Power Generation Planning Research Articles

Research on electricity consumption forecasting model based on wavelet transform and multi-layer LSTM model

In order to formulate a reasonable power generation and transmission plan, and effectively prevent the waste of electricity resources, a power consumption prediction model based on wavelet transform and multi-layer LSTM is proposed. In this paper, the sample data is first denoised based on wavelet transform to eliminate the volatility of the electricity consumption data itself. Then, based on the pre-processed samples, the multi-layer LSTM model is used for training, and the proposed model is verified and predicted daily power consumption based on the power consumption of the area controlled by U.S. electric power company. The experimental results show that the prediction performance of this model is better than traditional LSTM and bidirectional LSTM. The mean square error is 0.019, and the coefficient of determination R2 is as high as 0.997. It also shows that wavelet denoising can further improve the prediction performance of the model.

Implementation of 100% Electric Vehicle in Bali with the Supply of Potential Independent Solar Energy

<p class="02abstracttext">Electrical vehicle is the future of transportation. This thesis is about how to transform the usage of fossil fuel vehicle to electrical vehicle in Bali. Bali is an island with the longest distance from one of its districts to Denpasar city is 95,6 km. This distance is reachable by the common electrical vehicle that available in the market now. The usage of the electrical vehicle requires good development and planning, otherwise it will cause problem for the electrical systems. The consumption of electrical energy will increase. In 2019, Bali used 5,908 GWh electricity in a year. And if all the 2 wheels and 4-wheels vehicles now are electrical vehicle, it will require extra 2,823 GWh per year. It will impact the planning of power generation in Bali.Another challenge for the electrical systems is the duck curve problem. The habit of the user charges their vehicle will also impact the daily load curve of an electrical systems. If all the two wheels and four wheels vehicles now are electrical vehicle, and all users conduct the charging at the same time in 4 hours duration, the load will increase about 1,934 GW. The practical and applicable solution is the independent power producer concept by the solar PV. If every electric vehicle user installs the solar PV for their electrical vehicle consumption, this will solve all the problem.</p>

Uncovering Hidden Factors in Electricity Consumption Based on Gaussian Mixture Estimation

Load characteristics play an essential role in the planning of power generation and distribution. Various undiscovered factors, which could be socioeconomic, geographic, or climatic, make it possible to describe the electricity demand by a multimodal distribution. This letter proposes a novel method based on multimodal distributions to characterize the hidden factors in electricity consumption. Consequently, a new approach is developed to evaluate the impact of the underlying factors of electricity consumption. Some quantifiable and predictable factors are analyzed in developing multimodal distribution to describe the expected demand. Simulations based on synthetic and real-world data have been conducted to demonstrate the usefulness and robustness of the proposed method.

Machine Learning Empowered Electricity Consumption Prediction

Electricity, being the most efficient secondary energy, contributes for a larger proportion of overall energy usage. Due to a lack of storage for energy resources, over supply will result in energy dissipation and substantial investment waste. Accurate electricity consumption prediction is vital because it allows for the preparation of potential power generation systems to satisfy the growing demands for electrical energy as well as: smart distributed grids, assessing the degree of socioeconomic growth, distributed system design, tariff plans, demand-side management, power generation planning, and providing electricity supply stability by balancing the amount of electricity produced and consumed. This paper proposes a medium-term prediction model that can predict electricity consumption for a given location in Saudi Arabia. Hence, this study implemented a standalone Artificial Neural Network (ANN) model and bagging ensemble for predicting total monthly electricity consumption in 18 locations across Saudi Arabia. The dataset used in this research is gathered exclusively from the Saudi Electric Company. The pre-processing phase included normalizing the data using min-max method and mapping the cyclical attribute to its sine and cosine facets. The number of neurons and learning rate of the standalone model were optimized using hyperparameter tuning. Finally, the standalone model was tested against the bagging ensemble using the optimized ANN. The bagging ensemble with an optimized ANN as the chosen classifier outperformed the standalone ANN model. The results for the proposed model produced 0.9116 Correlation Coefficient (CC), 0.2836 Mean Absolute Percentage Error (MAPE), 0.4578, Root Mean Squared Percentage Error (RMSPE), 0.0298 MAE, and 0.069 Root Mean Squared Error (RMSE), respectively.

