Seasonal Fluctuations In Demand Research Articles

Bio-inspired bidirectional deep machine learning for real-time energy consumption forecasting and management

Accurately predicting electrical power demand is crucial to making related forecasts and to effective sustainable energy management. Most relevant state-of-the-art studies deploy models that do not use optimizing parameters and do not incorporate strategies for using forecast results. This study was designed to develop a novel electricity consumption forecasting model, the Symbiotic Bidirectional Gated Recurrent Unit, which integrates Gated Recurrent Unit, Bidirectional Technique, and Symbiotic Organisms Search algorithms. The results of tests on a series of evaluation criteria showed the proposed model performed significantly better than six comparison models when parameter optimization was used. For all three sector datasets, the proposed model generated the most-accurate predictions of all models. In practical terms, when supply is expected to exceed demand, the prediction results may be used to adjust power plant output to reduce wastage. Conversely, when demand is expected to exceed supply, Time-of-Use tariffs may be implemented based on time-of-day and seasonal fluctuations in demand to facilitate reductions in peak usage and level out overall demand.

Machine Learning-Based Sales Prediction and Inventory Management for Grocery Stores

In today's competitive grocery retail environment, effective inventory management coupled with precise sales prediction is pivotal for success. This research undertakes an in-depth exploration into a machine learning framework tailored for "Sales Forecasting and Inventory Optimization in Grocery Retail." Utilizing historical sales records, meteorological data, and consumer behavior metrics, the proposed model endeavors to predict nuanced seasonal demand fluctuations. The primary value proposition of this approach lies in its capacity to curtail wastage, ensuring the balance between overstocking and inventory stockouts. By recognizing and adjusting for seasonal dynamics, the system offers enhanced demand fulfillment during high-demand periods. The subsequent refinement of the replenishment cycle fosters superior operational efficacy. As an outcome, businesses witness cost reductions, augmented profit margins, and elevated consumer contentment due to consistent product availability. As the broader grocery sector undergoes transformation, embedding sophisticated machine learning strategies can be a linchpin for sustained adaptability and competitiveness. This research further underscores the role of emergent technologies, such as machine learning within the IoT spectrum, in reshaping supply chain and communication paradigms. The endeavor here is to curtail lifecycle expenses in the supply chain by refining inventory practices. The research introduces a Deep Inventory Management (DIM) technique, employing the LSTM paradigm of deep learning. Through DIM's innovative approach, time-series challenges are reimagined as supervised learning tasks, enabling efficient model training. Preliminary tests indicate DIM's prediction accuracy hovers around 80%, translating to an impressive 25% reduction in inventory expenses when juxtaposed with prevailing methods, alongside rapid anomaly detection in inventory activities

SYSTEMATIC APPROACH TO PLANNING THE ASSORTMENT OF A PHARMACY ORGANIZATION

The management of the pharmacy organization is based on the competent management of the main business processes, among which the leading position is occupied by assortment planning. Many pharmaceutical workers form the structure and volume of the assortment based on the indicators of the previous period by averaging. This approach does not take into account the dynamism of the market of medicines: seasonal fluctuations in demand, changes in legislation, marketing activity of manufacturers and consumer preferences depending on it, as well as other factors. The use of a systematic approach in the formation of the assortment of pharmacy by the method of two-factor ABC- and XYZ-analysis allows you to quickly and flexibly respond to the most significant changes in the pharmaceutical market, contributing to the maintenance of liquidity, profitability and efficiency of the pharmacy. This method of analysis is applicable to various pharmacotherapeutic groups.

Machine Learning-Based Sales Prediction and Inventory Management for Grocery Stores

