Multi-Sequence LSTM-RNN Deep Learning and Metaheuristics for Electric Load Forecasting
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Short term electric load forecasting plays a crucial role for utility companies, as it allows for the efficient operation and management of power grid networks, optimal balancing between production and demand, as well as reduced production costs. As the volume and variety of energy data provided by building automation systems, smart meters, and other sources are continuously increasing, long short-term memory (LSTM) deep learning models have become an attractive approach for energy load forecasting. These models are characterized by their capabilities of learning long-term dependencies in collected electric data, which lead to accurate prediction results that outperform several alternative statistical and machine learning approaches. Unfortunately, applying LSTM models may not produce acceptable forecasting results, not only because of the noisy electric data but also due to the naive selection of its hyperparameter values. Therefore, an optimal configuration of an LSTM model is necessary to describe the electric consumption patterns and discover the time-series dynamics in the energy domain. Finding such an optimal configuration is, on the one hand, a combinatorial problem where selection is done from a very large space of choices; on the other hand, it is a learning problem where the hyperparameters should reflect the energy consumption domain knowledge, such as the influential time lags, seasonality, periodicity, and other temporal attributes. To handle this problem, we use in this paper metaheuristic-search-based algorithms, known by their ability to alleviate search complexity as well as their capacity to learn from the domain where they are applied, to find optimal or near-optimal values for the set of tunable LSTM hyperparameters in the electrical energy consumption domain. We tailor both a genetic algorithm (GA) and particle swarm optimization (PSO) to learn hyperparameters for load forecasting in the context of energy consumption of big data. The statistical analysis of the obtained result shows that the multi-sequence deep learning model tuned by the metaheuristic search algorithms provides more accurate results than the benchmark machine learning models and the LSTM model whose inputs and hyperparameters were established through limited experience and a discounted number of experimentations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures












Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Bouktif et al. [43] optimized the LSTM hyperparameters in their prediction model using GA and PSO.”
From Prediction of Heat and Cold Loads of Factory Mushroom Houses Based on EWT Decomposition (2023) · cites this paper as [43]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“In particular, LSTM networks, deep learning variations proposed by Hochreiter and Schmidhuber [8], were designed specially to learn long-term dependencies present in sequential data.”
BackgroundKennedy, J., & Eberhart, R. (2002) · Proceedings of ICNN'95 - International Conference on Neural Networks · doi:10.1109/icnn.1995.488968 · Cited by 58,192
Particle swarm optimization: An overview
Poli, R., Kennedy, J., & Blackwell, T. (2007) · Swarm Intelligence · doi:10.1007/s11721-007-0002-0 · Cited by 21,101 · cited 1×
“It is evolved by imitating the social behavior of a school of fishes and a flock of birds that collectively search for the best locations and are likely to move close to an optimum fitness function [39].”
BackgroundA new optimizer using particle swarm theory
Eberhart, R., & Kennedy, J. (2002) · MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science · doi:10.1109/mhs.1995.494215 · Cited by 16,067 · cited 1×
“Particle swarm optimization developed by Kennedy and Eberhart in 1995 was inspired by the social behavior [38].”
Method(2012) · Cited by 8,009
Neural Networks and the Bias/Variance Dilemma
Geman, S., Bienenstock, E., & Doursat, R. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.1 · Cited by 3,578 · cited 1×
“A deeper neural network with more layers will have a greater capacity, but more layers can eventually result in a decrease in the performance due to high variance and model overfitting and thus a reduced generalization power for the electricity dataset [43].”
BackgroundTime series analysis forecasting and control
Janacek, G. (2010) · Journal of Time Series Analysis · doi:10.1111/j.1467-9892.2009.00643.x · Cited by 2,584 · cited 1×
“Traditional linear statistical models such as autoregressive (AR), moving average (MA) and autoregressive integrated moving average (ARIMA) have remained the baseline for time-series predictions, with extensive use in several industrial applications [3,4].”
BackgroundA Comparative Analysis of Selection Schemes Used in Genetic Algorithms
Goldberg, D. E., & Deb, K. (1991) · Foundations of Genetic Algorithms · doi:10.1016/b978-0-08-050684-5.50008-2 · Cited by 2,407 · cited 1×
“A large tournament value results in a stronger selective pressure, and the population can converge to a faster solution, at the cost of the solution being potentially not as good [44].”