A Fast Calculation Method for Long-term Security-constrained Unit Commitment of Large-scale Power Systems with Renewable Energy

With the increase in the penetration rate of renewable energy, the planning and operation of power systems will face huge challenges. To ensure the sufficient utilization of renewable energy, the reasonable arrangement for the long-term power generation plan has become more crucial. Security-constrained unit commitment (SCUC) is a critical technical means to optimize the long-term power generation plan. However, the plentiful power sources and the complex grid structure in large-scale power systems will bring great difficulties to long-term SCUC. In this paper, we propose a fast calculation method for long-term SCUC of large-scale power systems with renewable energy. First, a method for unit status reduction based on temporal decomposition is proposed, which will reduce plenty of binary variables and intertemporal constraints in SCUC. Then, an efficient redundant constraint identification (RCI) method is developed to reduce the number of network constraints. Furthermore, a joint accelerated calculation framework for status reduction and RCI is formed, which can reduce the complexity of long-term SCUC while ensuring a high-precision feasible solution. In case studies, numerical results based on two test systems ROTS2017 and NREL-118 are analyzed, which verify the effectiveness and scalability of the proposed calculation method.

A Novel Runoff Forecasting Model Based on the Decomposition-Integration-Prediction Framework

Runoff forecasting is of great importance for flood mitigation and power generation plan preparation. To explore the better application of time-frequency decomposition technology in runoff forecasting and improve the prediction accuracy, this research has developed a framework of runoff forecasting named Decomposition-Integration-Prediction (DIP) using parallel-input neural network, and proposed a novel runoff forecasting model with Variational Mode Decomposition (VMD), Gated Recurrent Unit (GRU), and Stochastic Fractal Search (SFS) algorithm under this framework. In this model, the observed runoff series is first decomposed into several sub-series via the VMD method to extract different frequency information. Secondly, the parallel layers in the parallel-input neural network based on GRU are trained to receive the input samples of each subcomponent and integrate their output adaptively through the concatenation layers. Finally, the output of concatenation layers is treated as the final runoff forecasting result. In this process, the SFS algorithm was adopted to optimize the structure of the neural network. The prediction performance of the proposed model was evaluated using the historical monthly runoff data at Pingshan and Yichang hydrological stations in the Upper Yangtze River Basin of China, and seven various single and decomposition-based hybrid models were developed for comparison. The results show that the proposed model has obvious advantages in overall prediction performance, model training time, and multi-step-ahead prediction compared to several comparative methods, which is a reasonable and more efficient monthly runoff forecasting method based on time series decomposition and neural networks.

Design and operation optimization of city-level off-grid hydro–photovoltaic complementary system

Increasing attentions have been paid on the design and operation optimization of hydro-photovoltaic complementary systems due to the inherent uncertainty associated withthe solar energy. However, studies mainly focused on the household or community integrated power system while the city-level off-grid systems remained less explored. That was because both the large scale of the studied area and the complex factors associated with the city attached difficulties to the problems. This paper proposed an off-grid PV-hydro hybrid optimization model for the cities which were located nearby sufficient water resources based on Geographic Information System. The proposed model can guarantee the electricity demand with less economic cost and less storage facilities by taking full advantage of water resources. Firstly, the optimization-based economic analysis considering PV capital cost and hydroelectricity price was proposed to determine whether to install PV panels and the optimal size if install. Then, we set six scenarios to identify the relationship between the electricity consumption structure and the optimal PV scale due to the structure transformation according to the current energy policies. Finally, the detailed optimal power generation plan in typically weather conditions during operation period was analyzed. Results indicated that: (1) The city level off-grid PV-hydro complementary system was feasible according to the studied case. (2) The critical PV panel capital cost was 920 $/kW when the hydroelectricity price was 5¢/kW·h, and there was a linear relationship between these two parameters. (3) Optimal PV size was influenced by electricity consumption structure and peak month type, and the current structure transformation policy was beneficial for the PV-hydro systems. (4) The power generation plan varied a lot in different weather conditions and the detailed operation plan could be obtained in this paper.

