Demand Data Research Articles

A Deep Learning Approach for Short-Term Electricity Demand Forecasting: Analysis of Thailand Data

Accurate electricity demand forecasting serves as a vital planning tool, enhancing the reliability of management decisions. Apart from that, achieving these aims, particularly in managing peak demand, faces challenges due to the industry’s volatility and the ongoing increase in residential energy use. Our research suggests that employing deep learning algorithms, such as recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent units (GRU), holds promise for the accurate forecasting of electrical energy demand in time series data. This paper presents the construction and testing of three deep learning models across three separate scenarios. Scenario 1 involves utilizing data from all-day demand. In Scenario 2, only weekday data are considered. Scenario 3 uses data from non-working days (Saturdays, Sundays, and holidays). The models underwent training and testing across a wide range of alternative hyperparameters to determine the optimal configuration. The proposed model’s validation involved utilizing a dataset comprising half-hourly electrical energy demand data spanning seven years from the Electricity Generating Authority of Thailand (EGAT). In terms of model performance, we determined that the RNN-GRU model performed better when the dataset was substantial, especially in scenarios 1 and 2. On the other hand, the RNN-LSTM model is excellent in Scenario 3. Specifically, the RNN-GRU model achieved an MAE (mean absolute error) of 214.79 MW and an MAPE (mean absolute percentage error) of 2.08% for Scenario 1, and an MAE of 181.63 MW and MAPE of 1.89% for Scenario 2. Conversely, the RNN-LSTM model obtained an MAE of 226.76 MW and an MAPE of 2.13% for Scenario 3. Furthermore, given the expanded dataset in Scenario 3, we can anticipate even higher precision in the results.

A NEW APPROACH TO WIRELESS CHARGING AND ON-DEMAND DATA GATHERING (SSWCODDG) FOR RWSN

These days, WSNs (wireless sensor networks) are all about collecting data and reducing energy use. Mobile sinks and chargers can visit Cluster Heads (CHs) to gather data and recharge their batteries, respectively. A mobile VAN (MV) combines a mobile charger and sinks to improve the energy efficiency of a WSN. Determining the CHs’ guest instructions for wireless data collecting and charging is difficult. In response to these problems, the authors of this study present SSWCODDG (Santosh Soni Wireless Charging and on Demand Data Gathering), a new approach to wirelessly charging and data collection for rechargeable wireless sensor networks. Utilizing mobile VAN, the proposed algorithm gathers data from CHs and charges them according to their choices and needs. Here, Mobile VAN maintains a routing table and, in response to requests, visits CHs. To divide the network into clusters, the proposed method employs the LEACH clustering algorithm. One full cycle is executed by the LEACH (Low Energy Adaptive Clustering Hierarchy) algorithm. To back up its claims, this study compares the recently created SSWCODDG algorithm to the SPSS and M2C algorithms that came before it. In addition, SSWCODDG outperforms SPSS (Single path scheduling scheme) and M2C (Mobile to Cluster) for a range of sensor node densities by 38.62 and 25.78 percentage points, respectively.

Comparative analysis of battery energy storage systems’ operation strategies for peak shaving in industries with or without installed photovoltaic capacity

Battery energy storage systems can address energy security and stability challenges during peak loads. This study examines the integration of such systems for peak shaving in industries, whether or not they have photovoltaic capacity. The battery-sizing problem has been analyzed extensively. However, most analyses assume a specific battery operation strategy and ignore the impact of battery-charging schemes on system behavior. In this paper, the authors compare three different operation strategies for charging batteries in an industrial peak-shaving application based on historical demand data from a large electricity consumer in El Salvador. The three strategies are fast charging, time-based charging, and low-power threshold charging. The study analyzes the possible integration of a photovoltaic system with two different sizes for a range of battery sizes (from 250 to 1,500 kWh capacity), examining optimal peak shaving levels, economic savings, and battery degradation. Results indicate that fast-charging reduces monthly billing but degrades batteries faster. The estimated lithium-ion battery lifespan is 10-10.5 years, with a maximum difference of five months. These differences could affect the life cycle economics due to the high costs of battery replacement. The economic savings achieved by the peak shaving operation of the storage system are not enough to compensate the battery investment in this study. However, other case studies with different load profiles or other locations with more expensive electricity tariffs could make the adoption of these systems economically viable.

