Demand Prediction Research Articles

Methods for projecting health workforce planning in Ireland: a collaborative approach

Abstract Background Health workforce planning (HWFP) is the process of analysing, forecasting, and planning workforce supply and demand, assessing gaps, and determining target workforce to ensure that health systems are prepared for future demand. HWFP elicits recommendations that are ideally utilised by the health system to support medical workforce over a defined time. Methods The objective of this project is to inform intake for medical and surgical specialties in Ireland to reach the necessary consultant workforce by 2038. A literature search was conducted to help inform the methodology for this project. The most common approach was a needs-based model, and additional reviews discussed the integration of medical engagement into the modelling approach. Results This project will employ a collaborative approach, combining mathematical modelling and a combination of quantitative and qualitative inputs, including the following phases: 1. The research phase will estimate baseline supply and demand data across medical and surgical specialties in Ireland using statistical models; 2. The presentation phase will include input from clinical leads to allow for more accurate assumptions in the baseline of each model; 3. Review of projections will include feedback from the clinical leads to help clarify and improve the initial model; 4. Presentation of the revised projection will include further collaboration with clinical leads to finalise the model. Conclusions The robust methodology for this HWFP project will ideally inform medical and surgical specialities in Ireland through 2038. Specific and extensive predictions of health workforce supply and demand will enhance strategic preparation, which is a key priority for the Health Service Executive in Ireland. Key messages • A collaborative approach to HWFP is essential for health service preparation and improvement. • The project will be finalised by the end of 2024, and the methodology for conducting similar HWFP projects can be adapted by other EU states.

Prediction of Power Equipment Emergency Repair Based on Adaptive Neural Network Fuzzy Inference Method

If the emergency repair prediction of power equipment is only made from the perspective of historical spare parts inventory data, it cannot reflect the impact of disaster-causing elements and disaster evolution on the demand for emergency repair spare parts in the future. Therefore, this paper aims to propose a reliable power equipment emergency repair prediction method, and constructs a demand prediction method for emergency repair spare parts of power equipment based on scenario analysis. Constructing a power equipment repair system through intelligent reasoning methods to improve the efficiency of power equipment repair. This article comprehensively uses methods such as literature analysis, model inference, and case simulation verification, this paper innovatively combines the adaptive neural network fuzzy inference system with expert experience. This paper validates the superiority of the prediction method constructed in this paper through comparative analysis. The results show that with the increase of the amount of data, the prediction accuracy of the method proposed in this paper will be improved, which can provide a reference for the subsequent emergency repair prediction of power equipment.

A multi-step regularity assessment and joint prediction system for ordering time series based on entropy and deep learning

Customer maintenance is of vital importance to the enterprise management. Valuable assessment and efficient prediction for customer ordering behavior can offer better decision-making and reduce business costs significantly. According to existing studies about customer behavior regularity segment and demand prediction most focus on e-commerce and other fields with large amount of data, making them not suitable for small enterprises and data features like sparsity and outliers are not mined when doing regularity quantification. Additionally, more and more complex network structures for demand prediction are proposed, which builds on the assumption that all the samples have predictive value, ignoring the fine-grained analysis of different time series regularity with high cost. To deal with the above issues, a multi-step regularity assessment and joint prediction system for ordering time series is proposed. For extracting features, comprehensive assessment of customer regularity based on entropy weight method with the result of predictability quantification using K-Means clustering algorithm, real entropy, LZW algorithm and anomaly detection adopting Isolation Forest algorithm not only gives an objective result to ‘how high the regularity of customers is’, filling the gap in the field of regularity quantification, but also provides a theoretical basis for demand prediction models selection. Prediction models: Random Forest regression, XGBoost, CNN and LSTM network are experimented with sMAPE and MSLE for performance evaluation to verify the effectiveness of the proposed regularity quantitation method. Moreover, a merged CNN-BiLSTM neural network model is established for predicting those customers with low regularity and difficult to predict by traditional machine leaning algorithms, which performs better on the data set compared to others. Random Forest is still used for prediction of customers with high regularity due to its high training efficiency. Finally, the results of prediction, regularity quantification, and classification are output from the intelligent system, which is capable of providing scientific basis for corporate strategy decision and has highly extendibility in other enterprises and fields for follow-up research.