A Two-Stage Short-Term Load Forecasting Method Using Long Short-Term Memory and Multilayer Perceptron

Load forecasting is an essential task in the operation management of a power system. Electric power companies utilize short-term load forecasting (STLF) technology to make reasonable power generation plans. A forecasting model with low prediction errors helps reduce operating costs and risks for the operators. In recent years, machine learning has become one of the most popular technologies for load forecasting. In this paper, a two-stage STLF model based on long short-term memory (LSTM) and multilayer perceptron (MLP), which improves the forecasting accuracy over the entire time horizon, is proposed. In the first stage, a sequence-to-sequence (seq2seq) architecture, which can handle a multi-sequence of input to extract more features of historical data than that of single sequence, is used to make multistep predictions. In the second stage, the MLP is used for residual modification by perceiving other information that the LSTM cannot. To construct the model, we collected the electrical load, calendar, and meteorological records of Kanto region in Japan for four years. Unlike other LSTM-based hybrid architectures, the proposed model uses two independent neural networks instead of making the neural network deeper by concatenating a series of LSTM cells and convolutional neural networks (CNNs). Therefore, the proposed model is easy to be trained and more interpretable. The seq2seq module performs well in the first few hours of the predictions. The MLP inherits the advantage of the seq2seq module and improves the results by feeding artificially selected features both from historical data and information of the target day. Compared to the LSTM-AM model and single MLP model, the mean absolute percentage error (MAPE) of the proposed model decreases from 2.82% and 2.65% to 2%, respectively. The results demonstrate that the MLP helps improve the prediction accuracy of seq2seq module and the proposed model achieves better performance than other popular models. In addition, this paper also reveals the reason why the MLP achieves the improvement.

Lessons learned from power industry reform and electricity spot market trial operation in Southern China

Following the new round of electricity market reform, the spot market in Guangdong province has successfully entered the trial operation stage recently and is considered as the first pilot in China. In this paper, we review the performance of the trial operation of the electricity spot market in Guangdong. We discuss two main challenges encountered in Guangdong's market reform including the imbalanced funds caused by dual-track pricing and the compensation to gas power generators. The dual-track pricing refers to the two different settlement systems in the Guangdong trial market, one for the non-market electricity traded via the "priority power generation plan," and another traded via the spot market. While the dual-track pricing is inevitable since the Chinese government is accustomed to a gradual approach to economic reforms, it does lead to the serious problem of imbalanced funds which caused a lot of controversies. Furthermore, we discuss a case when a large number of renewable energy generators join the market. For the gas generator compensation, the market operator has three alternatives based on the present long-term transaction market. We employ a Hybrid Experimental Learning (HEL) approach to study which alternative is most in the interest of the gas generators.

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

Inaccurate electricity load forecasting can lead to the power sector gaining asymmetric information in the supply and demand relationship. This asymmetric information can lead to incorrect production or generation plans for the power sector. In order to improve the accuracy of load forecasting, a combined power load forecasting model based on machine learning algorithms, swarm intelligence optimization algorithms, and data pre-processing is proposed. Firstly, the original signal is pre-processed by the VMD–singular spectrum analysis data pre-processing method. Secondly, the noise-reduced signals are predicted using the Elman prediction model optimized by the sparrow search algorithm, the ELM prediction model optimized by the chaotic adaptive whale algorithm (CAWOA-ELM), and the LSSVM prediction model optimized by the chaotic sparrow search algorithm based on elite opposition-based learning (EOBL-CSSA-LSSVM) for electricity load data, respectively. Finally, the weighting coefficients of the three prediction models are calculated using the simulated annealing algorithm and weighted to obtain the prediction results. Comparative simulation experiments show that the VMD–singular spectrum analysis method and two improved intelligent optimization algorithms proposed in this paper can effectively improve the prediction accuracy. Additionally, the combined forecasting model proposed in this paper has extremely high forecasting accuracy, which can help the power sector to develop a reasonable production plan and power generation plans.

