Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis

Peng, Yayu; Wang, Yishen; Lu, Xiao; Li, Haifeng; Shi, Di; Wang, Zhiwei; Li, Jie

doi:10.1109/isgt-asia.2019.8881343

Cited by 33 publications

(18 citation statements)

References 19 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Laurinec et al (2019) introduced two unsupervised ensemble learning methods include the newly proposed density-clustering based and bootstrap aggregating based to assess the performance of prediction on clustered or aggregated load. Peng et al (2019) focused on STLF for small-and-medium enterprise and residential customers at the aggregate level. Various methods, from the linear regression to deep learning, are used to obtain the aggregated load forecast.…”

Section: Literature Reviewmentioning

confidence: 99%

A combined effective time series model based on clustering and whale optimization algorithm for forecasting smart meters electricity consumption

Rostum

Moustafa

Ziedan

et al. 2021

COMPEL

View full text Add to dashboard Cite

Purpose The current challenge for forecasting smart meters electricity consumption lies in the uncertainty and volatility of load profiles. Moreover, forecasting the electricity consumption for all the meters requires an enormous amount of time. Most papers tend to avoid such complexity by forecasting the electricity consumption at an aggregated level. This paper aims to forecast the electricity consumption for all smart meters at an individual level. This paper, for the first time, takes into account the computational time for training and forecasting the electricity consumption of all the meters. Design/methodology/approach A novel hybrid autoregressive-statistical equations idea model with the help of clustering and whale optimization algorithm (ARSEI-WOA) is proposed in this paper to forecast the electricity consumption of all the meters with best performance in terms of computational time and prediction accuracy. Findings The proposed model was tested using realistic Irish smart meters energy data and its performance was compared with nine regression methods including: autoregressive integrated moving average, partial least squares regression, conditional inference tree, M5 rule-based model, k-nearest neighbor, multilayer perceptron, RandomForest, RPART and support vector regression. Results have proved that ARSEI-WOA is an efficient model that is able to achieve an accurate prediction with low computational time. Originality/value This paper presents a new hybrid ARSEI model to perform smart meters load forecasting at an individual level instead of an aggregated one. With the help of clustering technique, similar meters are grouped into a few clusters from which reduce the computational time of the training and forecasting process. In addition, WOA improves the prediction accuracy of each meter by finding an optimal factor between the average electricity consumption values of each cluster and the electricity consumption values for each one of its meters.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A combined effective time series model based on clustering and whale optimization algorithm for forecasting smart meters electricity consumption

Rostum

Moustafa

Ziedan

et al. 2021

COMPEL

View full text Add to dashboard Cite

show abstract

“…Otherwise, the modeled behavior may be partial. In addition, databases may differ in predictability which increases the difficulty of comparing and analyzing accuracy results [3,40]. To avoid this issue, Table 1 includes a measure of approximate entropy (ApEn) as a measure of unpredictability.…”

Section: Data Analysis 221 Load Datamentioning

confidence: 99%

Use of Available Daylight to Improve Short-Term Load Forecasting Accuracy

et al. 2020

View full text Add to dashboard Cite

This paper introduces a new methodology to include daylight information in short-term load forecasting (STLF) models. The relation between daylight and power consumption is obvious due to the use of electricity in lighting in general. Nevertheless, very few STLF systems include this variable as an input. In addition, an analysis of one of the current STLF models at the Spanish Transmission System Operator (TSO), shows two humps in its error profile, occurring at sunrise and sunset times. The new methodology includes properly treated daylight information in STLF models in order to reduce the forecasting error during sunrise and sunset, especially when daylight savings time (DST) one-hour time shifts occur. This paper describes the raw information and the linearization method needed. The forecasting model used as the benchmark is currently used at the TSO’s headquarters and it uses both autoregressive (AR) and neural network (NN) components. The method has been designed with data from the Spanish electric system from 2011 to 2017 and tested over 2018 data. The results include a justification to use the proposed linearization over other techniques as well as a thorough analysis of the forecast results yielding an error reduction in sunset hours from 1.56% to 1.38% for the AR model and from 1.37% to 1.30% for the combined forecast. In addition, during the weeks in which DST shifts are implemented, sunset error drops from 2.53% to 2.09%.

show abstract

“…by photovoltaic systems) and market, being a powerful tool that can be exploited by households to maximize their self-sufficiency. However, residential demand is very volatile and quickly fluctuates over time; for this reason, this task is much more challenging than long-term forecasting or aggregated short-term forecasting [3].…”

Section: Introductionmentioning

confidence: 99%

Short-Term Energy Consumption Forecasting at the Edge: A Federated Learning Approach

Savi

Olivadese

2021

IEEE Access

View full text Add to dashboard Cite

Residential short-term energy consumption forecasting plays an essential role in modern decentralized power systems. The rise of innovative prediction methods able to handle the high volatility of users' electrical load has posed the basis to accomplish this task. However these methods, which mostly rely on Artificial Neural Networks, require that a huge amount of users' fine-grained sensitive consumption data are centrally collected to train a generalized forecasting model, with implications on privacy and scalability. This paper proposes an innovative architecture specifically designed to overcome this need. By exploiting Federated Learning and Edge Computing capabilities, many Long Short-Term Memory (LSTM) models are locally trained by different users based on their own historical energy consumption samples. Such models are then aggregated by a specific-purpose node to build a generalized model that is re-distributed for improved forecasting at the edge. For better forecasting, our proposed local training procedure takes as input relevant features related to calendar (i.e., hour, weekday and average consumption of previous days) and weather conditions (i.e., clustered apparent temperature), and the architecture can group users according to consumption similarities (using K-means) or socioeconomic affinities. We thoroughly evaluate the approach through simulations, showing that it can lead to similar forecasting performance than a stateof-the-art centralized solution in terms of Root Mean Square Error (RMSE), but with up to an order of magnitude lower training time and up to 50 times less exchanged data when samples are recorded at finer granularity than one hour. Nonetheless, it keeps sensitive data local and therefore guarantees users' privacy.

show abstract

Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis

Cited by 33 publications

References 19 publications

A combined effective time series model based on clustering and whale optimization algorithm for forecasting smart meters electricity consumption

A combined effective time series model based on clustering and whale optimization algorithm for forecasting smart meters electricity consumption

Use of Available Daylight to Improve Short-Term Load Forecasting Accuracy

Short-Term Energy Consumption Forecasting at the Edge: A Federated Learning Approach

Contact Info

Product

Resources

About