Energy Demand Forecasting Research Articles

Energy Demand Forecast in Yunnan Province Based on Seq2Seq Model

Energy demand forecast has an important practical significance for the sustainable development of the national economy, the reasonable allocation of resources, and the construction of modernization goals. This study is based on the analysis of coal, electricity, natural gas, and other energy data in Yunnan Province from 2011 to 2018 and uses long short-term memory, sequence to sequence, deep learning, and ridge regression coupling methods to construct an energy demand forecast model in Yunnan Province. Forecast results show the following. The total energy consumption of Yunnan Province from 2021 to 2025 will continue to increase. Moreover, the coal consumption of Yunnan Province will continue to decline from 2021 to 2025. Furthermore, the electricity consumption of Yunnan will increase by about 8.02% year-on-year from 2021 to 2025. The experiment proves that the forecasting effect of the energy demand forecast model proposed in this study is excellent.

Big data analysis and prediction method of multidimensional space-time features of energy internet based on fuzzy rough model

Nowadays, energy has become a hot issue of concern to the whole society. With the unbalanced distribution of resources in the world and more severe climate change, the constraints of resource conditions and environmental status on global energy development are becoming stronger and stronger. The rapid development of the Internet, as well as the proposal of the energy Internet, has a better application in the analysis of energy demand, which can effectively alleviate the contradiction between energy and environment. Aiming at the big data of energy Internet and based on the advantages of fuzzy rough model, this paper studies a method of big data analysis and prediction of multidimensional space-time characteristics of energy Internet based on fuzzy rough model. Firstly, according to the spatio-temporal characteristics of energy Internet data, extract the multidimensional spatio-temporal characteristics of energy internet. Secondly, rough set and fuzzy set are two commonly used mathematical tools, and the combination of the two fuzzy rough models can more fully mine data information. In view of the shortcomings of the commonly used fuzzy rough set reduction algorithm, a reduction algorithm based on conditional entropy is proposed. Finally, taking multidimensional space-time characteristics as input, combining the advantages of fuzzy rough model and neural network, a prediction model is established to analyze and forecast energy demand. The simulation experiments show that the design method is feasible and superior, and can achieve the prediction of energy demand well, so as to make more rational use of energy.

Methodology for forecasting electricity consumption by Grey and Vector autoregressive models

Forecasting energy demand in general, and electricity demand in particular, requires the developing reliable forecasting tools that can be used to monitor the evolution of consumers’ energy needs more accurately. The proposed new hybrid GM(1,1)-VAR(1) model is meant for that purpose. The latter is based on the Grey and Vector autoregressive approaches, and makes it possible to predict future demand, by taking into account economic and demographic determinants with an exponential growth trend. With an associated APE of 1.5, a MAPE of 1.628%, and an RMSE of 15.42, this new model thus presents better accuracy indicators than hybrid models of the same nature. Also, it proves to be as accurate as some recent hybrid artificial intelligence models. The model is thus a reliable forecasting tool that can be used to monitor the evolution of energy demand.•The Grey and Vector autoregressive models are coupled to improve their accuracy.•Five economic and demographic parameters are included in the new hybrid model.•This new model is a reliable forecasting tool for assessing energy demand.

Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

Industrial and building sectors demand efficient smart energy strategies, techniques of optimization, and efficient management for reducing global energy consumption due to the increasing world population. Nowadays, various artificial intelligence (AI) based methods are utilized to perform optimal energy forecasting, different simulation tools, and engineering methods to predict future demand based on historical data. Nevertheless, nonlinear energy demand modeling is still unfledged for a better solution to handle short-term and long-term dependencies and avoid static nature because it is purely on historical data-driven. In this paper, we propose an ensemble deep learning-based approach to predict and forecast energy demand and consumption by using chronological dependencies. Our system initially processes the data, cleaning, normalization, and transformation to ensure the model performance. Furthermore, the preprocess data is fed to proposed ensemble model to extract hybrid discriminative features by using convolution neural network (CNN), stacked, and bi-directional long-short term memory (LSTM) architectures. We trained our proposed system on the historical data to forecast the energy demand and consumption with a different time interval. In the proposed technique, we utilized the concept of active learning based on moving windows to ensure and improve the prediction performance of the system. The proposed system could be applicable to employ energy consumption in industrial and building sectors to demonstrate their significance and effectiveness. We evaluated the proposed system by using benchmark, residential UCI, and local Korean commercial building datasets. We conducted different extensive experimentation to show the error rate and used various kinds of evaluation matrices, which indicate the lower error rate of the proposed system.

