Load Demand Forecasting Research Articles

Integration of Renewable Based Distributed Generation for Distribution Network Expansion Planning

Electrical energy is critical to a country’s socioeconomic progress. Distribution system expansion planning addresses the services that must be installed for the distribution networks to meet the expected load need, while also meeting different operational and technical limitations. The incorporation of distributed generation sources (DGs) alters the operating characteristics of modern power systems, resulting in major economic and technical benefits, such as simplified distribution network expansion planning, lower power losses, and improved voltage profile. Thus, in this study, an analytical method is used to design the expansion planning of the Addis North distribution network considering the integration of optimal sizes of distributed generations for the projected demand growths. To evaluate the capability of the existing Addis North distribution network and its capability to supply reliable power considering future expansion, the load demand forecast for the years 2020–2030 is done using the least square method. The performance evaluation of the existing and the upgraded network considering the existing and forecasted load demand for the years 2030 is done using ETAP software. Accordingly, the results revealed that the existing networks cannot meet the existing load demand of the town, with major problems of increased power loss and a reduced voltage profile. To mitigate this problem, the Addis North feeder-1 distribution network is upgraded and for each study case, the balanced and positive sequence load flow analysis was executed and the maximum total real and reactive power losses were found at bus 29. The result shows that the upgraded network of bus 29 was the optimal location of DG and its size was 9.93 MW. After the optimal size of DG was placed at this bus, the real and reactive power losses of the upgraded networks were 0.2939 MW and 0.219 MVAr, respectively. At bus 29 the maximum power losses reduction and voltage profile improvements were found. The active and reactive power losses were minimized by 21.285% and 19.633% respectively and the voltage profiles were improved by 8.78%. Thus, in the predicted year 2030, DG power sources could cover 61.12% of the feeder-1 power requirements.

Short-term forecasting of the Italian load demand during the Easter Week

Short-term forecasting of the Italian load demand during the Easter Week

Smart energy management for optimal economic operation in grid-connected hybrid power system

ABSTRACT This manuscript presents a hybrid method for smart energy management (EM) in grid connected microgrid (MG) system. The grid connected micro grid system consists of photovoltaic (PV), wind turbine (WT), micro turbine (MT), and battery. The proposed method is the combined execution of Radial Basis Function Neural Network (RBFNN) and Squirrel Search Algorithm (SSA), hence it is called RBFNN-SSA method. Here, the necessary load demand of grid-connected MG system is constantly monitored by AI strategy. SSA has developed the perfect combination of MG considering the forecast load demand. The major intention of the RBFNN-SSA method is fuel cost involvement, grid power hourly power variation, operation with maintenance cost of grid connected micro grid system. The constraints are the accessibility of renewable energy sources (RES), power requirement and state of charge (SoC) of storage elements. Batteries are used as an energy source, to stabilize and allow the renewable power system units for maintaining constant output power. The proposed method is activated in MATLAB/Simulink working site. Then, the efficiency is assessed with existing methods such as improved artificial bee colony (IABC), bacterial foraging optimizer and artificial neural network (BFOANN), ant lion optimizer (ALO), grasshopper optimization algorithm with particle swarm optimization including artificial neural network (GOAPSNN). The root mean square error (RMSE), mean absolute percentage error (MAPE), and mean bias error (MBE) of proposed and existing methods under 50 and 100 count of trails are also analyzed. The proposed technique achieves the RMSE is 9.3, MAPE is 4.2, and MBE is 2 for 50 number of trails. For 100 count of trails, the proposed method achieves the RMSE is 13.5, MAPE is 3.9 and MBE is 5.7. The mean, median and standard deviation of RBFNN-SSA method achieves 0.9681, 0.9062 and 0.1099. The elapsed time of RBFNN-SSA method attains 30.15 s.