In today's competitive grocery retail environment, effective inventory management coupled with precise sales prediction is pivotal for success. This research undertakes an in-depth exploration into a machine learning framework tailored for "Sales Forecasting and Inventory Optimization in Grocery Retail." Utilizing historical sales records, meteorological data, and consumer behavior metrics, the proposed model endeavors to predict nuanced seasonal demand fluctuations. The primary value proposition of this approach lies in its capacity to curtail wastage, ensuring the balance between overstocking and inventory stockouts. By recognizing and adjusting for seasonal dynamics, the system offers enhanced demand fulfillment during high-demand periods. The subsequent refinement of the replenishment cycle fosters superior operational efficacy. As an outcome, businesses witness cost reductions, augmented profit margins, and elevated consumer contentment due to consistent product availability. As the broader grocery sector undergoes transformation, embedding sophisticated machine learning strategies can be a linchpin for sustained adaptability and competitiveness. This research further underscores the role of emergent technologies, such as machine learning within the IoT spectrum, in reshaping supply chain and communication paradigms. The endeavor here is to curtail lifecycle expenses in the supply chain by refining inventory practices. The research introduces a Deep Inventory Management (DIM) technique, employing the GradientBoostingRegressor paradigm of machine learning. Through DIM's innovative approach, time-series challenges are reimagined as supervised learning tasks, enabling efficient model training. Preliminary tests indicate DIM's prediction accuracy hovers around 85%, translating to an impressive 15% reduction in inventory expenses when juxtaposed with prevailing methods, alongside rapid anomaly detection in inventory activities

СКЛАДСЬКЕ ГОСПОДАРСТВО ТА ПІДХОДИ ДО ФІНАНСУВАННЯ СТАРТАПІВ У ЛОГІСТИЧНІЙ ГАЛУЗІ

The relevance of the proposed study is due to the importance of the coordinated activity of the warehouse economy, as one of the most important elements of the logistics system, which takes place at any stage of the material flow from the sources of raw materials to production and, subsequently, to the final consumer. The method of research is the analysis of logistics problems in the activities of business companies, their leaders and the identification of optimal financing options. During the research, we used the bibliographic method, methods of analysis and synthesis, the method of descriptive statistics, the method of expert assessments, graphical and tabular methods, as well as the modeling method. By the method of expert assessments, the key problems of warehouse logistics enterprises are summarized, the causes of their occurrence and the possible consequences of ignoring them are determined. The author's vision of solving the specified warehouse problems in order to ensure the preservation of stocks, cost efficiency and the optimal level of logistics service is presented. Ways to solve warehouse problems include the implementation of specialized software, warehouse planning technology, in particular, the warehouse management system (WMS), establishing relationships with various links of the supply chain, and organizing external and internal marketing research to prepare the logistics enterprise for seasonal fluctuations in demand; the safety rules for warehouse personnel are summarized, as well as the issue of organizing regular control of logistics processes of the warehouse is substantiated. The main logistics functions and the structure of the logistics process of the consolidation warehouse are considered, the advantages and disadvantages of their use are classified. Examples are given of the priorities for the development of robotics and the introduction of startups in the innovative activities of the domestic warehouse infrastructure. Current trends of the Ukrainian robotics market are highlighted. Popular forms of financing the needs of warehouse management are outlined. The advantages and disadvantages of external sources of financing innovative activities are analyzed. Examples of attracting grants for the needs of warehouse logistics equipment are given.

Обеспечение эффективности осуществления закупок товаров, работ, услуг в ФСИН России на основе учета сезонного и регионального факторов

The article discusses the importance of taking into account seasonality and regional characteristics when making purchases at the Federal Penitentiary Service of Russia. The seasonal factor has a significant impact on prices and availability of goods, works and services, while regional specifics introduce additional variables into the procurement process. The necessity of taking into account seasonal fluctuations in demand and prices when planning and conducting purchases is indicated. This allows you to organize procurement processes more efficiently, reduce the risk of shortages of goods and services during periods of increased demand, and optimize procurement costs. The importance of taking into account regional peculiarities in procurement is emphasized. Different regions may have their own specific requirements and needs, so adapting procurement procedures to regional specifics allows for more efficient execution of tasks and customer satisfaction. It is concluded that taking into account seasonal and regional factors will improve efficiency, take into account specific conditions and requirements, as well as reduce risks and improve the quality of purchased goods, works and services in the Federal Penitentiary Service of Russia.