Energy Efficiency Assessment of Cryogenic Minimum Quantity Lubrication Cooling for Milling Operations

Cryogenic minimum quantity lubrication (CMQL) extends the application spectrum of cryogenic cooling by the possibility of lubrication. This enables the proportion of both cooling and lubrication capacity to be adapted to the process as required. Especially liquid CO2 has been established for the CMQL. This application enables a sustainable use of CO2 in a circular cycle opposed to its emission to the atmosphere. For a comparison of conventional flood cooling with CMQL, the specific energy has to be determined in addition to the process-related suitability. Specifications by the European Commission and the desire for sustainable production require a quantification of the environmental impact. For the determination of these product carbon footprints, energy demand forecasts are essential.This paper presents a method for calculating the energy demand for milling processes under CMQL and wet machining according to the life cycle assessment EN ISO 14044 taking the material flows into account. The considered material flows include the cutting energy of the process, the energy to provide the water for the emulsion for flood cooling, the energy to liquefy the CO2, the energy for the oil refining process for emulsion and CMQL, the energy for the coolant pumps and the energy for the manufacturing of the tools. The balancing is carried out for a defined functional unit. Due to the different tool lifetimes, there are large fluctuations in the energy requirements. It is shown that despite the high energy expenditure for the provision of CO2 and the energy supply for flood cooling, the most significant influence on the energy expenditure results from the manufacture of the tools. By increasing the tool life and increasing the number of tool regrinding cycles, the energy requirement for the functional unit can be reduced.

Analysis of Guangdong Energy Demand Forecast Based on DIP-REM Model

Computer data mining technology has a positive impact on the accurate prediction of China's energy demand. In order to effectively alleviate the energy crisis that China is currently facing, and further forecast the energy demand, it will provide an active driving force for the sustainable economic development of our country in the future. In this study, the authors studied the current energy use trends in China, and then the authors used the DIP-REM model to predict their future development needs based on a study of the use of energy resources in Guangdong Province. This model can accurately predict the future energy expansion value of Guangdong Province. The research aims to provide a reference for related research on China's energy demand forecast.

Beijing-Tianjin-Hebei Energy Demand Combination Forecast Analysis

Energy demand forecasting is the basis for responding to high-quality economic development requirements and targeted adjustments to the Beijing-Tianjin- Hebei energy structure. This paper selects five main factors that affect energy demand, constructs a combined forecasting model of a combination of multi-factor gray neural network and ARIMA-BP neural network, and introduces the idea of chaos optimization on this basis to simulate and analyse data from 2012 to 2016, and predict the energy demand in the Beijing-Tianjin-Hebei region in 2020 and 2025.The results show that: 1. Compared with the CGA-ARIMA-BP model and the CGA-GNN model, the CGA-GNN-ARIMA-BP model has higher prediction accuracy; 2. It is estimated that in 2020 and 2025, the energy demand in the Beijing-Tianjin-Hebei region will reach 493 and 552 million tons of standard coal.

