Fired

Völker, Benjamin; Pfeifer, Marc; Scholl, Philipp M.; Becker, Bernd

doi:10.1145/3408308.3427623

Cited by 10 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the author's experience with using MOGA, the algorithm parametrization was as follows. For both models, the hidden layer's number of neurons was set in the range of [2,30], whereas the number of input features was set in the range of [1,20] for the classification and in the range of [1,30] for the estimation models. A population size of 100 was used, with a number of generations fixed at 100.…”

Section: Moga Design Radial Basis Function Neural Network Resultsmentioning

confidence: 99%

“…NILM algorithms are often classified into event-based algorithms [16][17][18][19] that relate signal state changes to device state changes and eventless algorithms that estimate a global system state using statistical and machine learning approaches [20]. Event-based approaches seek to detect and classify ON/OFF events of electrical devices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Energy Disaggregation Using Multi-Objective Genetic Algorithm Designed Neural Networks

et al. 2022

View full text Add to dashboard Cite

Energy-saving schemes are nowadays a major worldwide concern. As the building sector is a major energy consumer, and hence greenhouse gas emitter, research in home energy management systems (HEMS) has increased substantially during the last years. One of the primary purposes of HEMS is monitoring electric consumption and disaggregating this consumption across different electric appliances. Non-intrusive load monitoring (NILM) enables this disaggregation without having to resort in the profusion of specific meters associated with each device. This paper proposes a low-complexity and low-cost NILM framework based on radial basis function neural networks designed by a multi-objective genetic algorithm (MOGA), with design data selected by an approximate convex hull algorithm. Results of the proposed framework on residential house data demonstrate the designed models’ ability to disaggregate the house devices with excellent performance, which was consistently better than using other machine learning algorithms, obtaining F1 values between 68% and 100% and estimation accuracy values ranging from 75% to 99%. The proposed NILM approach enabled us to identify the operation of electric appliances accounting for 66% of the total consumption and to recognize that 60% of the total consumption could be schedulable, allowing additional flexibility for the HEMS operation. Despite reducing the data sampling from one second to one minute, to allow for low-cost meters and the employment of low complexity models and to enable its real-time implementation without having to resort to specific hardware, the proposed technique presented an excellent ability to disaggregate the usage of devices.

show abstract

Section: Moga Design Radial Basis Function Neural Network Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Energy Disaggregation Using Multi-Objective Genetic Algorithm Designed Neural Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The number of NILM datasets has been increasing over the last years, see [127,128] for recent overviews and [129][130][131] for the most recent published datasets we are aware of. In Table 3, we characterize only the publicly available datasets that have been used in the reviewed studies.…”

Section: Datasetsmentioning

confidence: 99%

Review on Deep Neural Networks Applied to Low-Frequency NILM

et al. 2021

View full text Add to dashboard Cite

This paper reviews non-intrusive load monitoring (NILM) approaches that employ deep neural networks to disaggregate appliances from low frequency data, i.e., data with sampling rates lower than the AC base frequency. The overall purpose of this review is, firstly, to gain an overview on the state of the research up to November 2020, and secondly, to identify worthwhile open research topics. Accordingly, we first review the many degrees of freedom of these approaches, what has already been done in the literature, and compile the main characteristics of the reviewed publications in an extensive overview table. The second part of the paper discusses selected aspects of the literature and corresponding research gaps. In particular, we do a performance comparison with respect to reported mean absolute error (MAE) and F1-scores and observe different recurring elements in the best performing approaches, namely data sampling intervals below 10 s, a large field of view, the usage of generative adversarial network (GAN) losses, multi-task learning, and post-processing. Subsequently, multiple input features, multi-task learning, and related research gaps are discussed, the need for comparative studies is highlighted, and finally, missing elements for a successful deployment of NILM approaches based on deep neural networks are pointed out. We conclude the review with an outlook on possible future scenarios.

show abstract