ELECTRIC LOAD AND POWER FORECASTING USING ENSEMBLE GAUSSIAN PROCESS REGRESSION

We propose a new forecasting method for predicting load demand and generation scheduling. Accurate week-long forecasting of load demand and optimal power generation is critical for efficient operation of power grid systems. In this work, we use a synthetic data set describing a power grid with 700 buses and 134 generators over a 365-days period with data synthetically generated at an hourly rate. The proposed approach for week-long forecasting is based on the Gaussian process regression (GPR) method, with prior covariance matrices of the quantities of interest (QoI) computed from ensembles formed by up to twenty preceding weeks of QoI observations. Then, we use these covariances within the GPR framework to forecast the QoIs for the following week. We demonstrate that the the proposed ensemble GPR (EGPR) method is capable of accurately forecasting weekly total load demand and power generation profiles. The EGPR method is shown to outperform traditional forecasting methods including the standard GPR and autoregressive integrated moving average (ARIMA) methods.

A Study of Load Demand Forecasting Models in Electricity using Artificial Neural Networks and Fuzzy Logic Model

Since load time series are very changeable, demand forecasting of the short-term load is challenging based on hourly, daily, weekly, and monthly load forecast demand. As a result, the Turkish Electricity Transmission Company (TEA) load forecasting is proposed in this paper using artificial neural networks (ANN) and fuzzy logic (FL). Load forecasting enables utilities to purchase and generate electricity, load shift, and build infrastructure. A load forecast was classified into three sorts (hourly, weekly and monthly). Over time, forecasting power loads with artificial neural networks and fuzzy logic reveals a massive decrease in ANN and a progressive increase in FL from 24 to 168 hours. As illustrated, fuzzy logic and artificial neural networks outperform regression algorithms. This study has the highest growth and means absolute percentage error (MAPE) rates compared to FL and ANN. Although regression has the highest prediction growth rate, it is less precise than FL and ANN due to their lower MAPE percentage. Artificial Neural Networks and Fuzzy Logic are emerging technologies capable of forecasting and mitigating demand volatility. Future research can forecast various Turkish states using the same approach.

A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment

Recently, with the establishment of new thermal regulation, the energy efficiency of buildings has increased significantly, and various deep learning-based methods have been presented to accurately forecast the heating load demand of buildings. However, all of these methods are executed on a dataset with specific distribution and do not have the property of global forecasting, and have no guarantee of data privacy against cyber-attacks. This paper presents a novel approach to heating load demand forecasting based on Cyber-Secure Federated Deep Learning (CSFDL). The suggested CSFDL provides a global super-model for forecasting heating load demand of different local clients without knowing their location and, most importantly, without revealing their privacy. In this study, a CSFDL global server is trained and tested considering the heating load demand of 10 different clients in their building environment. The presented results, including a comparative study, prove the viability and accuracy of the proposed procedure.

Recurring Multi-layer Moving Window Approach to Forecast Day-ahead and Week-ahead Load Demand Considering Weather Conditions

The incorporation of weather variables is crucial in developing an effective demand forecasting model because electricity demand is strongly influenced by weather conditions. The dependence of demand on weather conditions may change with time during a day. Therefore, the time stamped weather information is essential. In this paper, a multi-layer moving window approach is proposed to incorporate the significant weather variables, which are selected using Pearson and Spearman correlation techniques. The multi-layer moving window approach allows the layers to adjust their size to accommodate the weather variables based on their significance, which creates more flexibility and adaptability thereby improving the overall performance of the proposed approach. Furthermore, a recursive model is developed to forecast the demand in multi-step ahead. An electricity demand data for the state of New South Wales, Australia are acquired from the Australian Energy Market Operator and the associated results are reported in the paper. The results show that the proposed approach with dynamic incorporation of weather variables is promising for day-ahead and week-ahead load demand forecasting.