Research on the impact of financial transmission rights on transmission expansion: A system dynamics model

With the development of the power market, the traditional transmission congestion management method of using a power generation plan is no longer applicable, and congestion management using financial transmission rights (FTRs) is becoming a trend. However, after the introduction of FTRs, the profit from transmission lines changes, and those changes affect the expansion of and investment in transmission lines. Therefore, this paper constructs a system dynamics analysis model and presents specific calculation methods and a case analysis. Load growth, construction time, congestion, the step nature of the bid from generating units, and relative changes in the locational marginal prices (LMPs) at the sink and source nodes under the expansion and non-expansion scenarios are considered for a simulation calculation of net present value of transmission expansion project. Sensitivity analyses of factors such as generator bid prices, transmission expansion costs, the proportion of expansion capacity to transmission congestion, and the market maturity of FTRs are analysed. The results show that decision-making on the basis of transmission expansion investment in combination with FTRs is feasible and such decision-making can reflect the value of transmission expansion via the market, which conforms to market rules. That decision-making method is very important for the marketisation of power transmission.

A thorough analysis of renewable hydrogen projects development in Uzbekistan using MCDM methods

The energy supply system of Uzbekistan is not well positioned to meet the rapidly rising domestic energy demand of this country. Uzbekistan's current energy supply system is outdated and has very low diversity, as most of its energy comes from natural gas. In addition to producing immense amounts of greenhouse gas and environmental pollution, this situation is untenable considering the eventual depletion of fossil fuel reserves of this country. Uzbekistan's renewable energy sector is highly undeveloped, a situation that can be attributed to the lack of coherent policies for the advancement of renewable power and the low price of natural gas. However, this country has significant untapped renewable potentials, especially wind energy, that can perform a significant performance in the country's power generation plans. Also, producing hydrogen from renewable power can provide a good alternative to fossil fuels and help meet the needs of the Uzbek industrial sector, especially oil, gas, and petrochemical industries. In this study, the suitability of 17 regions in Uzbekistan for wind-powered hydrogen production was analyzed in terms of 16 sub-criteria in four categories of technical, economic, social, and environmental factors. To obtain robust results, the ranking was performed using a hybrid of BWM and EDAS, as well as WASPAS, ARAS, and WSM techniques. The weighting results exhibited the Levelized Cost of Electricity (LCOE), Levelized Cost of Hydrogen (LCOH), and Annual Energy Production (AEP) to be the most important sub-criteria for this evaluation. Nukus, Buhara, and Kungrad were introduced as the top three most appropriate locations for hydrogen development from wind plants. It was estimated that using 2000 kW turbines, a wind-powered hydrogen production plant built in the Nukus region can achieve an annual power output of 4432.7 MW and annual hydrogen output of 71.752 tons.

The External Cost of Electricity Generation: An Applicable Approach for Environmental Decision-Making on Electricity Exportation Strategy

The Burning of fossil fuels, such as coal, fuel oil, natural gas, and diesel in power sector, has become one of the major sources of air pollutants, namely COX, NOX and SOX. These are thought to adversely affect the environment and human health. This paper assesses the external cost of electricity production from fossil fuel power plants in Iran using the Extern-E study. In addition, the future of average amount of emissions and their external cost was predicted according to the development of Iran’s power generation system. Investigation of power generation planning in Iran from 2013 to 2023 shows that the average emissions of PM10, SO2, CO, and CO2 will reduce by 26.7%, 54.2%, 65.4%, and 20%, respectively, in fossil power plants. Moreover, it was predicted that the average external cost of power generation in 2023 would decrease up to 28.9%, 27.6%, and 23.1% in low, medium, and high scenarios, respectively. Moreover, analyzing the trend of Iran’s electricity exportation and considering the prospect of Iran’s energy sector, we claim that substitution of old gas power plants with high throughput combined cycle will help achieve the goal of Iran’s power generation development more sustainably.