Optimizing Urban Mobility: A Comparative Analysis of Taxi Demand Prediction Models

Optimizing Urban Mobility: A Comparative Analysis of Taxi Demand Prediction Models

Asynchronous decentralized traffic signal coordinated control in urban road network

AbstractThis study introduces an asynchronous decentralized coordinated signal control (ADCSC) framework for multi‐agent traffic signal control in the urban road network. The controller at each intersection in the network optimizes its signal control decisions based on a prediction of the future traffic demand as an independent agent. The asynchronous framework decouples the entangled interdependence between decision‐making and state prediction among different agents in decentralized coordinated decision‐making problems, enabling agents to proceed with collaborative decision‐making without waiting for other agents’ decisions. Within the proposed ADCSC framework, each controller dynamically optimizes its signal timing strategy with a unique rolling horizon scheme. The scheme's individualized parameters for each controller are determined based on the vehicle travel time between the adjacent intersections, ensuring that controllers can make informed control decisions with accurate arrival flow information from upstream intersections. The signal optimization problem is formulated as a mixed integer linear program model, which adopts a flexible signal scheme without a fixed phase structure and sequence. Simulation results demonstrate that the proposed ADCSC strategy significantly outperforms the benchmark signal coordination methods in terms of average delay, travel speed, stop numbers, and energy consumption. Experimental analysis on computation time validates the applicability of the proposed optimization model for real‐time implementation. Sensitivity analysis on key parameters in the framework is conducted, offering insights for parameter selection in practice. Furthermore, the ADCSC framework is extended to a road network in Qinzhou City, China, with 45 signalized intersections, demonstrating its effectiveness and scalability in the real‐world road network.

Data-driven collaborative healthcare resource allocation in pandemics

Severe shortages of healthcare resources are major challenges in pandemics, especially in their early stages. To improve emergency management efficiency, this paper proposes a novel rolling predict-then-optimize framework that includes three interactive modules, i.e., data-driven demand prediction, healthcare resource allocation, and parameter rolling update. Such a framework uses historical data to dynamically update the control parameters of the proposed Net-SEIHRD model, which predicts the healthcare needs of each region by jointly considering government interventions and cross-regional travel behaviors. Based on the forecasted healthcare resource demand in real-time, an optimization model is then formulated to realize coordinated resource allocation across multiple regions by minimizing the total generalized cost. To facilitate model solving, the proposed mixed integer nonlinear programming model is converted into an equivalent mixed integer linear model by using some linearization techniques. Finally, the proposed method is applied to the SARS-CoV-2 emergency response and collaborative allocation of healthcare resources in Shanghai, China. The results show that the proposed prediction model can effectively predict the peak and scale of the spread of the virus. Compared with the traditional LM and SEIHR models, the prediction accuracy of the Net-SEIHRD model is improved by 10.76% and 24.11%, respectively. Moreover, coordinated relief activities across regions, such as patient transfer and drug-sharing can improve the efficiency of pandemic control and save social costs.

Artificial Neural Networks for Energy Demand Prediction in an Economic MPC‐Based Energy Management System

ABSTRACTMicrogrids are a development trend and have attracted a lot of attention worldwide. The control system plays a crucial role in implementing these systems and, due to their complexity, artificial intelligence techniques represent some enabling technologies for their future development and success. In this paper, we propose a novel formulation of an economic model predictive control (economic MPC) applied to a microgrid designed for a faculty building with the inclusion of a predictive model to deal with the energy demand disturbance using a recurrent neural network of the long short‐term memory (RNN‐LSTM). First, we develop a framework to identify an RNN‐LSTM using historical data registered by a smart three‐phase power quality analyzer to provide feedforward power demand predictions. Next, we present an economic MPC formulation that includes the prediction model for the disturbance within the optimization problem to be solved by the MPC strategy. We carried out simulations with different scenarios of energy consumption, available resources, and simulation times to highlight the results obtained and analyze the performance of the energy management system. In all cases, we observed the correct operation of the proposed control scheme, complying at all times with the objectives and operational restrictions imposed on the system.

