Search

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

Stable electric load forecasting plays a significant role in power system operation and grid management. Improving the accuracy of electric load forecasting is not only a hot topic for energy managers and researchers of the power system, but also a fair challenging and difficult task due to its complex nonlinearity characteristics. This paper proposes a new combination model, which uses the least squares support vector machine, extreme learning machine, and generalized regression neural network to predict the electric load in New South Wales, Australia. In addition, the model employs a heuristic algorithm–whale optimization algorithm to optimize the weight coefficient. To verify the usability and generalization ability of the model, this paper also applies the proposed combined model to electricity price forecasting and compares it with the benchmark method. The experimental results demonstrate that the combined model not only can get accurate results for short-term electric load forecasting, but also achieves fine accuracy for the same period of electricity price forecasting. [ABSTRACT FROM AUTHOR]

Accurate and reliable low-voltage load forecasting is critical to optimal operation and control of distribution network and smart grid. However, compared to traditional regional load forecasting at high-voltage level, it faces tough challenges due to the inherent high uncertainty of the low-capacity load and distributed renewable energy integrated in the demand side. This paper proposes a novel hybrid ensemble deep learning (HEDL) approach for deterministic and probabilistic low-voltage load forecasting. The deep belief network (DBN) is applied to low-voltage load point prediction with the strong ability of approximating nonlinear mapping. A series of ensemble learning methods including bagging and boosting variants are introduced to improve the regression ability of DBN. In addition, the differencing transformation technique is utilized to ensure the stationarity of load time series for the application bagging and boosting methods. On the basis of the integrated thought of ensemble learning, a new hybrid ensemble algorithm is developed via integrating multiple separate ensemble methods. Considering the diversity in various ensemble algorithms, an effective K nearest neighbor classification method is utilized to adaptively determine the weights of sub-models. Furthermore, HEDL based probabilistic forecasting is proposed by taking advantage of the inherent resample idea in bagging and boosting. The effectiveness of the HEDL method for both deterministic and probabilistic forecasting has been systematically verified based on realistic load data from East China and Australia, indicating its promising prospective for practical applications in distribution networks. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting (STLF) is of positive significance to the effective management of power companies and the stable operation of society. In spite of many studies conducted in this field, there are few to consider the inherent disadvantages of an individual module, which results in sub-optimal forecasting accuracy. Therefore, by integrating data preprocessing module and optimization module into support vector regression (SVR) forecasting module, this paper successfully presents a novel model (AHO-Lasso-SVR). The data preprocessing module, which is comprised of feature construction and Lasso feature selection, is used to construct and select meaningful features. An adaptive hybrid optimization (AHO) algorithm is proposed by introducing two strategies on the basis of standard particle swarm optimization (PSO). The AHO algorithm inevitably increases the computational complexity of model learning, thus, this paper proposes a subsampling technology to improve the optimization efficiency of the algorithm based on the sparsity of SVR. The proposed model is used to forecast the load at 48 points in the next day. To verify the properties of the proposed model, power load data from New South Wales, Australia are adopted as a case study. The results reveal that our model positively exceeds all comparison models in terms of forecasting accuracy and stability. [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The emerging complex circumstances caused by economy, technology, and government policy and the requirement of low-carbon development of power grid lead to many challenges in the power system coordination and operation. However, the real-time scheduling of electricity generation needs accurate modeling of electricity demand forecasting for a range of lead times. In order to better capture the nonlinear and non-stationary characteristics and the seasonal cycles of future electricity demand data, a new concept of the integrated model is developed and successfully applied to research the forecast of electricity demand in this paper. The proposed model combines adaptive Fourier decomposition method, a new signal preprocessing technology, for extracting useful element from the original electricity demand series through filtering the noise factors. Considering the seasonal term existing in the decomposed series, it should be eliminated through the seasonal adjustment method, in which the seasonal indexes are calculated and should multiply the forecasts back to restore the final forecast. Besides, a newly proposed moth-flame optimization algorithm is used to ensure the suitable parameters of the least square support vector machine which can generate the forecasts. Finally, the case studies of Australia demonstrated the efficacy and feasibility of the proposed integrated model. Simultaneously, it can provide a better concept of modeling for electricity demand prediction over different forecasting horizons. [ABSTRACT FROM AUTHOR]