Prediction of Transportation Energy Demand by Novel Hybrid Meta-Heuristic ANN

Prediction of Transportation Energy Demand by Novel Hybrid Meta-Heuristic ANN

Prediction of Hydropower Generation and Energy Demand by Representative Concentration Representative Scenarios and Optimal Ann Model

Prediction of Hydropower Generation and Energy Demand by Representative Concentration Representative Scenarios and Optimal Ann Model

Prediction and estimation model of energy demand of the AMR with cobot for the designed path in automated logistics systems

The ecosystem of the Industry 4.0 involves many new technologies, such as autonomous mobile robots (AMR) and cobots (collaborative robots), these are characterized with higher flexibility and cost effectiveness which makes them more suitable for automated internal logistics systems. The evaluation of energy consumption of AMRs for a designed path in a real case scenario using analytical tools are challenging. This paper proposes a method of evaluation of the sustainability of new technologies of Industry 4.0 in internal logistics.The proposed framework demonstrates data management technique of the industrial robots. Since, the AMR with manipulator perform different tasks as a single system in logistics there is big demand to develop model of cyber physical system. During task execution measured robots’ physical parameters used as input data to perform analytics. Moreover, acquired data from different condition use cases have been used to monitor the battery behaviour of the AMR and preliminary results of the linear regression model is presented.

Determination of industrial energy demand in Turkey using MLR, ANFIS and PSO-ANFIS

Energy is one of the most critical inputs in social and economic development, is an essential factor in increasing living standards and creating sustainable development. Since energy is an indispensable input in all sectors, energy dependence contributed to the necessity of countries' energy policy. It has critical importance to predict energy demand to determine energy policies. According to Turkey's annual energy consumption, the industry sector has consumed the most energy in the last five years. The prediction and analysis of energy demand with economic data in the industrial sector is an essential indicator of the economic development relationship between energy demand and industry. In this study, Multiple Linear Regression (MLR), Adaptive Neuro-Fuzzy Inference System (ANFIS), and optimized ANFIS with Particle Swarm Optimization (PSO) methods are employed to forecast energy demand for Turkish industrial sectors. The indicators which affect energy consumption were determined to estimate the energy demand. The 30-year dataset between 1990 and 2019 was split as training and test set. MLR, ANFIS and PSO- ANFIS were compared according to performance evaluation, and the most proper model was identified. The coefficient of determination (R2) for PSO-ANFIS, MLR, and ANFIS models are 0.9951, 0.9889, and 0.9932 in the training stage, and 0.9423, 0.9181, and 0.8776 in the testing stage, respectively. The study results indicated that the PSO-ANFIS model showed superior prediction capability with the least estimation error than MLR and ANFIS models. Consequently, parameters tuned PSO-ANFIS is able to predict the industrial energy demand in Turkey with high accuracy.

Robust Optimal Operation of an Energy Supply System Based on Interval Prediction of Energy Demands

Robust Optimal Operation of an Energy Supply System Based on Interval Prediction of Energy Demands

Reducing Grid Distortions Utilizing Energy Demand Prediction and Local Storages

Energy storage systems will play a key role in the establishment of future smart grids. Specifically, the integration of storages into the grid architecture serves several purposes, including the handling of the statistical variation of energy supply through increasing usage of renewable energy sources as well as the optimization of the daily energy usage through load scheduling. This article is focusing on the reduction of the grid distortions using non-linear convex optimization. In detail an analytic storage model is used in combination with a load forecasting technique based on socio-economic information of a community of households. It is shown that the proposed load forecasting technique leads to significantly reduced forecasting errors (relative reductions up-to 14.2%), while the proposed storage optimization based on non-linear convex optimizations leads to 12.9% reductions in terms of peak to average values for ideal storages and 9.9% for storages with consideration of losses respectively. Furthermore, it was shown that the largest improvements can be made when storages are utilized for a community of households with a storage size of 4.6-8.2 kWh per household showing the effectiveness of shared storages as well as load forecasting for a community of households.