Barriers to digital technologies-driven circular economy in the Nigerian construction industry

PurposeThe purpose of this study is to investigate barriers to the adoption of digital technologies (DTs) in the circular economy (CE) transition in the construction industry. The aim is to quantitatively investigate what the barriers to DTs-driven CE are in the Nigerian construction industry.Design/methodology/approachA review of existing literature identified 32 barriers to DTs-led CE. A well-structured quantitative research questionnaire was developed and administered to construction experts using a convenient sampling technique via hand delivery and Google form. The gathered data were analysed using arrays of both descriptive and inferential statistical methods.FindingsThe study revealed that the awareness of the digitalisation of CE is high, but the adoption is low. Five themes of the leading 10 factors responsible for the low adoption of DTs in CE transition in the Nigerian construction industry are (1) finance and demand barrier, (2) data management and information vulnerability, (3) skills shortage and infrastructure challenge, (4) poor government and management support and (5) interoperability and resistance problems.Practical implicationsThis study could be helpful to decision-makers and policy formulators, which would provide an avenue for higher adoption of DTs in CE transition in the construction industry, better performance and environmental protection. It also provides a foundation for further research efforts in Nigeria and other developing countries of Africa and beyond.Originality/valueStudies on the barriers to DT adoption in CE transition are still growing, and this is even non-existent in the Nigerian construction context. This offers a unique insight and original findings by pioneering the identification and assessment of barriers to the digitalisation of CE transition in Nigeria’s construction industry.

Weather rebate sharing contract for enhancing supply chain performance

Weather risk in a supply chain has become a potential issue. We propose a new class of contract, a weather rebate sharing contract, that enhances the supply chain performance under weather risk. To design the contract parameters, the risk aversion of supply chain members is taken into account. The Conditional Value at Risk (CVaR) function is used to measure a firm’s objective under risk. The optimal hedging and ordering decisions are obtained by maximizing the CVaR of the supply chain’s expected profit. The weather rebate sharing contract parameters have been designed so that both parties obtain a Pareto-improving solution. We have investigated the performance of the traditional revenue sharing contract and our designed contract under weather risk by using industry demand data and corresponding temperature data. Irrespective of the risk aversion of the supply chain members, we conclude that our designed contract coordinates effectively under all weather conditions and performs better than a traditional revenue sharing contract. Moreover, our results show that the designed contract coordinates under different weather conditions and provides a better coordination framework than the previously designed contracts under weather risk. We recommend that practitioners use this class of contract for administering the supply chain under weather-related uncertainties.

RFM user value tags and XGBoost algorithm for analyzing electricity customer demand data

With the increasing demand for electricity, predicting user electricity demand has become an essential task. The electricity demand characteristics of users in the electricity market are different, so it is necessary to classify and predict users. Aiming at the above problems, a classified forecasting model of electricity demand based on recent consumption, frequency, monetary (RFM), K-means, XGBoost and dynamic time warping (DTW) algorithm is proposed. The experiment showcases that among the electricity consumption of commercial users, the first type of load has the lowest proportion in autumn, at around 18.6 %; The second type of load has the highest proportion in autumn, about 81.3 %; Accurate classification has been made for the consuming quantity of electricity of commercial users. The average error in the forecasting results of the RFM-KM-XGboost model and the actual value of commercial electricity demand is about 0.07 kW; The average errors between the forecasting results of SVM model and RF model and the true values are about 0.2 kW and 0.14 kW, respectively; It indicates that the forecasting error of the RFM-KM-XGBoost model is smaller. The above results indicate that the RFM-KM-XGBoost model can extract users' electricity demand characteristics by classifying user types and load types, and make more accurate predictions of electricity demand for different types of users.