Short‐term load forecasting is essential to power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate the intrinsic time‐related dimensions of electric load data and the decomposition methods into machine learning models so that their prediction accuracy and robustness still have much room for improvement. To solve this problem, this paper proposes a decomposition‐based multi‐time dimension long short‐term memory (DB‐MTD‐LSTM) model for short‐term electric load forecasting (STELF). In DB‐MTD‐LSTM, empirical mode decomposition with adaptive noise (CEEMDAN) is first introduced to smooth non‐linear non‐stationary electric load data and constrain the modal aliasing or noise of decomposed electric load data in the traditional decomposed method. A joint relevant time dimensions method (JRTDM) is then developed using autocorrelation analysis to rationally extract the temporal characteristics of decomposed data in multiple time dimensions. An improved LSTM called MTD‐LSTM is developed by combining JRTDM with LSTM, which can effectively apply multi‐dimensional time characteristics of the decomposed load to improve the predictive accuracy and robustness. Several datasets from Australia and China are performed to check the predictive performance of DB‐MTD‐LSTM. Experimental results verify that DB‐MTD‐LSTM has better predictive accuracy and satisfactory robustness compared with state‐of‐the‐art and conventional predictive models. [ABSTRACT FROM AUTHOR]

Intermittent electrical power output from grid-connected solar farms causes intermittent and uncertain requirements for dispatchable power to balance power supply and demand. Accurate forecasting of electrical power output from solar farms can improve managing power generators connected to the grid. To forecast the electrical power output, a time series model is developed for two solar farms in Australia. The forecast model consists of a Fourier series that models seasonality and an autoregressive moving-average component that models the difference between the observed electrical power outputs and the Fourier series. Persistence detection is added to the model to improve forecast performance on clear days. Using minutely data, the model forecasts the electrical power output seven minutes ahead at every five-minute interval to comply with the requirements of the Australian Energy Market Operator (AEMO). Based on a 30-day testing period, the normalized mean absolute error (NMAE) skills of the time series model are 10.9% and 13.2% lower than those of the clear sky index persistence (CSIP) model. However, the normalized root mean squared error (NRMSE) skills of the time series model are approximately 3% and 12% higher than those of CSIP and the model currently used by AEMO, respectively. As the NRMSE skills are more indicative than the NMAE skills in reducing large forecast errors that would reduce electricity grid stability, the results suggest that AEMO can improve the management of the electricity grid with an inexpensive tool by adopting the developed model to forecast electrical power output of solar farms. [ABSTRACT FROM AUTHOR]

• A novel CElif system is proposed in this paper. • Decomposition and denoising strategy is designed in the CElif system. • The MSsa mechanism is superior both in search ability and operation efficiency. • The construction of the five ANNs covers the inherent modes of sequence. • Differences in people's behavior on weekdays and weekends are considered. Under the trend of the global green and low-carbon transformation, accurate prediction of electric load is an urgent problem for all countries to maintain the normal operation of production and living activities. Currently, a large number of models based on single-point forecasting of electric load have emerged. However, these models are limited by the high randomness of electric load data, which restricts the further improvement of prediction accuracy. To fill this gap, a CElif (Combined Electric Load Interval Forecasting) system is proposed in this paper, which contains decomposition and denoising module, individual forecasting module, optimization module and evaluation module, aiming to tolerate uncertainty to provide policymakers with more information. Decomposition and denoising strategy is adopted to extract and reconstruct the inherent modes of the original sequence. In order to verify the superiority of the CElif system, the electric load data of 30-minute interval in Australia are used to test. The numerical results conclude the CElif system not only has excellent coverage performance in electric load interval prediction, controls the uncertainty to a great extent, but also provides a basis for power system dispatching management. [ABSTRACT FROM AUTHOR]