BackgroundEngineering Optimization: An Introduction with Metaheuristic Applications
Yang, X. (2010) · Wiley eBooks · doi:10.1002/9780470640425 · Cited by 1,248 · cited 1×
“In our case, metaheuristics will select from an infinite number of configurations the appropriate lags as well as the best parameter setting for an accurate time series analysis using deep learning [13].”
BackgroundApplied Time Series Econometrics
(2004) · Cambridge University Press eBooks · doi:10.1017/cbo9780511606885 · Cited by 1,196 · cited 1×
“If the selected lags are not relevant, this may unnecessarily increase the curse of dimensionality, slow down the training process, and lead to model overfitting [41].”
Background
Research works printed but not linked: 5
- Defilippo, S.B., Neto, G.G., and Hippert, H.S. (September, January 31). Short-term load forecasting by artificial neural networks specified by genetic algorithms–a simulation study over a Brazilian dataset. Proceedings of the XIII Simposio Argentino de Investigación Operativa (SIO)—JAIIO 44, Rosario, Santa Fe, Argentina.
- Brownlee, J. (2011). Clever Algorithms: Nature-Inspired Programming Recipes, Lulu Press.
- Holland, J.H., and Goldberg, D. (1989). Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley.
- Holland, J.H. (1975). Adaptation in Natural and Artificial Systems, University of Michigan Press.
- Meyer-Baese, A., and Schmid, V.J. (2014). Pattern Recognition and Signal Analysis in Medical Imaging, Elsevier.
Cited by
Fan, Z., Yan, Z., & Wen, S. (2023) · Sustainability · doi:10.3390/su151813493 · Cited by 346
“Bouktif et al. [90] emphasized the importance of short-term electric load forecasting for efficient power grid management.”
BackgroundArtificial Intelligence Techniques in Smart Grid: A Survey
Omitaomu, O. A., & Niu, H. (2021) · Smart Cities · doi:10.3390/smartcities4020029 · Cited by 371
Multimodal Emotion Recognition using Deep Learning
Abdullah, S. M. S. A., Ameen, S. Y. A., M. Sadeeq, M. A., & Zeebaree, S. (2021) · Journal of Applied Science and Technology Trends · doi:10.38094/jastt20291 · Cited by 347
“In [60], to boost the efficiency of the multimodal fusion, a new algorithm and new architecture using the kernel matrix and a deep neural network are proposed.”
BackgroundMethodEsenogho, E., Djouani, K., & Kurien, A. M. (2022) · IEEE Access · doi:10.1109/access.2022.3140595 · Cited by 247
Ullah, K., Ahsan, M., Hasanat, S. M., Haris, M., Yousaf, H., Raza, S. F., Tandon, R., Abid, S., & Ullah, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3440631 · Cited by 219
Metadata
- Authors
- Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M. A.
- Affiliations
- United Arab Emirates University (AE)
- École de Technologie Supérieure (CA)
- Corresponding author
- Bouktif, Salah
- Venue
- Energies
- Publisher
- MDPI AG
- Published
- 2020-01-13
- Volume
- 13
- Issue
- 2
- Pages
- 391
- ISSN
- 1996-1073 (ISSN-L)
- OpenAlex
- W2999869395
- Cited by
- 256
- References
- 39
- Citations by year
- 2026: 29 · 2025: 42 · 2024: 48 · 2023: 46 · 2022: 44 · 2021: 37 · 2020: 10
- FWCI
- 11.75
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Energies (publishedVersion, cc-by)
- Espace ÉTS (ETS) (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- United Arab Emirates University (G00002211)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Energy Load and Power Forecasting
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Smart Grid Energy Management
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Keywords
- short-term load forecasting, LSTM hyperparameter optimization, genetic algorithm, particle swarm optimization, metaheuristic search, energy consumption time series, power grid management, smart meter data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Multi-Sequence LSTM-RNN Deep Learning and Metaheuristics for Electric Load Forecasting. https://app.cochat.ai/papers/10.3390/en13020391
- The paper
- Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M. A. (2020). Multi-Sequence LSTM-RNN Deep Learning and Metaheuristics for Electric Load Forecasting. Energies. https://doi.org/10.3390/en13020391
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.