A novel ontology-assisted inference platform in automotive troubleshooting tasks

Recent intelligent systems as required for Industry 4.0 merge data from diverse domains and more gradually demand data to be combined with field knowledge. The convergence and scenarization of data permits for the high-level inferring required to create knowledge based on the data under consideration. In this study, a framework for an ontology-assisted multi-scenario inference platform is proposed to help some of the desirable platform qualities in automotive troubleshooting service involve message clarity, platform interoperability, and elegant maturing. This framework is constructed through the model with triple modes (Conception-Expression-Manipulation, CEM), which is a communication-based framework. This proposed framework applies a two-tier class with three performers and can combine and use multiple scenarios. There are several characteristics, including flexibility, interaction, and handily maintenance. The transformation of data is separated from one element of the platform and thus does not implicate several other elements. A field of employment can be easily decided by the utilization of prototypes and field-norm elements. This proposed framework is instantiated applying an instance study including data from the troubleshooting tasks of automotive system.

Integrated conservative profitability evaluation for newsboy-type product in an OBM group

ABSTRACT Manufacturers in competitive markets can enhance profit opportunities by transforming their business model to own branding and manufacture (OBM). Note however that in situations involving limited storage and production capacity, OBM groups must determine the optimal preparation quantity and frequently evaluate profitability in all channels. This is particularly important when dealing with newsboy-type (i.e. single-period) products. The achievable capacity index (ACI) can effectively measure and estimate the profitability of a newsboy-type product. However, the ACI is applicable only to measure a single product in a single retail point. In the current study, we developed an integrated achievable capacity index (IACI) to enable OBM groups with owned channels to measure the overall profitability with multiple independent normal demands. To estimate the true IACI, we derived the statistical properties of the IACI estimator based on the historical demand data. The lower confidence bound on IACI (LCBIA) was also presented to prevent overestimation due to sampling error. The LCBIA values for various values of parameters were summarized as the generic tables for the manager’s convenience pertaining to decision-making in conservative profitability evaluation. Finally, the applicability of the proposed scheme was assessed by applying numerical and sensitivity analyses to a real-world OBM example.

Two level neuro-functional forecaster: A novel dynamic hybridization for functional data forecasting

With the advancement of technology, time series data are automatically collected without human intervention. As the data collection process becomes effortless, the next change encountered is to identify the best method to forecast time series data with high accuracies. In this regard, hybrid approaches have gained much attention where the strengths of two approaches can be combined to lessen the weaknesses of each individual approach. When exploring the features of time series data, some depict repetitive patterns and also data can be observed at several levels. The repeating curves can be considered as the higher level, whereas each individual observation can be considered as the lower level. Thus, in order to handle the data in a more effective way, the series can be handled at two levels by giving prominence to the features of each level separately. This paper proposes a novel algorithm named two level neuro-functional forecaster, which is capable of handling data at two levels, hybridizing a statistical approach with an artificial intelligence approach, to gain high accuracy levels. In addition, as this approach handles data at two levels, data sparsity at a particular level can be accommodated at the other level. To apply this algorithm to a real world dataset, electricity demand data in Sri Lanka was considered where the series consisted of daily load curves with repetitive pattern across the days. The proposed hybrid algorithm, outperforms the two approaches when individually used, with a MAPE of 3.324% for a year.

School Electricity Consumption in a Small Island Country: The Case of Fiji

Electricity consumption in buildings is one of the major causes of energy usage and knowledge of this can help building owners and users increase energy efficiency and conservation efforts. For Pacific Island countries, building electricity demand data is not readily accessible or available for constructing models to predict electricity demand. This paper starts to fill this gap by studying the case of schools in Fiji. The aim of the paper is to assess the factors affecting electricity demand for grid-connected Fijian schools and use this assessment to build mathematical models (multiple linear regression (MLR) and artificial neural network (ANN)) to predict electricity consumption. The average grid-connected electricity demand in kWh/year was 1411 for early childhood education schools, 5403 for primary schools, and 23,895 for secondary schools. For predicting electricity demand (ED) for all grid-connected schools, the stepwise MLR model shows that taking logarithm transformations on both the dependent variable and independent variables (number of students, lights, and air conditioning systems) yields statistically significant independent variables with an R2 value of 73.3% and RMSE of 0.2248. To improve the predicting performance, ANN models were constructed on both the natural form of variables and transformed variables. The optimum ANN model had an R2 value of 95.3% and an RMSE of 59.4 kWh/year. The findings of this study can assist schools in putting measures in place to reduce their electricity demand, associated costs, and carbon footprint, as well as help government ministries make better-informed policies.