Recurrence Multilinear Regression Technique for Improving Accuracy of Energy Prediction in Power Systems

This paper demonstrates how artificial intelligence can be implemented in order to predict the energy needs of daily households using both multilinear regression (MLR) and single linear regression (SLR) methods. As a basic implementation, the SLR makes use of one input variable, which is the total amount of energy generated as an input. The MLR implementation involves multiple input variables being taken from various energy sources, including gas, coal, geothermal, wind, water, biomass, oil, etc. All of these variables are derived from detailed energy production data from the various energy sources. The purpose of this paper is to demonstrate that it is possible to analyze energy demand and supply directly together as a way to produce a more in-depth analysis. By analyzing energy production data from previous periods of time, a prediction of energy demand can be made. Compared to the SLR implementation, the MLR implementation is found to perform better because it is able to achieve a smaller error value. Furthermore, the forecasting pattern is carried out sequentially based on a periodic pattern, so this paper calls this method the recurrence multilinear regression (RMLR) method. This paper also creates a pre-clustering using the K-Means algorithm before the energy prediction to improve accuracy. Other models such as exponential GPR, sequential XGBoost, and seq2seq LSTM are used for comparison. The prediction results are evaluated by calculating the MAE, RMSE, MAPE, MAPA, and time execution for all models. The simulation results show that the fastest and best model that obtains the smallest error (3.4%) is the RMLR clustered using a weekly pattern period.

A Distributed VMD-BiLSTM Model for Taxi Demand Forecasting with GPS Sensor Data.

With the ubiquitous deployment of mobile and sensor technologies in modes of transportation, taxis have become a significant component of public transportation. However, vacant taxis represent an important waste of transportation resources. Forecasting taxi demand within a short time achieves a supply-demand balance and reduces oil emissions. Although earlier studies have forwarded highly developed machine learning- and deep learning-based models to forecast taxicab demands, these models often face significant computational expenses and cannot effectively utilize large-scale trajectory sensor data. To address these challenges, in this paper, we propose a hybrid deep learning-based model for taxi demand prediction. In particular, the Variational Mode Decomposition (VMD) algorithm is integrated along with a Bidirectional Long Short-Term Memory (BiLSTM) model to perform the prediction process. The VMD algorithm is applied to decompose time series-aware traffic features into multiple sub-modes of different frequencies. After that, the BiLSTM method is utilized to predict time series data fed with the relevant demand features. To overcome the limitation of high computational expenses, the designed model is performed on the Spark distributed platform. The performance of the proposed model is tested using a real-world dataset, and it surpasses existing state-of-the-art predictive models in terms of accuracy, efficiency, and distributed performance. These findings provide insights for enhancing the efficiency of passenger search and increasing the profit of taxicabs.

Comparison of energy prediction models for residential buildings: A case study in Himachal Pradesh, India

Abstract The demand for consumption of energy has been increasing globally with the tremendous increase in population. Different studies have proved that inadequate energy management and planning may lead to energy crisis which is a result of inadequacies in energy prediction. Accurate prediction of energy demand is important as underestimation may lead to shortage in supply and overestimation may lead to overinvestment in energy generation. Various available literature has been reviewed for determining the various factors responsible for affecting the energy consumption of residential buildings. Based on the factors determined, survey questionnaire has been formulated and survey was conducted in 400 residential buildings in one of northern states of India, i.e., Himachal Pradesh. It was observed by reviewing various studies that different models developed for energy consumption by different researchers were based on either of the three approaches, namely, engineering-based, AI-based, and hybrid approaches. Three tools namely, case-based reasoning, artificial neural network, and multilinear regression, based on these approaches were individually used for developing the model in this study, and their prediction results were compared. It was observed that the accuracy in the overall predicted results was highest in the proposed ANN model, followed by CBR model, and MLR model, with an overall accuracy of 99.93%, 96.3%, and 91.7%, respectively. The error obtained in the predicted results using ANN, CBR and MLR ranges from -4.0 to +3.0%, -15.0 to +26.0%, -30.0% to 20.0%, respectively. The overall RMSE of ANN, CBR, and MLR model was 1.44%, 11.7%, and 19.5%, respectively. It is concluded that ANN model is best suitable for predicting the short and long-term energy consumption with very high accuracy, as compared to the CBR and MLR. The results discussed in this study can be advantageously used for enhancing the consumption of operational energy in existing as well as proposed buildings.