Electricity Demand Time Series Forecasting Based on Empirical Mode Decomposition and Long Short-Term Memory

Load forecasting is critical for a variety of applications in modern energy systems. Nonetheless, forecasting is a difficult task because electricity load profiles are tied with uncertain, non-linear, and non-stationary signals. To address these issues, long short-term memory (LSTM), a machine learning algorithm capable of learning temporal dependencies, has been extensively integrated into load forecasting in recent years. To further increase the effectiveness of using LSTM for demand forecasting, this paper proposes a hybrid prediction model that incorporates LSTM with empirical mode decomposition (EMD). EMD algorithm breaks down a load time-series data into several sub-series called intrinsic mode functions (IMFs). For each of the derived IMFs, a different LSTM model is trained. Finally, the outputs of all the individual LSTM learners are fed to a meta-learner to provide an aggregated output for the energy demand prediction. The suggested methodology is applied to the California ISO dataset to demonstrate its applicability. Additionally, we compare the output of the proposed algorithm to a single LSTM and two state-of-the-art data-driven models, specifically XGBoost, and logistic regression (LR). The proposed hybrid model outperforms single LSTM, LR, and XGBoost by, 35.19%, 54%, and 49.25% for short-term, and 36.3%, 34.04%, 32% for long-term prediction in mean absolute percentage error, respectively.

Forecast and Analysis of Regional Energy Demand Based on Grey Linear Regression Forecast Model

Energy is an important material basis for guaranteeing and promoting economic growth and social development. In order to predict the future energy demand for regional energy in Liaoning Province, this paper uses the gray forecast model to make reasonable predictions on regional energy in Liaoning. This paper first establishes a gray prediction model, analyzes the applicable environment and conditions of the gray prediction model, and secondly uses the gray prediction model to predict the energy of Liaoning Province from 2010 to 2019, and compares it with the actual data and elastic coefficient method. It shows that the prediction accuracy based on the gray prediction model is significantly higher than that of the traditional elasticity coefficient prediction method, which proves the scientificity and effectiveness of the model for regional energy demand prediction. Finally, on this basis, this paper uses the grey prediction model to analyze the energy of Liaoning Province from 2020 to 2029. The method and data can provide reliable data basis for the planning of Liaoning power grid and the evolution of the future power grid.

Integrated energy system planning research based on big data load prediction method

The planning of integrated energy system is a very complex multi-target, multi-constraint, nonlinear, random uncertainty mixed integrated combination optimization problem, its planning and design process should not only consider the interdependence between the system capacity, energy conversion, energy storage, energy use and other links, but also consider the interaction and integration of cold, hot, electricity and other multi-energy flows, which is essentially a non-deterministic polynomial difficult problem. China’s energy continues to develop rapidly, all kinds of sensors and intelligent equipment data is increasing, the data obtained in the equipment and all kinds of sensors collected energy load prediction related factors such as temperature, weather, wind speed and other data volume increased dramatically, the data dimension is also increasing, the scale of data has also increased from GB to TB or even higher, based on the traditional prediction methods and intelligent prediction methods, has been far below the load forecast desired to achieve accuracy and speed requirements, Therefore, the use of big data technology to predict energy demand is an important future direction.

The Estimation of Turkey's Energy Demand Through Artificial Neural Networks and Support Vector Regression Methods

Energy demand and consumption are very important for the development and progress of countries. Energy demand is increasing rapidly day by day, especially in developing countries. Energy policies should be determined correctly to sustain the industry sector and make the right investments. Forecasting energy demand in the near and long term is important for the strategy that countries will follow. In this study, by using the monthly electricity energy data realized in Turkey between January 2016 and March 2020 and other data affecting this, a model to estimate electrical energy consumption was developed. In this model, artificial neural networks (ANN) and support vector regression (SVR) were used as methods. This study used 15 independent variables as the input value, and Turkey's energy consumption value as the dependent variable was estimated. Correlation, coefficient of determination, MAE, MSE, RMSE, MAPE statistical methods were used to measure success and error rate, and both models were found to have acceptable error values and success estimation rates. According to the results, it was concluded that the ANN method was more successful than the SVR method.

