Short-term household load forecasting based on Long- and Short-term Time-series network

Forecasting domestic electricity consumption is important for a wide range of modern power system solutions and smart applications that support network operation, grid stability, and demand-side management, most of which depend on robust and accurate predictions. The methods producing these predictions infer future load from statistical regularity in historical data. If such regularity is lacking, predictions then regress towards the most recently observed consumption value used in the input set. Predictions then follow the actual load data one step behind in time, potentially affecting the robustness of predictions and functionality of applications. Current evaluation methods do not detect this behaviour which may result in overconfidence in prediction results. In this study, we I) define and systematically analyse this behaviour, which we label the Persistence Forecast Effect and illustrate its impacts, II) propose a novel method, called 1-Step-Shifting, to detect its presence, and III) analyse and establish the relationship between irregularity in data and the effect. Further, we provide a case study applying state-of-the-art forecasting techniques to a real-world dataset of electricity consumption data from 69 households in order to demonstrate the Persistence Forecast Effect, its implications, and its relationship to statistical regularity in historical data.

show abstract

“…[2] Corr., MAPE, RMSE [4] RMSE [6], [35], [36] MAPE, RMSE [8]- [10] MAPE [15] S-MAPE [11], [37], [38] MAE, MAPE, RMSE [39] MAE, RMSE, N-RMSE…”

Section: Study Evaluation Metricmentioning

confidence: 99%

Avoiding Overconfidence in Predictions of Residential Energy Demand Through Identification of the Persistence Forecast Effect

Akyol

Preist

Schien

2023

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

show abstract

“…Specifcally, skip links are added between the currently hidden cell and the hidden cells in the same phase in adjacent periods. Te hidden state of recurrent units at time t is computed as [11]…”

Section: Improved Lstnet Modelmentioning

confidence: 99%

“…Furthermore, LSTNet adopts the traditional autoregressive (AR) model to tackle the scale-insensitive problem of the neural network model. LSTNet has been applied to wind power prediction [10], household load prediction [11], and temperature prediction [12]. In [10], the performance of models such as LSTNet, temporal pattern attention-based long short-term memory (TPA-LSTM), and dual-stage attention-based recurrent neural network (DA-RNN) was compared and analyzed for the wind power prediction problem.…”

Section: Introductionmentioning

confidence: 99%

Short‐Term Wind and Solar Power Prediction Based on Feature Selection and Improved Long‐ and Short‐Term Time‐Series Networks

Wang

et al. 2023

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In terms of the problems of high feature dimension and large data redundancy in the wind and solar power prediction method, an improved prediction model is proposed by combining feature selection methods with the long- and short-term time-series network (LSTNet). The long short-term memory (LSTM) unit in the LSTNet model is replaced with the bidirectional long short-term memory (BiLSTM), which enables recursive response training for the states of hidden layers at the start and end of the sequence. For feature selection, both feature screening and dimension reduction methods are considered, including random forest (RF), grey relational analysis (GRA), and principal component analysis (PCA). Finally, based on wind and solar power data, the effectiveness of the proposed methods is verified, where the RF-LSTNet performs the best. For wind power prediction, the mean absolute percentage error is reduced by 29.7% and root mean square error is reduced by 24.1% compared with the traditional LSTNet model, and for solar power prediction, the MAPE is reduced by 12.9% and RMSE is reduced by 3.8%.

show abstract

“…Dalam mengukur ketepatan prediksi perlu dilakukan perhitungan guna mengetahui kesesuaian antara data aktual dan data hasil prediks. Terdapat beberapa perhitungan yang umumnya digunakan untuk mengukur keakuratan hasil prediksi, yaitu RMSE dan MAPE [32]. 1.…”

Section: Pemilihan Model Terbaikunclassified

Prediksi Harga Ekspor Non Migas di Indonesia Berdasarkan Metode Estimator Deret Fourier dan Support Vector Regression

et al. 2023

View full text Add to dashboard Cite

Pertumbuhan ekonomi merupakan salah satu indikator dalam Sustainable Development Goals (SDGs) pada peningkatan kegiatan ekonomi. Salah satu kegiatan yang menopang berjalannya perekonomian adalah perdagangan antar negara, seperti ekspor. Di Indonesia, ekspor non migas memegang peranan penting dalam total ekspor beberapa tahun terakhir, diantaranya ekspor batu bara menjadi ekspor utama. Oleh karena itu, prediksi harga ekspor non migas Indonesia menjadi sangat penting sebagai bahan evaluasi kebijakan untuk mendorong pertumbuhan ekonomi. Hal tersebut menjadi fokus utama dari penelitian ini. Dalam studi ini, prakiraan harga ekspor non migas dibuat dengan mempertimbangkan isu-isu terkini seperti pandemi COVID-19 dan perang Rusia-Ukraina. Keakuratan model yang diperoleh dari estimator deret Fourier dan Support Vector Regression (SVR) diselidiki dengan membandingkan nilai Mean Absolute Percentage Error (MAPE) untuk memprediksi harga ekspor non migas Indonesia. Hasil penelitian menunjukkan bahwa masalah pandemi COVID-19 dan perang Rusia-Ukraina berdampak signifikan terhadap harga ekspor non migas. Model SVR dengan kernel Radial Basis Function (RBF) menunjukkan akurasi yang lebih baik daripada model estimator deret Fourier fungsi cos sin, dengan masing-masing nilai MAPE sebesar 9,29 dan 15,26% untuk setiap data uji. Oleh karena itu, kajian ini diharapkan dapat menjadi dasar untuk merumuskan kebijakan terkait pengaturan proses ekspor non migas untuk mendukung pertumbuhan ekonomi di Indonesia. Kata kunci⎯ ekspor, non migas, estimator deret Fourier, support vector regression, radial basis function.ABSTRACT ⎯ Economic growth is one of the indicators in the Sustainable Development Goals (SDGs) on increasing economic activity. One of the activities that supports the running of the economy is trade between countries, such as exports. In Indonesia, non-oil and gas exports have played an important role in total exports in recent years, including coal exports being the main export. Therefore, price predictions for Indonesia's non-oil and gas exports are very important as material for evaluating policies to encourage economic growth. This is the main focus of this research. In this study, non-oil and gas export price forecasts are made taking into account current issues such as the COVID-19 pandemic and the Russia-Ukraine war. The accuracy of the model obtained from the Fourier series estimator and Support Vector Regression (SVR) is investigated by comparing the Mean Absolute Percentage Error (MAPE) value to predict Indonesia's non-oil and gas export prices. The results of the study show that the COVID-19 pandemic and the Russia-Ukraine war have had a significant impact on non-oil and gas export prices. The SVR model with the Radial Basis Function (RBF) kernel shows better accuracy than the Fourier series estimator model of the cos sin function, with MAPE values of 9.29 and 15.26% for each test data, respectively. Therefore, this study is expected to be the basis for formulating policies related to regulating non-oil and gas export p...

show abstract

Short-term household load forecasting based on Long- and Short-term Time-series network

Cited by 48 publications

References 13 publications

Avoiding Overconfidence in Predictions of Residential Energy Demand Through Identification of the Persistence Forecast Effect

Avoiding Overconfidence in Predictions of Residential Energy Demand Through Identification of the Persistence Forecast Effect

Short‐Term Wind and Solar Power Prediction Based on Feature Selection and Improved Long‐ and Short‐Term Time‐Series Networks

Prediksi Harga Ekspor Non Migas di Indonesia Berdasarkan Metode Estimator Deret Fourier dan Support Vector Regression

Contact Info

Product

Resources

About