A bike-sharing demand prediction model based on Spatio-Temporal Graph Convolutional Networks

Shared bikes, as an eco-friendly transport mode, facilitate short commutes for urban dwellers and help alleviate traffic. However, the prevalent station-based strategy for bike placements often overlooks urban zones, cycling patterns, and more, resulting in underutilized bikes. To address this, we introduce the Spatio-Temporal Bike-sharing Demand Prediction (ST-BDP) model, leveraging multi-source data and Spatio-Temporal Graph Convolutional Networks (STGCN). This model predicts spatial user demand for bikes between stations by constructing a spatial demand graph, accounting for geographical influences. For precision, ST-BDP integrates an attention-based graph convolutional network for station demand graph’s temporal-spatial features, and a sequential convolutional network for multi-source data (e.g., weather, time). In real dataset, experimental results show that ST-BDP has excellent performance with mean absolute error (MAE) = 1.62, mean absolute percentage error (MAPE) = 15.82%, symmetric mean absolute percentage error (SMAPE) = 16.14%, and root mean square error (RMSE) = 2.36, outperforming the baseline techniques. This highlights its predictive accuracy and potential to guide future bike-sharing policies.

INTEGRATED FORECASTING AND AGGREGATE PLANNING FOR PRODUCTION OPTIMIZATION: A COMPARATIVE ANALYSIS OF OVERTIME AND SUBCONTRACTING CONTROLS

The current potential market demand with ever-changing situations and conditions must be managed properly to find out the potential market demand in the future. Rumah Warna Yogyakarta is one of the manufacturing industry players that has experienced fluctuations in market demand, even tending to decline from the end of 2021 to mid-2022. Data was obtained from the database and direct interviews with Rumah Warna in Yogyakarta from November 2021 to November 2022. This study aims to determine the prediction of product demand for Rumah Warna Yogyakarta in the next period, so that companies can carry out production planning strategies to minimize production cost. Product demand prediction is carried out using the Grey System method of the GM (1,1) model. Then proceed with the heuristic aggregate planning method that focuses on overtime control and subcontracting control. Based on the results of the analysis, the Grey System GM (1,1) method produces good prediction accuracy of 9.231%. The best aggregate planning method is the overtime control where Rumah Warna Yogyakarta can reduce costs by Rp 351,258,758 when compared to the subcontracting control method.

Regional Logistics Demand Prediction Using BP Neural Network Based on Particle Swarm Optimization

Accurate regional logistics demand prediction is an indispensable part of a scientific and reasonable logistics construction system. This article mainly uses machine learning methods to screen features, select effective features, and then uses intelligent algorithms to optimize the BP neural network. The optimized model is trained and predicted for the future, optimizing research on regional logistics demand prediction, and providing effective suggestions for the development of the logistics industry. This article first uses the random forest algorithm to select features, eliminate redundant features, and then uses particle swarm optimization algorithm to optimize the parameters of the BP neural network to improve model performance. Finally, grey prediction is used to construct a prediction dataset, and the future trend of regional logistics demand is predicted, based on which suggestions are proposed. The results show that the optimized combination model proposed in this article can effectively improve prediction accuracy and make an effective contribution to the development of regional logistics.