Load forecasting is a challenging task in power markets that require attention in generating accurate and stable load to deal with planning and management strategies. In past few years, several intelligence-based models have been introduced for precise load forecast. Among them, artificial neural network (ANN) seems more effective and capable to handle the non-linear behavior of load and generates an accurate forecast. However, it suffers from overfitting problem thus reducing the accuracy of load forecasts. To overcome this problem, a hybrid methodology namely ANN-IEAMCGM-R, for short-term load forecast is proposed in this paper. ANN is integrated with an enhanced evolutionary algorithm (IEAMCGM-R) to find optimal network weights. This evolutionary algorithm is composed of improved environmental adaptation method with real parameters (IEAM-R) and our proposed Controlled Gaussian Mutation (CGM) method to bring greater diversity within the population resulting in a higher convergence of solutions. The electric load data from the New England Power Pool (NEPOOL, ISO New England) and Australian Energy Market Operator (New South Wales (NSW), Australia) have been used to illustrate the efficacy of the proposed hybrid methodology. Results show that the proposed hybrid methodology generates higher accuracy than other state-of-the-art algorithms. • Proposal of Controlled Gaussian Mutation for enhancing the diversity of IEAM-R. • Proposal of enhanced optimization algorithm, namely IEAMCGM-R. • A hybrid methodology is presented for load forecasting. • Experimental results show that ANN-IEAMCGM-R generates least forecasting error. • Statistical test results ensures the statistical signi_cance of forecasted load. [ABSTRACT FROM AUTHOR]

This article focuses on the use of the rough set theory in modeling of time series forecasting. In this paper, we have used the double exponential smoothing (DES) model for forecasting. The classical DES model has been improved by using the rough set technique. The improved double exponential smoothing (IDES) method can be used for the time series data without any statistical assumptions. The proposed method is applied on tourism demand of the air transportation passenger data set in Australia and the results are compared with the classical DES model. It has been observed that the forecasting accuracy of the proposed model is better than that of the classical DES model. [ABSTRACT FROM AUTHOR]

Establishing accurate electrical load prediction is vital for pricing and power system management. However, the unpredictable behavior of private and industrial users results in uncertainty in these power systems. Furthermore, the utilization of renewable energy sources, which are often variable in their production rates, also increases the complexity making predictions even more difficult. In this paper an interval type-2 intuitionist fuzzy logic system whose parameters are trained in a hybrid fashion using gravitational search algorithms with the ridge least square algorithm is presented for short-term prediction of electrical loading. Simulation results are provided to compare the performance of the proposed approach with that of state-of-the-art electrical load prediction algorithms for Poland, and five regions of Australia. The simulation results demonstrate the superior performance of the proposed approach over seven different current state-of-the-art prediction algorithms in the literature, namely: SVR, ANN, ELM, EEMD-ELM-GOA, EEMD-ELM-DA, EEMD-ELM-PSO and EEMD-ELM-GWO. [ABSTRACT FROM AUTHOR]

• A novel integrated short-term power load forecasting system is proposed. • The fuzzy granulation technique simplifies the large-scale dataset and extracts the effective characteristics of the raw data. • A novel multi-objective variant of the tuna swarm optimizer is utilized to integrate multiple forecasting sequences. • The optimal weight coefficients of the ensemble model are theoretically demonstrated to be the Pareto optimal solutions. • Our proposed forecasting system can gauge the uncertainty of future electricity load. As an irreplaceable power source, electricity is responsible for sustaining the national economy and social development, and the precondition for the power system's stable operation is to perform an accurate short-term load forecast (STLF). However, with the increasing forms of social power consumption and the emergence of large-scale sustainable resources on the grid, which make STLF increasingly challenging as the power load exhibits greater stochasticity and instability. Therefore, a novel STLF system is developed in this paper, which incorporates data fuzzy granulation, a high-performance optimizer for integrating forecasting sequences, point and interval forecasts. Moreover, the performance tests of the optimization algorithm verify that our proposed optimizer can obtain more approximate solution sets to the real Pareto front and outshines the traditional optimization algorithm concerning convergence and diversity. Load data from three regions of Australia demonstrate that our developed system can remarkably contribute to the accuracy and stability of the STLF , and also quantify the volatility and uncertainty of the power load, which allows power workers to better capture the fluctuation interval of future loads and effectively enhance the flexibility of grid operation. [ABSTRACT FROM AUTHOR]

