Design of a hybrid deep learning model for long-term power load forecasting: Learnable-DTimesNet-Linear

Establishing a scientific and reasonable mid- and long-term power load forecasting method is the premise of power industry planning and construction. This paper constructs a hybrid electric load forecasting model based on Gaussian process (GPR) and particle swarm optimization (PSO). The paper uses the PSO algorithm to optimize the parameters in the co-variance function, and uses the modified parameters as the initial value to train the power load in the GPR model. Under the Bayesian framework, the parameters in the co-variance function are again optimized. Finally, the trained GPR model is used to predict the power load, and the results are compared with the auto-regressive integral moving average model and the exponential smoothing model. The verification results show that the hybrid electric load forecasting model based on Gaussian process (GPR) and particle swarm optimization (PSO) has good stability and higher prediction accuracy, and is suitable for medium and long-term electric load forecasting.

Long-term load forecasting and economical operation of wind farms for Egyptian electrical network

Long-term load forecasting by a collaborative fuzzy-neural approach

8 - Dynamic Electric Load Forecasting

Medium-and long-term load forecasting in the distribution network has important guiding significance for overload warning of distribution transformer, transformation of distribution network and other scenarios. However, there are many constraints in the forecasting process. For example, there are many predict objects, the data sample size of a single predict object is small, and the long term load trend is not obvious. The forecasting method based on neural network is difficult to model due to lack of data, and the forecasting method based on time sequence law commonly used in engineering is highly subjective, which is not effective. Aiming at the above problems, this paper takes distribution transformer as the research object and proposes a medium-and long-term load forecasting method for group objects based on Image Representation Learning (IRL). Firstly, the data of distribution transformer is preprocessed in order to restore the load variation in natural state. And then, the load forecasting process is decoupled into two parts: the load trend forecasting of the next year and numerical forecasting of the load change rate. Secondly, the load images covering annual and inter-annual data change information are constructed. Meanwhile, an Image Representation Learning forecasting model based on convolutional neural network, which will use to predict the load development trend, is obtained by using load images for training; And according to the data shape, the group classification of the data in different periods are carried out to train the corresponding group objects forecasting model of each group. Based on the forecasting data and the load trend forecasting result, the group forecasting model corresponding to the forecasting data can be selected to realize the numerical forecasting of load change rate. Due to the large number of predict objects, this paper introduces the evaluation index of group forecasting to measure the forecasting effect of different methods. Finally, the experimental results show that, compared with the existing distribution transformer forecasting methods, the method proposed in this paper has a better overall forecasting effect, and provides a new idea and solution for the medium-and long-term intelligent load forecasting of the distribution network.

Grey model is a common method in medium and long-term power load forecasting, but it has great limitations. According to the characteristics of medium and long term power load forecasting, the method of sliding average and the principle of Markov model are introduced into the Grey forecasting theory, and the model is improved. This improvement can effectively improve the prediction accuracy of the model. Based on the load data of Qingdao City in the past ten years, it can be proved that the improved Grey model has improved the accuracy of the former.

To handle the data imbalance and inaccurate prediction in power load forecasting, an integrated data denoising power load forecasting method is designed. This method divides data into administrative regions, industries, and load characteristics using a four-step method, extracts periodic features using Fourier transform, and uses Kmeans++ for clustering processing. On this basis, a Transformer model based on an adversarial adaptive mechanism is designed, which aligns the data distribution of the source domain and target domain through a domain discriminator and feature extractor, thereby reducing the impact of domain offset on prediction accuracy. The mean square error of the Fourier transform clustering method used in this study was 0.154, which was lower than other methods and had a better data denoising effect. In load forecasting, the mean square errors of the model in predicting long-term load, short-term load, and real-time load were 0.026, 0.107, and 0.107, respectively, all lower than the values of other comparative models. Therefore, the load forecasting model designed for research has accuracy and stability, and it can provide a foundation for the precise control of urban power systems. The contributions of this study include improving the accuracy and stability of the load forecasting model, which provides the basis for the precise control of urban power systems. The model tracks periodicity, short-term load stochasticity, and high-frequency fluctuations in long-term loads well, and possesses high accuracy in short-term, long-term, and real-time load forecasting.

Load forecasting is an important subject for power distribution systems and has been studied comparing different points of view. In general, load forecasts should be performed over a broad spectrum of time intervals, which could be classified into short-term, medium-term and long-term forecasts. Several research groups have proposed various techniques for either short-term load forecasting or medium-term load forecasting or long-term load forecasting. This paper presents two approaches for modelling the long-term load forecasting: a neural network (NN) and a non-linear (cause/effect) model. The data used by the models are gross domestic product (GDP), the national minimum salary, the electrical energy price, the estimated national population and the total number of electrical connections. The suitability of the proposed approach is illustrated through a long-term load forecasting application (electricity consumption in Brazil ten years ahead).