Artificial Neural Network Based Long Term Electrical Peak Load Demand Forecasting in Case of South District Ethiopian Power System

Artificial Neural Network Based Long Term Electrical Peak Load Demand Forecasting in Case of South District Ethiopian Power System

Microgrid Energy Management System for Residential Microgrid Using an Ensemble Forecasting Strategy and Grey Wolf Optimization

Microgrid (MG) is a small-scale grid that consists of multiple distributed energy resources and load demand. The microgrid energy management system (M-EMS) is the decision-making centre of the MG. An M-EMS is composed of four modules which are known as forecasting, scheduling, data acquisition, and human-machine interface. However, the forecasting and scheduling modules are considered the major modules from among the four of them. Therefore, this paper proposed an advanced microgrid energy management system (M-EMS) for grid-connected residential microgrid (MG) based on an ensemble forecasting strategy and grey wolf optimization (GWO) based scheduling strategy. In the forecasting module of M-EMS, the ensemble forecasting strategy is proposed to perform the short-term forecasting of PV power and load demand. The GWO based scheduling strategy has been proposed in scheduling module of M-EMS to minimize the operating cost of grid-connected residential MG. A small-scale experiment is conducted using Raspberry Pi 3 B+ via the python programming language to validate the effectiveness of the proposed M-EMS and real-time historical data of PV power, load demand, and weather is adopted as inputs. The performance of the proposed forecasting strategy is compared with ensemble forecasting strategy-1, particle swarm optimization based artificial neural network, and back-propagation neural network. The experimental results highlight that the proposed forecasting strategy outperforms the other strategies and achieved the lowest average value of normalized root mean square error of day-ahead prediction of PV power and load demand for the chosen day. Similarly, the performance of GWO based scheduling strategy of M-EMS is analyzed and compared for three different scenarios. Finally, the experimental results prove the outstanding performance of the proposed scheduling strategy.

The stochastic short-term hydropower generation scheduling considering uncertainty in load output forecasts

Load demand forecasts for short-term hydropower generation scheduling (STHGS) has stochastic essence which is impacted by multiple uncertainties from hydrometeorology, streamflow and compensation operation. These dynamically changed uncertainties propagate to startup or shutdown transition, load dispatch and water consumption of hydro-units. However, dynamic uncertainty propagation process is not expounded effectively and its effects on STHGS are ignored to some extent when planners made short-term hydropower plan, leading to potential decision error. Moreover, computation efficiency and precision are also crucial for managers to make reliable decisions and adjustments timely. To this end, framework is developed to provide efficient model solver and identify effect of uncertain load demand forecast on STHGS. The framework contains: (1) stochastic load demand forecast based on martingale model of forecast evolution (MMFE); (2) enhanced shuffled frog leaping algorithm (SFLA) incorporating parallel computing; (3) risk quantification and evolvement revelation based on risk of exceedance (ROE). The STHGS for Three Gorges hydropower station (TGHS) is studied to demonstrate framework. The stochastic STHGS model is efficient solved by algorithms proposed. The propagation of forecast uncertainty and effect of different uncertainty levels and temporal correlations on STHGS is exhibited and fully discussed based on power load scenarios dynamically updated by MMFE.

Combination of Side‐Blotched Lizard and Chaos Game Optimization based distributed energy management for microgrid system

In the last decade, numerous energy management techniques have been presented. All of them have common objectives of minimizing the cost, PAR, and carbon emissions. In this manuscript, an optimal energy management (EM) on grid connected micro grid (MG) choosing energy scheduling with low emission and cost using hybrid technique is proposed. The proposed system is combination of Side-Blotched Lizard Algorithm (SBLA) and Chaos Game Optimization (CGO) Algorithm; thus it is called SBLA-CGO technique. The micro grid system consists of Photo-Voltaic (PV) system, Wind Turbine (WT), Battery Storage (BS), and Fuel cell (FC). The needed load demand of the grid connected MG system is continuously measured by SBLA method. Perfect combination of MG is increased via CGO along forecasted load demand circumstance. Moreover, the renewable energy (RE) predicting errors are assessed twice by micro grid EM to diminish the control. Several renewable energy source (RES) are considered by MG scheduling process to reduce the cost of electricity utilizing first method. The second method consists of balancing the power flow (PF) and reducing the effects of forecast errors according to rule given as programmed power reference. The major purpose of proposed method is assessed through the incorporation of FC, variation of hourly power of electrical network, cost of operation through preservation of system of microgrid linked to the network. According to RES, the power requirement and SOC of storage elements are the conditions. Batteries are used from source of energy to maintain and allow the units of renewable energy system to continue to operate at constant and stable power output. The proposed method is compared with other existing methods. The fitness of the proposed technique with the existing one is evaluated and the adequacy of proposed technique is 3.069. With this output results can know the advantage of proposed method and verify its effectiveness in solving the complexity.