Electric vehicle charging station demand prediction model deploying data slotting

Accurate prediction of energy requirement at charging station is essential for optimizing infrastructure usage, ensuring grid stability, and minimizing operational cost. Literatures suggest deployment of machine learning techniques to forecast the station demand. One major challenge associated with development of machine learning models is the inherent uncertainty in electric vehicle charging behaviour that includes variations in charging patterns, user preferences, and vehicle types. The conventional pre-processing techniques fail to dislodge nonlinearities and highly random patterns that include very low or zero-charging. Employing such techniques affects the model's forecast accuracy. This article performs data-slotting during pre-processing stage and then selects the best among 1-h, 2-h, 3-h and 4-h slots, to frame the feature vectors. The 4-h data with minimum variance is suggested to frame the dataset. Four distinct datasets, comprising different combination of average and total demands as predictor and response respectively are considered. The created dataset is deployed in Random Forest, Categorical Boosting, Extreme Gradient Boosting and Light Gradient Boosting models. The article recommends Categorical Boosting Regression model with least mean absolute error, mean square error and root mean square error of 0.0726, 0.0112, and 0.1059 respectively. Furthermore, the use of feature vector comprising of aggregated load for prescribed slots and the response representing the aggregated demand is observed to provide the least prediction error by the suggested model. The suggested model fed by the proposed feature vector offers significant advantage to charging station operator by enhancing the operational efficiency while performing resource and cost management with strategic planning.

Location and Size Planning of Charging Parking Lots Based on EV Charging Demand Prediction and Fuzzy Bi-Objective Optimization

The market share of electric vehicles (EVs) is growing rapidly. However, given the huge demand for parking and charging of electric vehicles, supporting facilities generally have problems such as insufficient quantity, low utilization efficiency, and mismatch between supply and demand. In this study, based on the actual EV operation data, we propose a driver travel-charging demand prediction method and a fuzzy bi-objective optimization method for location and size planning of charging parking lots (CPLs) based on existing parking facilities, aiming to reduce the charging waiting time of EV users while ensuring the maximal profit of CPL operators. First, the Monte Carlo method is used to construct a driver travel-charging behavior chain and a user spatiotemporal activity transfer model. Then, a user charging decision-making method based on fuzzy logic inference is proposed, which uses the fuzzy membership degree of influencing factors to calculate the charging probability of users at each road node. The travel and charging behavior of large-scale users are then simulated to predict the spatiotemporal distribution of charging demand. Finally, taking the predicted charging demand distribution as an input and the number of CPLs and charging parking spaces as constraints, a bi-objective optimization model for simultaneous location and size planning of CPLs is constructed, and solved using the fuzzy genetic algorithm. The results from a case study indicate that the planning scheme generated from the proposed methods not only reduces the travelling and waiting time of EV users for charging in most of the time, but also controls the upper limit of the number of charging piles to save construction costs and increase the total profit. The research results can provide theoretical support and decision-making reference for the planning of electric vehicle charging facilities and the intelligent management of charging parking lots.

Data-Driven Shelf Stocking: Robustness and Vertical-Location Effect

In this article, we study a shelf-stock allocation problem in a data-driven setting where the demand distribution is unknown. The retailer needs to decide which commodities to place on each level of the shelf (location decision), and determine the stock level for each selected commodity at the shelf (stock decision) that can be adjusted based on updated demand prediction, under constraints on allocation and capacity, so as to maximize total expected profit. Key issues of the problem include demand endogeneity on vertical-location effect and the demand ambiguity that may arise from the ever shorter life cycles of commodities and other complicated determinants. We address the problem in a rolling-horizon fashion and develop a two-phase data-driven robust optimization model leveraging a decision-dependent Wasserstein metric that incorporates time-series demand forecasts and captures vertical-location effect under demand ambiguity. We derive tractable solution schemes for the model, in which the phase-I model determines the optimal location decision by solving one instance of mixed-integer linear program, while the phase-II model admits an analytical solution for updating the optimal stock. Furthermore, we discuss the sensitivity implications on how the ambiguity aversion impacts the optimal stock, and prove the consistency of the model solution under regularity condition on the underlying demand process that well justifies the asymptotic performance of the proposed data-driven approach. Finally, we extend our model to incorporate substitution effect, and conduct sufficient numerical experiments with real-life data that demonstrate the performance of our model.

