter is also increasing largely, which can generate metering data per 15 mins, and there comes a huge amount of metering data. Thus such huge amount of data leads to some challenges in data processing. This paper introduces the meaning of studying load forecasting, and recommends current relevant research. Then, the cloud platform architecture, the key technologies based cloud and current relevant research for load forecasting based on cloud in smart grid is discussed. Finally it introduces the related load forecasting services based on the cloud platform architecture in smart grid. After all, there is a conclusion of this paper.

show abstract

Section: The Methods Of Forecasting Power Loadmentioning

confidence: 99%

On the Research of the Smart Grid Load Forecasting Cloud Platform Architecture

Zhai¹

2017

Advances in Computer Science Research

View full text Add to dashboard Cite

show abstract

“…AMI data have been intensively utilized to learn demand features for better understanding, predicting, and incentivizing demand. For instance, Barker et al (2014) captured key characteristics of each load type (e.g. microwave, laundry machines) from the data and proposed a method to retrieve load types by time of day.…”

Section: Literature Reviewmentioning

confidence: 99%

User-centric interdependent urban systems: Using time-of-day electricity usage data to predict morning roadway congestion

Zhang

Qian

2018

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Urban systems are interdependent as individuals' daily activities engage using those urban systems at certain time of day and locations. There may exist clear spatial and temporal correlations among usage patterns across all urban systems. This paper explores such a correlation among energy usage and roadway congestion. We propose a general framework to predict congestion starting time and congestion duration in the morning using the time-of-day electricity use data from anonymous households with no personally identifiable information. We show that using time-of-day electricity data from midnight to early morning from 322 households in the City of Austin, can make reliable prediction of congestion starting time of several highway segments, at the time as early as 2am. This predictor significantly outperforms a time-series predictor that uses only real-time travel time data up to 6am. We found that 8 out of the 10 typical electricity use patterns have statistically significant affects on morning congestion on highways in Austin. Some patterns have negative effects, represented by an early spike of electricity use followed by a drastic drop that could imply early departure from home. Others have positive effects, represented by a late night spike of electricity use possible implying late night activities that can lead to late morning departure from home. Figure 1: Interdependency of some urban systems: their system user patterns are inter-related both temporally and spatially congestion occurs in the afternoon peak for Segment 1, but generally not in the morning. Segment 2 typically has morning peak congestion, but not in the afternoon. Segment 3 has both morning and afternoon congestion in most of days. Figure 2(a) plots their respective time-varying travel times (in seconds) on a typical weekday (Jan 08, 2014). The free-flow traffic/passenger flow in the early morning does not exhibit clear patterns before it transitions to being congested (also known as traffic break-down). For all the three segments, the travel time stays flat (namely in free flow) until traffic break-down that causes an instantaneous drop in speed. Real-time monitoring the speed or travel time does not necessarily help predict the exact time of traffic break-down, nor would historical data help as much due to day-to-day variation. If we define "congestion starting time" as the time when traffic speed reduces by 50% over 10 minutes, Figure 2(b) shows the congestion starting time of those three road segments for 155 weekdays in 2014. For segment 3, the morning congestion starting time varies by 30-60 mins from day to day. The day-to-day variation of morning congestion patterns on both segments 1 and 2 are less than segment 1. Morning congestion occurs for about 20% of days on segment 1. Congestion started with 6:10-6:20am for most days on segment 2, but there are nine days when its congestion started after 6:30am. To sum up, daily congestion patterns are difficult to predict by only monitoring real-time traffic flow because traffic break-down is...

show abstract

“…We also describe how various kinds of electrical loads that are typically used by their users. Our characterization builds on prior work on empirically characterizing electrical loads [4,3].…”

Section: Characterizing Loadsmentioning

confidence: 99%

“…Typically, common devices, such as TVs, refrigerators, and computers, are only rated (often conservatively) based on their maximum power, but include no details of how the device consumes power over time. A recent effort [3,4] analyzed empirical data gathered from a large number of residential loads to argue that only the simplest loads, such as light bulbs, exhibit a simple on-off behavior and demonstrates that most loads exhibit more complex exponential decays or growth, bounded min-max, and cyclic patterns. While this work proposed more complex analytic models to describe load behavior, it did not propose any algorithms or approaches to derive (or construct) such models automatically.…”

Section: Introductionmentioning

confidence: 99%

Non-intrusive model derivation

Iyengar

Irwin

Shenoy

2016

Proceedings of the Seventh International Conference on Future Energy Systems

Self Cite

View full text Add to dashboard Cite

A variety of energy management and analytics techniques rely on models of the power usage of a device over time. Unfortunately, the models employed by these techniques are often highly simplistic, such as modeling devices as simply being on with a fixed power usage or off and consuming little power. As we show, even the power usage of relatively simple devices exhibits much more complexity than a simple on and off state. To address the problem, we present a Non-Intrusive Model Derivation (NIMD) algorithm to automate modeling of residential electric loads using concepts from power systems, statistics, and machine learning. NIMD automatically derives a compact representation of the time-varying power usage of any residential electrical load, including both the device's energy usage and its pattern of usage over time. Such models are useful for a variety of analytics techniques, such as Non-Intrusive Load Monitoring, that have relied on simple on-off models in the past. We evaluate the accuracy of our models by comparing them with both actual ground truth data, and against models that have been designed manually by human experts. We show that models derived via NIMD are comparable in accuracy to models built by experts and closely approximate the ground truth data.

show abstract

Empirical Characterization, Modeling, and Analysis of Smart Meter Data

Cited by 27 publications

References 21 publications

On the Research of the Smart Grid Load Forecasting Cloud Platform Architecture

On the Research of the Smart Grid Load Forecasting Cloud Platform Architecture

User-centric interdependent urban systems: Using time-of-day electricity usage data to predict morning roadway congestion

Non-intrusive model derivation

Contact Info

Product

Resources

About