Electrical Load Demand Forecasting Using Feed-Forward Neural Networks

The higher share of renewable energy sources in the electrical grid and the electrification of significant sectors, such as transport and heating, are imposing a tremendous challenge on the operation of the energy system due to the increase in the complexity, variability and uncertainties associated with these changes. The recent advances of computational technologies and the ever-growing data availability allowed the development of sophisticated and efficient algorithms that can process information at a very fast pace. In this sense, the use of machine learning models has been gaining increased attention from the electricity sector as it can provide accurate forecasts of system behaviour from energy generation to consumption, helping all the stakeholders to optimize their activities. This work develops and proposes a methodology to enhance load demand forecasts using a machine learning model, namely a feed-forward neural network (FFNN), by incorporating an error correction step that involves the prediction of the initial forecast errors by another FFNN. The results showed that the proposed methodology was able to significantly improve the quality of load demand forecasts, demonstrating a better performance than the benchmark models.

Electrical power supply consumption in education sector and energy audit: Case study of University of Jos


 
 
 Electricity supply has been identified as the key constraint to industrialization and economic development in Nigeria. The unbundling of the power sector was aimed at boosting electricity supply, this effort has yielded some appreciable results, but not very significant. As a result of the low power generation and distribution, Nigeria’s federal government is working towards solving the prevailing problems of inadequate power in some key sectors by building power generating plants in some of the institutions of learning in the country. This paper looks at the determinants of electrical energy consumption and electrical energy audit, a case study of the University of Jos. The load profiles demand survey, load demand forecast and other important factors were investigated. The result revealed that there is available power of 22–23 hours from the national grid and the balance 1–2 hours of power is supplied by the generating sets, good savings in the cost of diesel and maintenance. An annual excess of 2,199,900 kWH is enjoyed by the university over the national per capita power consumption.
 
 

Forecasting Electricity Load Demand- An Power System Planning

Moving holiday electricity load demand forecasting is one of the most challenging topics in the forecasting area. Forecasting electricity load demand is essential because it involves projecting the peak demand level. Overestimation of future loads results in excess supply. Wastage of this load is not welcome by the international energy network. An underestimation of load leads to failure in providing adequate reserve, implying high costs. Many factors can influence the electricity load demand, such as previous load demand, type of the day, coincidence with other holidays and the impact of major events. Hence, 12 independent variables were considered in constructing the regression model to forecast moving holiday electricity load demand. This study investigates Malaysia’s daily electricity load demand data using multiple linear regression to forecast electricity load demand on moving holidays, such as Hari Raya AidilFitri, Chinese New Year, Hari Raya AidilAdha, and Deepavali from September 2016 to October 2017. The result shows six independent variables are significant from the several method variables selections. Overall, the constructed models from this study give promising results and can forecast for next year’s moving holiday electricity load demand with a sample forecasting error of 3.7% on the day of the moving holiday.

PRONÓSTICO DE DEMANDA DE ENERGÍA ELÉCTRICA USANDO PROCESOS GAUSSIANOS: UN ANÁLISIS COMPARATIVO

Abstract—Load demand forecasting is an essential component for planning power systems, and it is an invaluable tool to grid operators or customers. Many methods have been proposed to provide reliable estimates of electric load demand, but few methods can address the problem of predicting energy demand from a probabilistic point of view. One of them is the Gaussian processes (GP) that considering an adequate covariance function are suitable tools to carry out this load forecasting task. In this article, we show how to use Gaussian processes to predict elec- trical energy demand. Additionally, we thoroughly test various covariance functions and provide a new one. The performance of the proposed methodology was tested on two real data sets, showing that GPs are competitive alternatives for short-term load demand forecasting compared to other state-of-the-art methods