SARIMA with Sliding Window Implementation for Forecasting Seasonal Demand Data

Demand forecasting is an essential part of business process management. A comparison of methods is needed to get the best model to provide good forecasting results. Difficulties in meeting consumer demands and predicting these requests using demand data at companies CV. ABCD is the main problem in this research. The SARIMA and decomposition methods are used for comparison and search for the best model before forecasting. SARIMA with a windowing size of 56, indicating the smallest MAPE value of 3,91%. The value <10%, so it can be said to produce an excellent forecasting value. Forecasting results with SARIMA show a meeting between actual and forecasting data in 2022. Therefore, it can be said the forecasting results for 2023 and 2024 can be used as a reference for the company CV. ABCD to meet customer demand and avoid stock shortages.

Machine learning application for estimating electricity demand by municipality

In order to achieve efficient and low carbon energy systems, attention has been focused on locally distributed energy systems, but a detailed and accurate supply–demand database is essential for simulating and optimizing such local systems. Demand data are generally not maintained at small scales, and it is common to estimate electricity demand by prorating global data from large energy carriers. However, the accuracy of the proration method is questionable. The present study explores the idea of using machine learning as an alternative to the proration method for downscaling electricity demand data based on a neural network model. The input data consist of four categories: weekday/holiday determination data, temperature data, periodic signal data, and demand sector configuration data. The model shows a satisfying generalization capacity for downscaling data from regional to prefectural and municipal scales while capturing local characteristics that are not accounted with the proration method.

Robust inventory routing problem under uncertain demand and risk-averse criterion

Inventory routing problem (IRP), which plays an important role in implementing vendor-managed-inventory strategy, is to determine the optimal timing and quantity of products to be delivered as well as the optimal vehicle delivery routes from the vendor to retailers. Retailers’ demand is usually uncertain and their distributions are ambiguous. We utilize limited historical demand data of retailers to construct a series of scenarios to characterize demand uncertainties. Moreover, we develop a framework to construct ambiguity sets and describe the ambiguities in demand distributions. To cater to the new feature of IRP as being exposed to downside risk and balance the mean and risk level of cost, we incorporate the worst-case mean-conditional value-at-risk (M-CVaR) criterion into the objective function and present a new distributionally robust IRP model. We transform the proposed model into a tractable formulation based on duality theory. A case study demonstrates the feasibility of the proposed method. The results indicate that our model can provide a robust delivery solution for immunizing against the influence of ambiguous demand distributions. In addition, an out-of-sample performance analysis shows that the delivery solution provided by our model can effectively reduce the product shortage rate.

Developing a hybrid technique for energy demand forecasting based on optimized improved SVM by the boosted multi-verse optimizer: Investigation on affecting factors

Electricity demand prediction accuracy is crucial for operational energy resource management and strategy. In this study, we provide a multi-form model for electricity demand prediction in China that based on incorporating of an upgraded Support Vector Machine (SVM) and a Boosted Multi-Verse Optimizer (BMVO). The suggested model is proposed to address the shortcomings of existing prediction approaches, which frequently fail to internment the complicated nonlinear interactions between demand for electricity and the variables that influence it. The improved SVM algorithm incorporates a modified genetic algorithm based on kernel function for enhancing the stability of the model. The BMVO technique is employed to optimize the combined model's weights and increase its generalization effectiveness. The suggested approach is tested by real-world Chinese energy demand data. The findings show that it outperforms existing prediction approaches in terms of reliability and precision. Further, the number of samples chosen affects how well the proposed BMVO linked with the Incremental SVM (ISVM) predicts outcomes. Particularly, when 1735 samples are chosen, the lowest level of Mean Absolute Percent Error (MAPE) was noted. The Root Mean Square Error (RMSE) and MAPE values under the proposed BMVO/ISVM model are reduced by 53.72% and 55.22%, respectively, compared to the Artificial Neural Network (ANN) approach reported in literature. Finally, the suggested model is capable of accurately predicting the electricity demand in China and has the potential to be applied to other energy-demand prediction applications.