Electricity load forecasting plays an essential role in improving the management efficiency of power generation systems. A large number of load forecasting models aiming at promoting the forecasting effectiveness have been put forward in the past. However, many traditional models have no consideration for the significance of data preprocessing and the constraints of individual forecasting models. Moreover, most of them only focus on the forecasting accuracy but ignore the forecasting stability, resulting in nonoptimal performance in practical applications. This paper presents a novel hybrid model that combines an advanced data preprocessing strategy, a deep neural network, and an avant-garde multi-objective optimization algorithm, overcoming the defects of traditional models and thus improving the forecasting performance effectively. In order to evaluate the validity of the proposed hybrid model, the electricity load data sampled in 30-min intervals from Queensland, Australia are used as a case to study. The experiments show that the new proposed model is obviously superior to all other traditional models. Furthermore, it provides an effective technical forecasting means for smart grid management. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) power forecasting can provide strong support for the safe operation of the power system. Existing forecasting methods are ineffective for grid scheduling decisions or risk analysis. The novel multicluster interval prediction method is proposed to consider the volatility and randomness of PV power output. First, this method utilizes the sparse autoencoder (SAE) and Bayesian regularized NARX network (BRNARX) for point forecasting of PV power. Second, density peak clustering improved by kernel Mahalanobis distance (KMDDPC) is applied to classify the dataset into multiple clusters, including forecasting error and meteorological factors. Finally, the joint probability density is established by multivariate kernel density estimation (MKDE) to accomplish the PV power interval prediction. The proposed hybrid method is applied for the interval prediction of PV power at Yulara, Australia. Comparative research of point forecasting is implemented to evaluate the machine learning and deep learning methods, with the proposed SAE-BRNARX under four different periods. Results shows that the average values of nRMSE, MRE, nMAE, and R2 for the four periods are 4.45%, 0.90%, −0.15%, 3.39%, and 95.93%, respectively. Moreover, the results of interval prediction obtained by the other interval prediction approaches are compared with the proposed KMDDPC-MKDE. It shows that the average values of PICP, PINAW, ACE, and nMPICD for four periods are 93.93%, 9.50%, 3.93%, and 7.10% at 90% confidence level, respectively. Outcomes demonstrate that the proposed method can obtain more accuracy, a higher coverage rate, narrower average bandwidth, and a closer distance between the middle of interval and actual value than other methods. [ABSTRACT FROM AUTHOR]

• Novel ensemble framework which improves short-term load forecasting accuracy. • Model divides the problem into several subtasks based on peak and off-peak conditions. • Classification and regression models were developed to solve each subtask. • Framework is validated on real-world operational demand across regions in Australia. • Model has a substantially higher accuracy (up to 25.4% in MAE) over other methods. [Display omitted] To keep the balance between electricity demand and supply as well as infrastructure planning, it is important to accurately forecast the electricity demand. This has become a challenging task due to increasing share of renewable energy and prosumers (i.e. consumers who produce electricity) in the electricity grid. This paper develops a cooperative ensemble framework which divides the forecasting problem into several subtasks based on peak and off-peak conditions. Each subtask is then solved using multiple forecasting models that include classification and regression. The developed framework is finally validated on real-world operational demand across the National Electricity Market (NEM) of Australia. The performance is comprehensively compared against various state-of-the-art techniques in the field, which indicates up to 25.4% mean absolute error (MAE) improvement. [ABSTRACT FROM AUTHOR]

• A hybrid short-term load forecasting method is proposed. • A data preprocessing module is conducted based on de-noising technique and fuzzy time series. • To balance the forecasting accuracy and stability, a multi-objective optimization algorithm is applied to optimize the BPNN model. Countries around the globe have introduced renewable energies (RE) and minimized the dependency of fossil resources in power systems to address extensive environmental risks. However, such large-scale energy transitions pose a great challenge to power systems due to the volatility of RE. Meanwhile, power demand is increasing over time and it shows temporal characteristics, such as seasonal and peak-valley patterns. Whether the future power system with a larger proportion of RE can meet the surging but fluctuated electricity demand remains problematic. Previous studies on short-term load forecasting focused more on forecasting accuracy than stability. Further, there is a relative paucity of research into temporal patterns. In order to fill in these research gaps, this paper proposes a fuzzy theory-based machine learning model for workdays and weekends short-term load forecasting. Fuzzy time series (FTS) is applied for data mining and back propagation (BP) neural network is used as the main predictor for short-term load forecasting. To exploit the trade-offs between forecasting stability and accuracy, multi-objective optimization is applied to modify the parameters of BP. Moreover, an interval forecasting architecture with several statistical tests is constructed to address forecasting uncertainties. Short-term load data from Victoria in Australia is selected as a case study. Results demonstrate that the proposed method can significantly boost forecasting stability and accuracy, and help strategy making in the field of energy and electricity system management and planning. [ABSTRACT FROM AUTHOR]