Resilient Predictive Control Coupled with a Worst-Case Scenario Approach for a Distributed-Generation-Rich Power Distribution Grid

In a context of accelerating deployment of distributed generation in power distribution grid, this work proposes an answer to an important and urgent need for better management tools in order to ‘intelligently’ operate these grids and maintain quality of service. To this aim, a model-based predictive control (MPC) strategy is proposed, allowing efficient re-routing of power flows using flexible assets, while respecting operational constraints as well as the voltage constraints prescribed by ENEDIS, the French distribution grid operator. The flexible assets used in the case study—a low-voltage power distribution grid in southern France—are a biogas plant and a water tower. Non-parametric machine-learning-based models, i.e., Gaussian process regression (GPR) models, are developed for intraday forecasting of global horizontal irradiance (GHI), grid load, and water demand, to better anticipate emerging constraints. The forecasts’ quality decreases as the forecast horizon grows longer, but quickly stabilizes around a constant error value. Then, the impact of forecasting errors on the performance of the control strategy is evaluated, revealing a resilient behaviour where little degradation is observed in terms of performance and computation cost. To enhance the strategy’s resilience and minimise voltage overflow, a worst-case scenario approach is proposed for the next time step and its contribution is examined. This is the main contribution of the paper. The purpose of the min–max problem added upstream of the main optimisation problem is to both anticipate and minimise the voltage overshooting resulting from forecasting errors. In this min–max problem, the feasible space defined by the confidence intervals of the forecasts is searched, in order to determine the worst-case scenario in terms of constraint violation, over the next time step. Then, such information is incorporated into the decision-making process of the main optimisation problem. Results show that these incidents are indeed reduced thanks to the min–max problem, both in terms of frequency of their occurrence and the total surface area of overshooting.

Energy management system for microgrids using weighted salp swarm algorithm and hybrid forecasting approach

The concept of a microgrid (MG) has been introduced to integrate the conventional generators, different renewable energy resources and energy storage systems (ESS) to meet the specific load demand. However, the intermittent nature of renewable energy resources produces a variable output, which drives an imbalance between power generation and demand in MG. The ESS is utilized to makes a balance between power generation and demand. When several renewable energy resources and ESS are available in MG as energy resources, then an energy management system (EMS) is required that can handle the stochastic nature of renewable energy resources, schedule the power of renewable energy resources and ESS for managing the power flow among MG resources and main grid while ensuing cost-effective operation. Therefore, this paper proposed an optimum EMS that aims to minimize the overall operating cost of grid-connected MG along with the short-term forecasting of PV power and load demand. The proposed EMS consists of four modules: forecasting, scheduling, data acquisition (DAQ), and human–machine interface (HMI) modules. An improved hybrid forecasting approach that combines a 3-level stationary wavelet transform (SWT) and grey wolf optimization-based least-square support vector machine (GWO-LSSVM) is proposed in the forecasting module to achieve day-ahead forecasting of PV power and load demand. In the scheduling module, the weighted salp swarm algorithm-based scheduling is applied to achieve the optimum power flow of grid-connected MG. Then, the DAQ and HMI module is used to monitor, analyze, and modified the input variables of the forecasting and scheduling module. The MATLAB/Simulink environment is then used to simulate the proposed EMS for grid-connected MG. Finally, numerical results demonstrate the efficiency of the proposed EMS for grid-connected MG with commercial load demand over the existing competitive approaches.

An adaptive backpropagation algorithm for long-term electricity load forecasting.