A Multi-step Data Assimilation Framework to Investigate the Effect of Measurement Uncertainty in the Reduction of Water Distribution Network Model Errors

Water distribution network (WDN) models are a common decision support tool for understanding the behavior and performance of WDNs, aiding in the planning and management of WDN systems. The increasing availability of real-time data has recently promoted the exploration of Data Assimilation (DA) techniques to improve these models. However, flow, pressure and demand data are uncertain, particularly due to sensor characteristics such as precision and noise. An open question is to what extent DA can still improve hydraulic models when the data used to this end is uncertain. This paper proposes a three-step Ensemble Kalman Filter based DA approach for WDNs (3-EnKF-WDN), building on previous approaches, and advancing in two main fronts: the use of extended period simulation, and the use of pressure-dependent demand (PDD) analysis. Different scenarios considering uncertain sensor data, with varied precision and noise, are applied to two networks of different sizes, representative of real-world WDNs. The computational demand of the 3-EnKF-WDN method is also assessed. Results show that increasing sensor’s precision and decreasing the noise in state measurements reduce model error, as expected. However, we also found that model errors: 1) are reduced more effectively by using 3-EnKF-WDN than by increasing sensors’ precision; 2) are not reduced if certain noise thresholds are surpassed; 3) can be reduced without assimilating demand data if the WDNs are fully monitored with head sensors in all the nodes and flow sensors in all the links.

The long-term effect of COVID-19 policy stringency on consumer food demand quantities in Switzerland

This is the first study investigating the effect of COVID-19 policy stringency on consumer food demand for the years 2020 and 2021. In particular, we compared food demand in periods with strict COVID-19 policies to food demand in periods with less strict COVID-19 policies. For this purpose, we used Switzerland, which imposed two COVID-19 lockdowns, as a case study. To test this link, we applied fixed effects dummy variable regressions (as baseline estimates) and dose–response functions. To capture the stringency of Swiss COVID-19 policies, we relied on daily data from the Oxford COVID-19 Government Response Tracker. Food demand data at the product level came from the combined retail and consumer panel of the market research company Nielsen and covered meat, milk products, vegetables, and fruits. Empirical findings revealed that consumer demand for all food products was on average 2.5 times higher during the two lockdowns compared to periods without lockdowns. While we found no statistically significant differences in consumer food demand between the two lockdowns for milk products, vegetables, and fruits, the total food demand and the demand for meat was higher during the first lockdown. Increases in Swiss food demand were likely caused by the closing of restaurants (both lockdowns) and the closing of borders to neighboring countries (only the first lockdown), preventing shopping tourism. Against the background of potential future pandemics, our research provides important information for policymakers on the quantification of food demand changes in times of crisis.

Global Residual Demand Analysis in a Deep Variable Renewable Energy Penetration Scenario for Replacing Coal: A Study of 42 Countries

This study analyzes the residual demand curves of 42 countries under five scenarios with varying variable renewable energy (VRE) levels to observe how replacing coal with VRE can alter the demand curve. Using 2018 demand data, the residual demand was calculated and analyzed by subtracting the VRE supply curve from the demand curve. The operational requirements for low-carbon load-following sources amid high VRE penetration are examined. Key findings indicate that substantial peak residual demand persists even with 70% energy from VREs, emphasizing the need for significant load-following resources. Transitioning to a 70% VRE scenario could reduce CO2 emissions by approximately 16.799 billion tons, advancing towards carbon neutrality. However, this benefit depends on maintaining grid stability, highlighting the importance of adequate load-following plants to manage VRE intermittency. Countries like Malaysia, South Korea, Tunisia, the UK, Japan, Indonesia, Thailand, and Libya face higher load-following demands due to specific renewable energy contexts. This study reveals varying renewable energy environments across countries, suggesting that a universal strategy for carbon neutrality and replacing coal may not be feasible. Each nation must develop its own approach to emission reduction, considering its unique conditions. This research emphasizes the urgent need for developing cost-effective, flexible, low-carbon load-following sources to enhance decarbonization potential globally.