РОЗВИТОК МОЛОКОПЕРЕРОБНОЇ ГАЛУЗІ УКРАЇНИ: ПЕРСПЕКТИВИ СТРАТЕГІЧНОГО МАРКЕТИНГОВОГО ПЛАНУВАННЯ

The article provides a detailed analysis of the daity industry of Ukraine. The prerequisites that determine the need for strategic marketing planning of dairy enterprises were indicated. The author singled out the necessity of researching the dairy industry, which is due to the following reasons: significant market capacity and development rates; marketing complications regarding the promotion of dairy products and seasonal fluctuations in demand; the unstable situation in the industry, which is associated with the unsatisfactory state of the raw material base and the uncompetitiveness of products. The significant increase in the cost of fuel and lubricants, the distance of dairies from the raw material base, the undeveloped structure of procurement points in rural areas, the increase in the cost of raw materials, the devaluation of the Ukrainian currency negatively affect the development of dairy enterprises and lead to a reduction in their production volumes. A detailed analysis of the trends in the development of the dairy industry in Ukraine made it possible to claim a reduction in the volume of milk production and various types of dairy products in Ukraine in the period 2013–2020 and to single out the main reasons: a reduction in the number of cows; increase in purchase prices for the main raw material – milk; a low level of capacity utilization as a result of an insufficient amount of raw materials; decrease in demand for dairy products due to the insufficiently high purchasing power of the population; a high level of competition from powerful enterprises equipped with modern equipment and technologies, etc. It was noted that the basis of the development of the dairy industry of Ukraine, and, in particular, milk processing enterprises, is the state support of this industry. It was proven that in order to maintain the existing market share, dairy enterprises must apply measures of publicity and sales promotion, combining their actions within the scope of the implementation of measures in the field of promotion.

Сучасні тенденції маркетингових досліджень у туристичній галузі

Currently, the tourism industry continues to outpace the global economy despite deteriorating global economic prospects, tensions in international trade, social worries, geopolitical uncertainty, instability and the COVID-19 pandemic. The article is aimed at identifying modern trends of marketing research as part of the complex of marketing instruments in the tourism sphere. To achieve this aim, the article uses the following research methods: abstract-logical; situational analysis; mean, absolute and relative values; comparison, graphic, sociological; statistical analysis; economic-mathematical; expert surveys and estimations. Based on the data of the World Tourism Organization, the indicators of development of the world market of tourist services are analyzed. Performed were the following: analysis of the dynamics of the number of subjects of tourism activity (tour operators and travel agents) in Ukraine; total average number of full-time employees; income from the provision of tourist services; operating expenses for the provision of tourist services; number of tourists served by tour operators and travel agents in Ukraine. The content of marketing research is disclosed as a multi-stage process, which should include the collection, registration and analysis of data in the sphere of tourism business. Marketing researches should be conducted according to 8 stages: determining the problem; development of the concept of research; cabinet marketing research; field market research; analysis of market conditions (supply and demand); research of foreign markets; simulation modeling; formation of a marketing information system. In order to determine the rating of tour operators of the mass segment of the tourism market in 2020, a questionnaire containing 16 questions is specified. Its results can be used when evaluating tour operators in terms of customer comfort and cooperation with travel agents. It is proved that marketing research in the tourism industry is advisable to be carried out systematically. This will provide for substantiating and elaborating managerial solutions in order to maximize the satisfaction of the needs of consumers of tourist services and solve the problems of significant seasonal fluctuations in demand.

МАТЕМАТИЧНА МОДЕЛЬ ПРОГНОЗУВАННЯ ТА ВИЗНАЧЕННЯ ОБСЯГУ ЗАПАСНИХ ЧАСТИН ДЛЯ СТАНЦІЙ ТЕХНІЧНОГО ОБСЛУГОВУВАННЯ АВТОМОБІЛІВ З УРАХУВАННЯМ ВТРАЧЕНИХ ПРОДАЖІВ