Artificial Neural Networks (ANNs) have been widely used to determine future demand for power in the short, medium, and long terms. However, research has identified that ANNs could cause inaccurate predictions of load when used for long-term forecasting. This inaccuracy is attributed to insufficient training data and increased accumulated errors, especially in long-term estimations. This study develops an improved ANN model with an Adaptive Backpropagation Algorithm (ABPA) for best practice in the forecasting long-term load demand of electricity. The ABPA includes proposing new forecasting formulations that adjust/adapt forecast values, so it takes into consideration the deviation between trained and future input datasets' different behaviours. The architecture of the Multi-Layer Perceptron (MLP) model, along with its traditional Backpropagation Algorithm (BPA), is used as a baseline for the proposed development. The forecasting formula is further improved by introducing adjustment factors to smooth out behavioural differences between the trained and new/future datasets. A computational study based on actual monthly electricity consumption inputs from 2011 to 2020, provided by the Iraqi Ministry of Electricity, is conducted to verify the proposed adaptive algorithm's performance. Different types of energy consumption and the electricity cut period (unsatisfied demand) factor are also considered in this study as vital factors. The developed ANN model, including its proposed ABPA, is then compared with traditional and popular prediction techniques such as regression and other advanced machine learning approaches, including Recurrent Neural Networks (RNNs), to justify its superiority amongst them. The results reveal that the most accurate long-term forecasts with the minimum Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) values of (1.195.650) and (0.045), respectively, are successfully achieved by applying the proposed ABPA. It can be concluded that the proposed ABPA, including the adjustment factor, enables traditional ANN techniques to be efficiently used for long-term forecasting of electricity load demand.

Optimal Allocation and Planning of Distributed Power Generation Resources in a Smart Distribution Network Using the Manta Ray Foraging Optimization Algorithm

In this study, optimal allocation and planning of power generation resources as distributed generation with scheduling capability (DGSC) is presented in a smart environment with the objective of reducing losses and considering enhancing the voltage profile is performed using the manta ray foraging optimization (MRFO) algorithm. The DGSC refers to resources that can be scheduled and their generation can be determined based on network requirements. The main purpose of this study is to schedule and intelligent distribution of the DGSCs in the smart and conventional distribution network to enhance its operation. First, allocation of the DGSCs is done based on weighted coefficient method and then the scheduling of the DGSCs is implemented in the 69-bus distribution network. In this study, the effect of smart network by providing real load in minimizing daily energy losses is compared with the network includes conventional load (estimated load as three-level load). The simulation results cleared that optimal allocation and planning of the DGSCs can be improved the distribution network operation with reducing the power losses and also enhancing the voltage profile. The obtained results confirmed superiority of the MRFO compared with well-known particle swarm optimization (PSO) in the DGSCs allocation. The results also showed that increasing the number of DGSCs reduces more losses and improves more the network voltage profile. The achieved results demonstrated that the energy loss in smart network is less than the network with conventional load. In other words, any error in forecasting load demand leads to non-optimal operating point and more energy losses.

Emerging Harris Hawks Optimization based load demand forecasting and optimal sizing of stand-alone hybrid renewable energy systems– A case study of Kano and Abuja, Nigeria

This paper presents load forecasting and optimal sizing for minimizing the Annualized Cost of the System (ACS) of a stand-alone photovoltaic (PV)/wind/battery hybrid renewable energy system. To achieve load forecasting, the Support Vector Regression (SVR) was integrated with the emerging Harris Hawks Optimization (HHO) and Particle Swarm Optimization (PSO) algorithms to form two hybrid SVR algorithms (SVR-HHO and SVR-PSO). The single SVR and the two obtained hybrid SVR algorithms were used to predict the load demand variability of remote areas in Kano and Abuja, Nigeria. For optimal sizing, a PSO algorithm was used. The prediction accuracy of the algorithms was evaluated using Correlation Coefficient (R), Coefficient of Determination (R2), Mean Square Error (MSE), and Root Mean Square Error (RMSE). The results show that both hybrid SVR algorithms outperformed the single SVR in terms of prediction accuracy. Furthermore, SVR-HHO has the highest goodness of fit and lowest prediction error. Besides, the SVR-HHO proved merit over SVR-PSO despite its reliability. These results concluded that metaheuristic algorithms are more promising in forecasting load demand and hence can serve as a reliable tool for decision making.