Multicriteria power generation planning and experimental verification of hybrid renewable energy systems for fast electric vehicle charging stations

The installation of fast electric vehicle charging stations (EVCS) will be essential to promote the acceptance by the users of electric vehicles (EVs). However, if EVCS are exclusively supplied by the grid, negative impacts on its stability together with possible CO2 emission increases could be produced. Introduction of hybrid renewable energy systems (HRES) for EVCS can cope with both drawbacks by reducing the load on the grid and generating clean electricity. This paper develops a weighted multicriteria methodology to design the most suitable configuration of HRES for EVCS. This method determines the local renewable resources and the EVCS electricity demand. Then, taking into account environmental, economic and technical aspects, it deduces the most adequate HRES power generation planning for EVCS. Besides, an experimental stage to validate the design deduced from the multicriteria methodology is included. Therefore, the final power generation planning for the HRES in EVCS is supported not only by a complete numerical evaluation, but also by an experimental verification of the demand being fully covered. Methodology application to Valencia (Spain) proves that an off-grid HRES with solar PV, wind and batteries support would be the most suitable configuration for the system. This solution was also experimentally verified.

Optimal dispatch of wind power-photovoltaic-concentrating solar power combined power generation system based on improved PSO

The output power of wind power and photovoltaic is randomness and uncertainty, which brings severe challenges to power generation planning and scheduling of power system. The concentrating solar power (CSP) station with heat storage has the same scheduling as the traditional unit. Through reasonable scheduling of CSP stations, the uncertainty of wind power and photovoltaic power generation can be effectively suppressed, and new energy consumption can be promoted. This paper comprehensively considers the market power sales benefits, grid-connected environmental benefits and system operation and maintenance costs of the wind power-photovoltaic-CSP combined system, a dispatching model is established with the objective of optimizing the grid connected benefits of the combined system. Aiming at the shortcomings of particle swarm optimization (PSO) that is easy to be premature, an improved particle swarm optimization (IPSO) algorithm is formed by adding convergence factor and improving inertia weight to optimize the scheduling model. The results show that the grid connection benefit of the combined system increases by 237784yuan per day after adding CSP. The convergence speed of the IPSO used in this paper has been greatly improved.

Application TadGAN to Detect Collective Anomaly in Power Usage Data

In order to develop an efficient power generation plan, it is necessary to identify consumers’ power usage patterns. In general, power usage data takes the form of time series data and in order to analyze that data, it is necessary to first verify that there is no data contamination. To this end, the process of verifying that there are no anomalies in the data is essential. In particular, for power data, anomalies are often recorded across multiple time units rather than just one point. In this work, we applied the TadGAN algorithm to detect these collective anomalies. Using the power usage data recorded in the actual building, the anomalies were injected randomly with various conditions. Afterwards, we detected anomalies by using TadGAN and showed that we were better at detecting collective anomaly than point anomaly.

The impact of development priorities on power system expansion planning in sub-Saharan Africa

Sub-Saharan Africa faces unique barriers to electricity development due to the large proportion of the population that is un-electrified and the prevalence of rural populations. Typically, power system expansion planning models assume all potential consumers can be immediately electrified. This assumption is unrealistic in sub-Saharan Africa, where electrification will likely be a gradual process over a number of years. Furthermore, since a large proportion of the population in sub-Saharan Africa is located in rural regions, the prioritization of these regions may impact how the grid develops. In this research, we develop a multi-period optimization model for power generation and transmission system expansion planning in sub-Saharan Africa. In contrast to existing models, which assume full electrification, we consider a variety of electrification policies and analyze the impact of varying the electrification rate and policy on the cost and resources selected for power system expansion. We test our model on a case study of Rwanda. We find that varying the year in which full electrification is reached has a larger impact on cost and generation capacity than varying the electrification policy does, although, when urban and rural regions are considered equitably, more rooftop solar is built. Varying the electrification policies has a larger impact on transmission expansion than on generation expansion and this impact is amplified when starting from zero initial system capacity rather than the original Rwanda system. Additionally, a sensitivity analysis shows that tightening the bounds on CO2eq emissions has a large impact on the generation portfolio and cost.