Load forecasting is of crucial importance for operations of electric power systems. In recent years, deep learning based methods are emerging for load forecasting because their strong nonlinear approximation capabilities can provide more forecasting precision than conventional statistical methods. However, they usually suffer from some problems, e.g., the gradient vanishment and over-fitting. In order to address these problems, an unshared convolution based deep learning model with densely connected network is proposed. In this model, the backbone is the unshared convolutional neural network and a densely connected structure is adopted, which could alleviate the gradient vanishment. What is more, we use a regularization method named clipped $L_2$ -norm to overcome over-fitting, and design a trend decomposition strategy to address the possible distribution differences between the training and validation data. Finally, we conduct five case studies to verify the outperformance of our proposed deep learning model for deterministic and interval load forecasting. Two high-voltage and an medium-voltage real load datasets from Australia, Germany and America are used for model training and validation, respectively. Results show that the proposed model can achieve higher load forecasting accuracy, compared with other existing methods including the popular conventional methods such as naive forecast and generalized additive model, and deep learning methods, e.g., long short-term memory network, convolutional neural network, fully connected network, etc. [ABSTRACT FROM AUTHOR]

Virtual power plants (VPPs) have become a driving force for the decentralized energy industry, due to their efficient management and control of distributed energy resources. Most of the operation strategies for VPPs are designed based on the day-ahead forecasts. However, the prediction errors of the renewable energy sources (RES) and loads in the power dispatch schedule can lead to a suboptimal operation. In this article, an adaptive and predictive energy management strategy for a real-time optimal operation of VPPs is proposed based on the model predictive control technique with a feedback correction (FC) to compensate for the prediction error. This strategy has two parts: 1) receding-horizon optimization (RHO), and 2) FC. In the first part, a hybrid prediction algorithm based on the integration of the time-series model and the Kalman filter is used to forecast the output powers of RES and the loads. Based on the prediction, the RHO model schedules the operation following the latest forecast information. In the second part, the receding schedule is adjusted based on the fast-rolling gray model's ultrashort-term error prediction. The FC is applied to minimize the adjustments for compensating the prediction error. The proposed strategy is implemented on a VPP in a real electricity distribution system in New South Wales, Australia. The simulation results demonstrate the effectiveness of the proposed strategy with a better tracking of the actual available resources and a minimal mismatch between demand and supply. [ABSTRACT FROM AUTHOR]

To a large extent, electricity price prediction is a daunting task because it depends on factors, such as weather, fuel, load and bidding strategies etc. Those features generate a lot of fluctuations to electricity price. As a type of RNN, LSTM has a good performance on processing time series data as well as some nonlinear and complex problems. To explore more accurate electricity price forecasting approach, in this paper, a new hybrid model based on wavelet transform and Adam optimized LSTM neural network, denoted as WT-Adam-LSTM, is proposed. After the wavelet transform, nonlinear sequence of electricity price can be decomposed and processed data will have a more stable variance, and the combination of Adam, one of efficient stochastic gradient-based optimizers, and LSTM can capture appropriate behaviors precisely for electricity price. This study presented four cases to verify the performance of the hybrid model, and the dataset from New South Wales of Australia and French were adopted to illustrate the excellence of the hybrid model. The results show that the proposed model can significantly improve the prediction accuracy. • Long short-term Memory (LSTM) is applied for electricity price forecasting. • Adam is used as optimizer for LSTM. • Pauta criterion and Min-max normalization are used as preprocessing methods for price data. • Wavelet transform is used to decompose the electricity price series into a set of better-performing constitutive series. • Four cases proved that proposed WT-Adam-LSTM outperforms the existing models reported in the literature. [ABSTRACT FROM AUTHOR]