The article deals with the order of formation of the mathematical model of forecasting and determination of the volume of spare parts, taking into account lost sales on the basis of actual expenses for repairs and sales through trade Object of research - system of inventory management of car maintenance stations Purpose of the study - to carry out research of mathematical model of forecasting and determination of spare parts volume taking into account lost sales and to find out the main components of it. Method of the study - the analysis and formalization: quantitative indicators of automobile parts reserves, methods of forming components and parameters of a mathematical model. It is established that the methodology of constructing a mathematical model involves the formalization of the main processes of the cost of automotive spare parts. The mathematical model includes the costs of spare parts: 1) for repairs of cars; 2) through the sale of a spare part in a shop operating at a service station. It was found out that in order to take into account the lost sales of spare parts, it is necessary to clearly register customer inquiries, indicating the factory catalogs of spare parts numbers, their number. In this case, in case of the need for a spare part and its presence in the warehouse of the enterprise, the client refuses to purchase, then such a requirement is not taken into account as dissatisfied. The construction of a mathematical multiplicative model of prediction and determination of the amount of spare parts based on lost sales in which the value of the seasonal component is not a constant, but represents a certain proportion of the trend value. The formulas for determining the need for spare parts in a multiplicative model based on parabolic, linear trends of demand and seasonal variation are considered and given. The importance of the seasonal component in the mathematical model of forecasting is substantiated; it is a factor of forecasting error, it allows to find out the causes of fluctuations and to calculate the insurance stock of parts. To calculate the seasonal component, a method of correction of the trend equation with an asymmetric seasonal wave is presented. The results of the article can be used to increase the efficiency of inventory management at both technical maintenance stations of cars and any subjects of entrepreneurial activity, in the case when there is a problem of dissatisfied consumer demand. Forecast assumptions about the object of study - the specification of the model for determining the volume of spare parts by studying the seasonal fluctuations in demand and studying the main trends in the development of car service services and the existing model range of cars, their age composition. KEYWORDS: DETAIL, SPARE PARTS, PROBABILITY, QUANTITY, MODEL, VOLUME, PERIOD, DEMAND, NEED, FORECAST, SALE, IMPLEMENTATION, EQUATION, SERIES, SEASONAL VARIATION, TREND.

Applied spatial modelling for retail planning in tourist resorts

Purpose The purpose of this paper is to demonstrate that applied spatial modelling can inform the planning, delivery and evaluation of retail services, offering improvements over traditional retail impact assessment (RIA), especially within localities which experience seasonal fluctuations in demand. Design/methodology/approach The paper first describes a new theoretically informed tourist-based spatial interaction model (SIM) which has been custom-built and calibrated to capture the dynamics of the grocery sector in Cornwall, UK. It tests the power of the model to predict store performance for stores not used in the original calibration process, using client data for a new store development. The model is operationalised for the evaluation of various retail development schemes, demonstrating its contribution across a full suite of location decision making application areas. Findings The paper demonstrates that this highly disaggregate modelling framework can provide considerable insight into the local economic and social impacts of new store developments, rarely addressed in the retail location modelling literature. Practical implications Whilst SIMs have been widely used in retail location research by the private sector, the paper shows that such a model can have considerable value for public sector retail planning, a sector which seemed to have abandoned such models from the 1980s onwards, replacing them with often very limited and crude RIA. Originality/value The ability to review the forecasting capabilities of a model (termed post-investment review) are very rare in academic research. This paper offers new evidence that SIMs can support the RIA process.

Modelling and optimisation of a hydrogen-based energy storage system in an autonomous electrical network

The European Union’s 2020 climate and energy package (known as “20–20–20” targets) requests, among other key objectives, 40% of the electricity production in Greece to be supplied from Renewable Energy Sources by 2020. The main barriers for reaching this target is the intermittency of renewable energy sources combined with the penetration limits in the local electrical grids and the high seasonal demand fluctuations. In this context, the introduction of energy storage systems, comprises one of the main solutions for coping with this situation. One of the most promising technologies for storing the excess energy, that would be otherwise lost, is the production and storage of hydrogen through water electrolysis. Hydrogen can be used for supporting the electricity grid during periods of high demand but also as transportation fuel for hydrogen-based automobiles (e.g. fuel cell vehicles). For this purpose, a simulation algorithm has been developed, able to assess the specifications of the optimum sizing of hydrogen production storage systems. For the application of the algorithm, the area of the Aegean Sea has been selected, owed to the considerable renewable energy sources curtailments recorded in the various non-interconnected islands in the region. More specifically, the developed algorithm is applied to an autonomous electricity network of 9 islands, located at the SE area of the Aegean Sea and known as the “Kos-Kalymnos” electricity system. The results obtained designate the optimum size of the hydrogen-based configuration, aiming to maximize the recovery of otherwise curtailed renewable energy production.