Challenges of investment and financing for developing photovoltaic power generation in Cameroon, and the countermeasures

In this paper we aim to analyze the status of investment and financing of photovoltaic power generation in Cameroon, find out the challenges it faces, and put forward solutions. Through in-depth analyses of the investment and financing data of photovoltaic power generation from Cameroon, reference countries and the world during 2008–2019 and by drawing lessons from international experiences, we find that Cameroon’s investment and financing is far from meeting the needs of its photovoltaic power generation development. The causal analyses show that the root causes leading to insufficient investment and financing of photovoltaic power generation in Cameroon are the government behavior defects. On this basis, using the appropriate problem-oriented analysis method, we put forward policy recommendations to improve the investment and financing situation of photovoltaic power generation in Cameroon. The basic conclusion of this paper is that the low investment scale, single financing structure, violent investment fluctuation and financing gap are the surface causes of slowing photovoltaic power generation in Cameroon, while the lack of consciousness about attracting international investment, the ambiguity of the application process for photovoltaic power generation projects, the lack of specific measures to stimulate photovoltaic power generation, and the backward national planning of photovoltaic power generation are the internal reasons delaying Cameroon’s photovoltaic power generation. This study not only benefits Cameroon by being a guide for optimizing and promoting the development of photovoltaic power generation, but also has universal reference value for other similar research.

Risk Analysis for Short-Term Operation of the Power Generation in Cascade Reservoirs Considering Multivariate Reservoir Inflow Forecast Errors

In the short-term operation of the power generation of cascade reservoirs, uncertainty factors such as inflow forecast errors could cause various types of risks. The inflow to a downstream reservoir is not only affected by inflow forecast errors from upstream reservoirs but also the forecast errors associated with inflow to the stream segment between the reservoirs, such as from a tributary. The inflow forecast errors of different forecast periods may also be correlated. To address this multivariate problem, the inflow forecast error variables were jointly fitted in this study using the Gaussian mixture model (GMM) and a t-Copula function based on the analysis of the error distribution characteristics in different forecast periods. Therefore, a stochastic model that coupled with the GMM and t-Copula to calculate inflow forecast errors in multiple forecast periods was established. Furthermore, according to the simulation results of the stochastic model and the predicted runoff series, a set of simulated runoff processes were obtained. Then they were combined with the existing power generation plan to carry out the risk analysis for short-term operation of the power generation in a cascade reservoir. The approach was evaluated using the Jinguan cascade hydropower system within the Yalong River basin as a case study. For this case study, the risk analysis for short-term operation of the power generation was analyzed based on stochastic simulation of the inflow forecast errors; the results show the feasibility and effectiveness of the proposed methods.

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Renewable energy becomes progressively popular in the world because renewable resources such as solar, geothermal, wind energy are clean, inexhaustible and come from natural sources. Wind energy is one of the most significant resources of renewable energy and it plays a key role in the generation of electricity. Thus, accurate wind power estimation is crucial to deal with the challenges to balance energy trading, planning, scheduling decisions and strategies of wind power generation. This study proposes a prediction model to solve a real-life problem in the renewable energy sector by accurately estimating the amount of wind energy production per hour in the next 24 hours by applying machine learning (ML) techniques using historical wind power generation data and weather forecasting reports. In the proposed approach, first, an unsupervised ML method (i.e., the K-Means clustering algorithm) is applied to group data into meaningful clusters; then, these clusters are accepted as new feature values and added to the dataset to enlarge it; finally, a supervised ML method (i.e., regression) is performed for prediction. This study compares nine supervised learning algorithms: K-Nearest Neighbors, Support Vector Regression, Random Forest, Extra Trees, Gradient Boosting, Ridge Regression, Least Absolute Shrinkage and Selection Operator, Decision Tree, and Convolutional Neural Network. The aim of this study is to investigate the success of different ML algorithms on real-world data of wind turbines and propose a methodology to benchmark various machine learning algorithms to choose the most accurate final model for wind power generation prediction.