Electricity use profiling and forecasting at microgrid level

Mele, Enea; Elias, Charalambos; Ktena, Aphrodite

doi:10.1109/rtucon.2018.8659866

Cited by 9 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the work of [26], yearly forecasts only for non-renewable generation are made for the next 14 years using linear regression, based only on the historical trend of generation. In [27], electricity consumption of a microgrid is forecast using the Nearest Neighbors algorithm for prediction after clustering in business days and weekends with Self-Organizing Maps. However, no comparison with other models is made, and weather data have not been used as input.…”

Section: Related Work and Our Contributionmentioning

confidence: 99%

Multi-Step Energy Demand and Generation Forecasting with Confidence Used for Specification-Free Aggregate Demand Optimization

2021

View full text Add to dashboard Cite

Energy demand and generation are common variables that need to be forecast in recent years, due to the necessity for energy self-consumption via storage and Demand Side Management. This work studies multi-step time series forecasting models for energy with confidence intervals for each time point, accompanied by a demand optimization algorithm, for energy management in partly or completely isolated islands. Particularly, the forecasting is performed via numerous traditional and contemporary machine learning regression models, which receive as input past energy data and weather forecasts. During pre-processing, the historical data are grouped into sets of months and days of week based on clustering models, and a separate regression model is automatically selected for each of them, as well as for each forecasting horizon. Furthermore, the multi-criteria optimization algorithm is implemented for demand scheduling with load shifting, assuming that, at each time point, demand is within its confidence interval resulting from the forecasting algorithm. Both clustering and multiple model training proved to be beneficial to forecasting compared to traditional training. The Normalized Root Mean Square Error of the forecasting models ranged approximately from 0.17 to 0.71, depending on the forecasting difficulty. It also appeared that the optimization algorithm can simultaneously increase renewable penetration and achieve load peak shaving, while also saving consumption cost in one of the tested islands. The global improvement estimation of the optimization algorithm ranged approximately from 5% to 38%, depending on the flexibility of the demand patterns.

show abstract

Section: Related Work and Our Contributionmentioning

confidence: 99%

Multi-Step Energy Demand and Generation Forecasting with Confidence Used for Specification-Free Aggregate Demand Optimization

2021

View full text Add to dashboard Cite

show abstract

“…Conventional forecasting algorithms have been developed taking into account the requirements and operation of the large main power grids of the conventional grid architecture. These are not appropriate for microgrids where the average and peak demand is not only several times smaller than in region-wide areas, but also its electricity consumption presents a much higher volatility [5].…”

Section: Background and Literature Review On Machine Learning Formentioning

confidence: 99%

“…Lately, the efforts concentrate on unsupervised learning neural networks such as Self Organizing Maps (SOMs) [15], [16], on Neural Networks [17] or on hybrid systems that combine both Self Organizing maps (SOMs) and algorithms, such as support vector machines (SVMs) [18] or k-Nearest Neighbors (kNN) [5]. In case of microgrids, however, we need to focus on short and very short-term forecasting.…”

Section: Background and Literature Review On Machine Learning Formentioning

confidence: 99%

“…The amount of data generated by the new grid architecture is increasing dramatically considering the large number of intermediate and lower levels of real time metering and control introduced by new grid entities, such as smart metering, electrical vehicles, and distributed generation and storage. Algorithms that are able to classify these data and use them to train systems are required [5]. For the management of microgrids, the short-term forecasting problem needs to be solved.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Platform for Profiling and Forecasting at Microgrid Level

Mele

Elias

Ktena

2019

Electrical, Control and Communication Engineering

Self Cite

View full text Add to dashboard Cite

The shift towards distributed generation and microgrids has renewed the interest in forecasting algorithms and methods, which need to take into account the advances in information, metering and control technologies in order to address the challenges of forecasting problems. Technologies such as machine learning have been proven useful for short-term electricity load forecasting, especially for microgrids, as they can also take into account several types of historical data and can adapt to changes often encountered in small-scale systems and on a short time scale. In this paper, we present a flexible and easily customized modular toolbox, called Divinus, for electricity use profiling and forecasting in microgrids. Divinus may support a variety of machine learning algorithms for forecasting and profiling that can be used independently or combined. For demonstration purposes, we have implemented Self-Organizing Maps for profiling and k-Neighbors for forecasting. The testing of the platform was based on electricity consumption data of the Euripus campus of the National and Kapodistrian University of Athens in Evia, Greece, from January 2010 till March 2018. The tests that have been carried out so far show that the platform can be easily customized and the algorithms examined yield high accuracy and acceptable mean errors for the case of a university campus energy profile.

show abstract

“…Th e proposed controllable load presented is powered by a hybrid autonomous microgrid that serves as a testbed for the study of aspects of optimal microgrid design [7] and demand side management [8]. It is designed to emulate the actual load curve of a University building for various days of the year, scaled down to the capacity of an existing microgrid consisting of photovoltaic panels (PVs) and lead-acid batteries ( Fig.1).…”

Section: Introductionmentioning

confidence: 99%

Controllable Load for a Microgrid Testbed

Kontantaras¹,

Billas²,

Tsambasis³

2019

Proceedings of the International Scientific Conference - Sinteza 2019

View full text Add to dashboard Cite

Microgrids are a building block of the smart grid facilitating the renewable energy sources penetration and customer involvement in demand side management. As the transition from the conventional to the smart grid progresses, the need for appropriate tools for development and testing increases as well. In this work we propose a design for a controllable load to be used with a microgrid testbed used to study stability, sizing and power quality aspects of microgrids. The smart load consists of commonly used loads controlled by a programmable logic controller to emulate actual load curves of a university building. It has been tested for a period of over a year using an existing autonomous microgrid that consists of photovoltaic panels and batteries. The results demonstrate its capability to emulate successfully actual load curves and its potential in microgrid testing.

show abstract

Electricity use profiling and forecasting at microgrid level

Cited by 9 publications

References 18 publications

Multi-Step Energy Demand and Generation Forecasting with Confidence Used for Specification-Free Aggregate Demand Optimization

Multi-Step Energy Demand and Generation Forecasting with Confidence Used for Specification-Free Aggregate Demand Optimization

Machine Learning Platform for Profiling and Forecasting at Microgrid Level

Controllable Load for a Microgrid Testbed

Contact Info

Product

Resources

About