Potential use of district heating networks and the prospects for the advancements within urban areas of Nottingham as a case study

Buildings in urban areas significantly contribute to global energy consumption, necessitating solutions to reduce energy demands and mitigate environmental impacts. This study investigates district heating networks in urban areas, using Nottingham as a case study. A literature review addresses key barriers to decarbonising building energy in the UK, focusing on: (1) Information, engagement, and behaviour, (2) Strategy, policy, and regulation, (3) Infrastructure, (4) Supply chain and skills, and (5) Distribution of costs and impacts. The study examines the network's location, current processes, energy performance, and potential future impacts. Heat mapping and energy flow assessments identify areas for energy savings, guiding system optimisation. The findings suggest that increasing the energy output from the heat station to the network can enhance performance. The analysis highlights the potential of a life cycle perspective for district heating networks, proposing a framework that considers all stages from material sourcing to system utilisation. This approach helps assess environmental impacts, including greenhouse gas emissions and resource depletion, identifying opportunities to improve resource efficiency and reduce environmental impacts. By evaluating current sustainability goals and regulatory compliance, the study provides insights into the environmental and social implications of the district heating network's operations, pinpointing areas for improvement. It emphasises the need for continuous optimisation and innovation throughout the network's life cycle. The potential of a full life cycle assessment (LCA) approach is highlighted to evaluate four main future advancements: (1) heating network with added energy storage, (2) advanced system operations through model predictive control (MPC) for demand prediction, (3) general network improvements, and (4) network expansion. Overall, this study aims to enhance the sustainability, efficiency, and resilience of district heating networks, contributing to the transition towards sustainable energy systems while ensuring environmental and economic viability over time.

Short-term electricity price forecasting through demand and renewable generation prediction

Electricity market prices depend on various variables, including energy demand, weather conditions, gas prices, renewable generation, and other factors. Fluctuating prices are a common characteristic of electricity markets, making electricity price forecasting a complex process where predicting different variables is crucial. This paper introduces a hybrid forecasting model developed for the Spanish case. The model comprises four forecasting tools, with three of them relying on artificial neural networks, while the demand forecasting model employs a similar-day approach with temperature correction. This model can be employed by electrical energy trading companies to enhance their trading strategies in the day-ahead market and in derivative markets with a time horizon ranging from two to ten days. The results indicate that, with a forecasting horizon of two days, the price forecast has a rMAE of 8.18%. Furthermore, the model enables a market agent to accurately decide whether to purchase energy in the daily market or in the derivatives market in 69.9% of the days.

Multi-swarm multi-tasking ensemble learning for multi-energy demand prediction

The increasing uptake of renewable energy sources leads to more uncertainties of energy scheduling, resulting in more difficulties of energy demand management in smart grid. Accurate forecasting plays a significant role in energy management, and in some cases it may involve predictions of different consumers or geographic regions. Traditionally, these prediction problems have been solved independently, ignoring the potential shared knowledge among them that may help facilitate the overall performance. In this manuscript, we propose a multi-swarm multi-tasking ensemble learning (MSMTEL) framework for solving the energy demand forecasting across multiple cities. The proposed method comprises single-task pretraining, multi-task optimization (MTO), and ensemble learning (EL). For each prediction task, several subtasks are generated based on predefined parameters in the forecasting model. Each subtask utilizes an independent deep neural network (DNN) as the predictor, which is pretrained individually. Subsequently, we modify the dynamic multi-swarm particle swarm optimization (DMS-PSO) as a customized multi-swarm PSO (CMS-PSO) algorithm for implementing MTO. Each subswarm in CMS-PSO focuses on finding the optimal model knowledge (pretrained DNN weights and biases) of source tasks (all subtasks) to be reused by the target subtask. Finally, instead of choosing the best forecasting among the subtasks, results of subtasks over the same energy prediction problem are combined to yield the EL result, wherein weight coefficients determining the contributions of subtasks to EL are optimized by PSO. MSMTEL is evaluated against single-task learning (STL) and MTO to demonstrate its superior performance.

Public Bike Scheduling Strategy Based on Demand Prediction for Unbalanced Life-Value Distribution

Public Bike Scheduling Strategy Based on Demand Prediction for Unbalanced Life-Value Distribution