Analytical Hydrogen Production and Storage Simulation for the “Kos-Kalymnos” System

The European Union's 2020 climate and energy package (known as “20-20-20” targets) requests, among other key objectives, 40% of the electricity production in Greece to be supplied from Renewable Energy Sources (RES) by 2020. The main barriers for reaching this target is the intermittency of RES combined with the penetration limits in the local electrical grids and the high seasonal demand fluctuations. In this context, the introduction of energy storage systems (ESSs), comprises one of the main solutions for coping with this situation. One of the most promising technologies for storing the excess energy, that would be otherwise lost, is the production and storage of hydrogen through water electrolysis. Hydrogen can be used for supporting the electricity grid during periods of high demand and as transportation fuel for H2-based automobiles (e.g. fuel cell vehicles). For this purpose, a simulation algorithm has been developed, able to assess the specifications of the optimum sizing of hydrogen production storage systems. For the application of the algorithm, the area of the Aegean Sea has been selected, owed to the considerable RES curtailments recorded in the various non-interconnected islands in the region. More specifically, the developed algorithm is applied to an autonomous electricity network of 9 islands, located at the SE area of the Aegean Sea and known as the “Kos-Kalymnos” electricity system. The results obtained designate the optimum size of the hydrogen-based configuration, aiming to maximize the recovery of otherwise curtailed RES production.

Analysis of factors affecting productivity and costs for a high-performance chip supply system

Declining market prices make it necessary to reduce supply costs of forest chips to ensure profitability in the supply chain and a continued supply of forest chips to the energy industry. Comminution and transport are two of the major contributors to the total costs in the forest fuel supply system. In order to fully utilise truck payloads and reduce transport costs, logging residues are usually chipped at the landing. For the chipping contractor, it is important to maximise the proportion of effective work time in relation to scheduled work time. Currently it is not uncommon that effective work time is less than 50 per cent of scheduled work time, due to chip transports using the chipper, waiting for chip trucks, and other delays. Increased chipper utilisation requires greater coordination between the chipper and the chip trucks transporting the produced chips to the customer. Supply systems have been simulated to examine how transport distance, number of trucks, shift scheduling and chip buffers affect the system costs for a high-performance chipper system. System costs and machine utilisation vary greatly, depending on system configuration. It is always beneficial to have six containers in the buffer on the landing rather than three, and trucks should begin their shifts at one-hour intervals. To maximise chipper use and minimise system costs, four container trucks are needed if the transport distance exceeds 50km. However, the large seasonal fluctuations in demand for biomass chips makes it hard to fully utilise the potential of the system over the whole year. The study concludes that it is important to regard chipping and chip transport as one operation, not two separate ones, as they are so dependent on each other.

Seasonality, price discrimination, and welfare

We discuss a potential limitation to a widely accepted result, namely that an output increase is a necessary condition for welfare to increase with price discrimination. We use a theoretical model to show that the existence of seasonal demand fluctuations may allow for a simultaneous reduction in average output and increase in average welfare. We also discuss a number of extensions of our basic model.

The impact of seasonal demand fluctuations on service network design of container feeder lines

Customer demand in global supply networks is highly uncertain due to unexpected global and local economic conditions and, in addition, affected by seasonal demand fluctuations for final products. Therefore, in maritime transportation the design of short-sea shipping services for containerized goods has to prove its economic efficiency under varying conditions of transportation demand. Since liner shipping involves significant capital investments and huge daily operating costs, the appropriate design of the service network is crucial for the profitability of the container feeder lines. Usually, quantitative models for shipping network design are based on deterministic forecasts, which are prone to errors caused by uncertainty factors and structural changes in the development of demand. This paper puts special emphasis on the impact of seasonal demand fluctuations on the structure of the related H&S networks, the capacity of the fleet operating within the network, the deployment of ship types as well as on the associated routes of the ships. A simulation and artificial neural network based forecasting framework is developed to support the design of service networks of short-sea shipping lines. The proposed methodology has been tested for a feeder liner shipping service in the East Mediterranean and Black Sea region. Numerical results show that seasonal demand fluctuations have vital impact on the network design of container feeder lines.

Responding to traveling patients' seasonal demand for health care services.