Technical-economic limitations of floating offshore wind energy generation in small isolated island power systems without energy storage: Case study in the Canary Islands

Coastal areas committed to the development of affordable and clean energy sources can find significant means to achieve their decarbonization objectives in offshore wind technology for power generation. However, the development of this technology in island territories with small-scale isolated electrical systems faces technical constraints that, in turn, translate into economic limitations. The objective of this study is to determine offshore wind energy curtailment and its impact on the LCOE in island territories with small-scale isolated electrical systems. To accomplish this, the data of electrical energy demand and generation of onshore renewable energy and conventional energy over a year have been used, with the Canary Islands (Spain-EU) adopted as a case study. The regional government there has established total decarbonization of its economy by 2040 as the central axis of its energy policy. The results show percentages of offshore wind energy curtailment exceeding 35% and an increase in the LCOE of up to 17%. One of the conclusions highlights the need for governmental action to neutralize this increase in the LCOE. This study sheds light on the technical and economic implications for government energy plans promoting the large-scale deployment of floating offshore wind facilities in island territories.

Physically 100 % renewable electricity supply through hybrid electricity storage – A top-down modelling study for the case of Austria

A top-down model calculation based on real generation and demand data is presented for the hypothetical case of 100 % renewable electricity generation combined with hybrid electricity storage infrastructure in the Austrian control area (9 million inhabitants, electric demand ∼70 TWh per year). To reach 100 % physical coverage by renewables, the actual wind and photovoltaic generation curves in the selected reference year of 2022 were scaled by a factor of 2.8 and 30, respectively. In the scope of the presented system are lithium-ion battery storage (cyclic efficiency 90 %), pumped hydro storage (70 %) and power-to-gas storage with subsequent re-electrification in gas turbine combined cycle plants operated as combined heat and power (CHP) system (30 %). Our core aspect lies in the optimized operation of the hybrid storage system, where the charging and discharging of the storage technology with higher cyclic efficiency is given priority. A straightforward cascading control algorithm is applied with individual elements functioning as simple proportional controllers. The results show how a 100 % renewable electricity system in Austria could be configured, partially building upon existing electricity generation infrastructure (pumped hydro and gas turbine combined cycle plants) and on the implementation of new lithium-ion battery storage with a total capacity of 100 GWh and new electrolysis infrastructure with a power of 5 to 10 GW. To overcome existing limitations of the presented model, an extension to a more complex model with spatial differentiation and consideration of electricity grid characteristics and constraints is recommended.

Virtual Power Plant’s Optimal Scheduling Strategy in Day-Ahead and Balancing Markets Considering Reserve Provision Model of Energy Storage System

In recent years, with the rapid increase in renewable energy sources (RESs), a Virtual Power Plant (VPP) concept has been developed to integrate many small-scale RESs, energy storage systems (ESSs), and customers into a unified agent in the electricity market. Optimal coordination among resources within the VPP will overcome their disadvantages and enable them to participate in both energy and balancing markets. This study considers a VPP as an active agent in reserve provision with an upward reserve capacity contract pre-signed in the balancing capacity (BC) market. Based on the BC contract’s requirements and the forecasted data of RESs and demand, a two-stage stochastic optimization model is presented to determine the VPP’s optimal scheduling in the day-ahead (DA) and balancing energy (BE) markets. The probability of reserve activation in the BE market is considered in this model. The ESS’s reserve provision model is proposed so as not to affect its schedule in the DA market. The proposed optimal scheduling model is applied to a test VPP system; then, the effects of the BC contract and the probability of reserve activation on the VPP’s trading schedule are analyzed. The results show that the proposed model has practical significance.