Forecast of demand for the rmal energy for buildings of secondary educational institutions based on the properties of heteromorphism of their energy systems

THE PURPOSE. Improving the accuracy of forecast calculations of demand for energy resources is an urgent task, especially in the light of the Digital Energy of the Russian Federation program. Prediction is also required for he at supply systems. The complexity of the analysis is the lack of confirmation of the similarity properties of energy systems and complexes for buildings with similar functionality. On the example of buildings of secondary educational institutions located i n the territory of Moscow, the assumption of heteromorphism of thermal systems is proved. METHODS. In the work, an assumption was made that there were no significant changes in the data on the heat consumption of the energy facilities of schools, which was confirmed by the absence of changes in the average annual heat consumption and jumps in the monthly heat consumption diagrams. The amount of heat energy consumption measured and transferred to the IS is influenced by a number of additional factors: accura cy drift of heat energy metering devices; aging and overgrowing of the internal surfaces of the building's heating network equipment; physical aging and deterioration of the building envelope and deterioration of their thermal insulation performance. When compiling predicted energy consumption, this means that it is permissible to use not only statistical data about the analyzed object itself, but also about a variety of objects similar to those analyzed in structure and functionality. RESULTS. A set of input factors is proposed that makes it possible to accurately determine the predicted demand for thermal energy for buildings of secondary educational institutions. The possibility and similar accuracy of the results of forecasting the demand for thermal ene rgy is shown both through the use of multivariate regression analysis and artificial neural networks. CONCLUSION. ЭBased on the combined use of various mathematical approaches, it is proposed to use the methodology for forecasting energy demand by energy complexes and systems as a mechanism for determining the correctness of the transmitted meter readings.

Federated Learning Meets Contract Theory: Economic-Efficiency Framework for Electric Vehicle Networks

In this paper, we propose a novel economic-efficiency framework for an electric vehicle (EV) network to maximize the profits (i.e., the amount of money that can be earned) for charging stations (CSs). To that end, we first introduce an energy demand prediction method for CSs leveraging federated learning approaches, in which each CS can train its own energy transactions locally and exchange its learned model with other CSs to improve the learning quality while protecting the CS's information privacy. Based on the predicted energy demands, each CS can reserve energy from the smart grid provider (SGP) in advance to optimize its profit. Nonetheless, due to the competition among the CSs as well as unknown information from the SGP, i.e., the willingness to transfer energy, we develop a multi-principal one-agent (MPOA) contract-based method to address these issues. In particular, we formulate the CSs’ profit maximization as a non-collaborative energy contract problem under the SGP's unknown information and common constraints as well as other CSs’ contracts. To solve this problem, we transform it into an equivalent low-complexity optimization problem and develop an iterative algorithm to find the optimal contracts for the CSs. Through simulation results using a real CS dataset, we demonstrate that our proposed framework can enhance energy demand prediction accuracy up to 24.63 percent compared with other machine learning algorithms. Furthermore, our proposed framework can outperform other economic models by 48 and 36 percent in terms of the CSs’ utilities and social welfare (i.e., the total profits of all participating entities) of the network, respectively.

Forecasting the impact of climate change on thermal comfort using a weighted ensemble of supervised learning models

This work presents a weighted ensemble of supervised learning models for estimating the days of the year where compliance with the Adaptive Model of thermal comfort is exceeded. The ensemble combines several gradient boosting on decision tree algorithms and Bayesian logistic regression. In a presented case study, the model is trained on three summers of hourly weather data and indoor air temperature data of a south-facing, naturally-ventilated office in Vancouver, Canada. The model is then used to predict thermal comfort exceedance under a possible climate change scenario. It is found that the ensemble outperforms its individual models in terms of accuracy, precision, and similar metrics. In eight of nine trials using the ensemble to re-assess known history, the ensemble predicts total comfort-exceeding days within a margin of one day. Under the RCP 8.5 global climate change scenario, the model predicts annual comfort-exceeding days will double before the 2050s, by that point exceeding current local thermal comfort compliance guidelines. Future applications of the presented methodology may assist other areas of data-driven forecasting, such as peak energy demand prediction. It may also assist analysis of emerging space cooling solutions such as radiant cooling of free-running buildings.