• Deep learning hybrid model is proposed for solar radiation prediction. • Convolutional network is used to extract features for solar radiation. • Long Short-Term Memory is used for prediction of solar radiation. • Deep learning hybrid model outperforms all comparative models. • The model can be adopted as a decision-support tool in solar energy simulation. This paper designs a hybridized deep learning framework that integrates the Convolutional Neural Network for pattern recognition with the Long Short-Term Memory Network for half-hourly global solar radiation (GSR) forecasting. The Convolution network is applied to robustly extract data input features from predictive variables (i.e., statistically significant antecedent inputs) while Long Short-Term Memory absorbs them for prediction. Half-hourly GSR for Alice Springs (Australia: 01 January 2006 to 31 August 2018) are extracted with stationarity checks applied via unit-root and mutual information test to capture antecedent GSR values required to forecast future GSR. The proposed hybrid model is benchmarked with standalone models as well as other Deep Learning, Single Hidden Layer and Tree based models. The results show that the benchmarked models are not able to generate satisfactory GSR predictions and the proposed hybrid model outperforms all other counterparts. The hybrid model registers superior results with over 70% of predictive errors lying below ±10 Wm−2 and outperforms the benchmark model for 1-Day half-hourly GSR prediction with low Relative Root Mean Square Error (≈1.515%), Mean Absolute Percentage Error (≈4.672%) and Absolute Percentage Bias (≈1.233%). This study ascertains that a proposed hybrid model based on a convolution network framework can accurately predict GSR and enable energy availability to be regularly monitored over multi-step horizons when coupled with a low latency Long Short-Term Memory network. Furthermore, it also concludes that the proposed model can have practical implications in forecasting GSR , capitalizing its versatility as a stratagem in monitoring solar powered systems by integrating freely available solar radiation into a real power grid system. [ABSTRACT FROM AUTHOR]

Accurate electrical load forecasting always plays a vital role in power system administration and energy dispatch, which are the foundation of the smooth operation of the national economy and people's daily life. Thinking from this vision, many scholars have made great efforts to seek suitable optimization algorithms to improve the performance of existing forecasting algorithm. However, most of the studies ignore the inherent disadvantages of single optimization algorithm, which leads to sub-optimal forecasting performance. Therefore, a novel electric load forecasting system was successfully proposed in this paper by the combination of data preprocessing, hybrid optimization algorithms, and several single classical forecasting methods, which successfully overcomes the defects of single traditional forecasting models and achieves higher forecasting accuracy than that of single model optimization. Besides, the 30 min interval data of Queensland, Australia from March to April is used as illustrative examples to evaluate the performance of the developed model. The results of tests demonstrate that the proposed hybrid model can better approximate the actual value, and it can also be employed as a useful tool for smart grids dispatching planning. • Develop a novel power load forecasting system for grid safety dispatch. • Extract important information effectively from the original load time series. • Creatively propose two hybrid optimization methods to optimize forecasting models. • Set up a comprehensive evaluation system to verify the effectiveness of the models. [ABSTRACT FROM AUTHOR]

From the perspective of energy providers, accurate short-term load forecasting plays a significant role in the energy generation plan, efficient energy distribution process and electricity price strategy optimisation. However, it is hard to achieve a satisfactory result because the historical data is irregular, non-smooth, non-linear and noisy. To handle these challenges, in this work, we introduce a novel model based on the Transformer network to provide an accurate day-ahead load forecasting service. Our model contains a similar day selection approach involving the LightGBM and k-means algorithms. Compared to the traditional RNN-based model, our proposed model can avoid falling into the local minimum and outperforming the global search. To evaluate the performance of our proposed model, we set up a series of simulation experiments based on the energy consumption data in Australia. The performance of our model has an average MAPE (mean absolute percentage error) of 1.13, where RNN is 4.18, and LSTM is 1.93. [ABSTRACT FROM AUTHOR]