The essentiality of electric load forecast for the effective design and management of electric power systems has been achieved in this study. PHEDC may plan for infrastructure construction, resource allocation, and energy management by using accurate long-term load forecasts of this study. In the context of the Woji Estate 11/0.415 kV Feeder in Port Harcourt, Nigeria, we have discussed the use of artificial neural networks (ANNs) for a long-term of ten (10) years load forecasting in this paper starting from January 2020- December 2029. However, curve fitting feed-forward artificial neural network has been employed for the simulation on MATLAB 2020 environment, with six (6) input datasets obtained from Transmission Company of Nigeria (TCN), Oginigba and Port Harcourt Electricity Distribution Company, and average temperature dataset from NIMET-Abuja all in Nigeria from January, 2015-December, 2019. The regression plot of epoch 11 with training; R=1 and validation of 0.9999 have been achieved which indicates how efficient the training of the dataset was. The Levenberg-Marquardt (LM) algorithm is used as an optimization technique in this study. In addition, training, test, validation, and error analysis have been used to examine the effectiveness of the LM algorithm; it has been found optimal with ANN. The general observation shows that ANN provides effective results on long-term electrical load forecasting of the Woji Estate Feeder with a total forecasted value of 29734.4 MWHR and an average value of 24778.67 MWHR at the end of the tenth year.

An optimization planning technique for Suez Canal Network in Egypt

The load forecasting problem is a complicated non-linear problem connected with the weather, economy, and other complex factors. For electrical power systems, long-term load forecasting provides valuable information for scheduling maintenance, evaluating adequacy, and managing limited energy supplies. A future generating, transmission, and distribution facility’s development and planning process begins with long-term demand forecasting. The development of advanced metering infrastructure (AMI) has greatly expanded the amount of real-time data collection on large-scale electricity consumption. The load forecasting techniques have changed significantly as a result of the real-time utilization of this vast amount of smart meter data. This study suggests numerous approaches for long-term load forecasting using smart-metered data from an actual distribution system on the NIT Patna campus. Data pre-processing is the process of converting unprocessed data into a suitable format by eliminating possible errors caused by lost or interrupted communications, the presence of noise or outliers, duplicate or incorrect data, etc. The load forecasting model is trained using historical load data and significant climatic variables discovered through correlation analysis. With a minimum MAPE and RMSE for every testing scenario, the proposed artificial neural network model yields the greatest forecasting performance for the used system data. The efficacy of the proposed technique has been through a comparison of the acquired results with various alternative load forecasting methods.

An efficient management and better scheduling by the power companies are of great significance for accurate electrical load forecasting. There exists a high level of uncertainties in the load time series, which is challenging to make the accurate short-term load forecast (STLF), medium-term load forecast (MTLF), and long-term load forecast (LTLF). To extract the local trends and to capture the same patterns of short, and medium forecasting time series, we proposed long short-term memory (LSTM), Multilayer perceptron, and convolutional neural network (CNN) to learn the relationship in the time series. These models are proposed to improve the forecasting accuracy. The models were tested based on the real-world case by conducting detailed experiments to validate their stability and practicality. The performance was measured in terms of squared error, Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). To predict the next 24 hours ahead load forecasting, the lowest prediction error was obtained using LSTM with R2 (0.5160), MLP with MAPE (4.97), MAE (104.33) and RMSE (133.92). To predict the next 72 hours ahead of load forecasting, the lowest prediction error was obtained using LSTM with R2 (0.7153), MPL with MAPE (7.04), MAE (125.92), RMSE (188.33). Likewise, to predict the next one week ahead load forecasting, the lowest error was obtained using CNN with R2 (0.7616), MLP with MAPE (6.162), MAE (103.156), RMSE (150.81). Moreover, to predict the next one-month load forecasting, the lowest prediction error was obtained using CNN with R2 (0.820), MLP with MAPE (5.18), LSTM with MAE (75.12) and RMSE (109.197). The results reveal that proposed methods achieved better and stable performance for predicting the short, and medium-term load forecasting. The findings of the STLF indicate that the proposed model can be better implemented for local system planning and dispatch, while it will be more efficient for MTLF in better scheduling and maintenance operations.

Research on power load forecasting model of economic development zone based on neural network

Modelling electric and heat load profiles of non-residential buildings for use in long-term aggregate load forecasts

At present, China’s power load development is facing a new situation in which policies such as the new economic norm, industrial structure adjustment, energy conservation and emission reduction, etc. are being deeply promoted, load growth in some areas begin to ease, and volatility of load gradually become prominent, which increases the difficulty of medium and long-term load forecasting. In this context, in view of multi-correlation, uncertainty of influence of policy factors on power load, in order to improve the accuracy of load forecasting under the influence of policy factors, and solve the problem that policy factors are ambiguous, difficult to be quantified, and difficult to be integrated into load forecasting model, a medium and long-term load forecasting model considering policy factors is proposed. First, by analyzing the influence of various policies on power load, a hierarchical policy influencing factor index system that combines macro and micro levels is constructed to systematically reflect the influence of economy and policies on load under the new situation. Then, in view of the traditional grey relational analysis model’s insufficient consideration of the difference of historical data and future power development situation, by respectively weighting historical periods and factor indexes, a quantification analysis model of power load influencing factors based on two-way weighted grey relational analysis is proposed to quantify the influence of various policy factors on power load, achieve the combination of subjective weighting and objective weighting,and obtain quantification weights. Finally, the weighted fuzzy cluster analysis method combined with weights is used to predict load under the influence of policy factors. The proposed model can better solve the difficulty of medium and long-term load forecasting caused by the volatility of load under the influence of policy factors, and is suitable for medium and long-term load forecasting under the background of policy changes. The analysis of calculation examples shows that compared with traditional grey relational analysis model, the quantification results of proposed methods are more realistic, compared with traditional prediction methods such as time series extrapolation and elasticity coefficient, proposed method has better prediction accuracy and engineering application value.