The Veterans Health Administration (VHA) provides care to over 8 million Veterans and operates over 1,700 sites of care across 21 regional networks in the United States. Health care providers within VHA report large seasonal variation in the demand for services, especially in the southern United States because of arrival of "snowbirds" during the winter. Because resource allocation activities are primarily carried out through an annual budgeting process, the seasonal load imposed by "traveling Veterans"-Veterans that seek care at VHA sites outside of their home network-make providing high-quality services more challenging. This work constitutes the first major effort within VHA to understand the impact of traveling Veterans. We discovered strong seasonal fluctuations in demand at a clinic located in the southeastern United States and developed a seasonal autoregressive integrated moving average model to help the clinic forecast demand for its services with significantly less error than historical averaging. Monte Carlo simulation of the clinic revealed that physicians are overutilized, suggesting the need to re-evaluate how the clinic is currently staffed. More broadly, this study demonstrates how operations management methods can assist operational decision making at other clinics and medical centers both within and outside VHA.

E-store

On-line transaction processing (OLTP) database management systems (DBMSs) often serve time-varying workloads due to daily, weekly or seasonal fluctuations in demand, or because of rapid growth in demand due to a company's business success. In addition, many OLTP workloads are heavily skewed to "hot" tuples or ranges of tuples. For example, the majority of NYSE volume involves only 40 stocks. To deal with such fluctuations, an OLTP DBMS needs to be elastic; that is, it must be able to expand and contract resources in response to load fluctuations and dynamically balance load as hot tuples vary over time. This paper presents E-Store, an elastic partitioning framework for distributed OLTP DBMSs. It automatically scales resources in response to demand spikes, periodic events, and gradual changes in an application's workload. E-Store addresses localized bottlenecks through a two-tier data placement strategy: cold data is distributed in large chunks, while smaller ranges of hot tuples are assigned explicitly to individual nodes. This is in contrast to traditional single-tier hash and range partitioning strategies. Our experimental evaluation of E-Store shows the viability of our approach and its efficacy under variations in load across a cluster of machines. Compared to single-tier approaches, E-Store improves throughput by up to 130% while reducing latency by 80%.

Developing and Applying a Disaggregated Retail Location Model with Extended Retail Demand Estimations

The spatial interaction model (SIM) is an important tool for retail location analysis and store revenue estimation, particularly within the grocery sector. However, there are few examples of SIM development within the literature that capture the complexities of consumer behavior or discuss model developments and extensions necessary to produce models which can predict store revenues to a high degree of accuracy. This article reports a new disaggregated model with more sophisticated demand terms which reflect different types of retail consumer (by income or social class), with different shopping behaviors in terms of brand choice. We also incorporate seasonal fluctuations in demand driven by tourism, a major source of non‐residential demand, allowing us to calibrate revenue predictions against seasonal sales fluctuations experienced at individual stores. We demonstrate that such disaggregated models need empirical data for calibration purposes, without which model extensions are likely to remain theoretical only. Using data provided by a major grocery retailer, we demonstrate that statistically, spatially, and in terms of revenue estimation, models can be shown to produce extremely good forecasts and predictions concerning store patronage and store revenues, including much more realistic behavior regarding store selection. We also show that it is possible to add a tourist demand layer, which can make considerable forecasting improvements relative to models built only with residential demand.

An empirical study on seasonal fluctuations in electricity demand in China

Seasonal fluctuations in electricity demand have resulted in power cuts in peak periods in China. This paper finds that the main component of fluctuations in electricity demand of secondary industry consists of four high energy consumption industries. The fluctuations in electricity demand of steel are relevant to the fluctuations in automobile sales. The energy consumption of tertiary industry is highly consistent with the seasonal fluctuations in residential electricity consumption, which is mainly affected by extreme weather conditions. In view of the transmission mechanism of the seasonal fluctuations in electricity demand from the demand side, to improve energy efficiency, electricity companies can adopt the strategy of price discrimination to smooth the seasonal fluctuations in demand.

An Empirical Study on Cyclical Fluctuations in Electricity Demand in China

Seasonal fluctuations in electricity demand have resulted in power cuts in peak periods in China. This paper finds that the main component of fluctuations in electricity demand of secondary industry consists of four high energy consumption industries. The fluctuations in electricity demand of steel are relevant to the fluctuations in automobile sales. The energy consumption of tertiary industry is highly consistent with the seasonal fluctuations in residential electricity consumption, which is mainly affected by extreme weather conditions. In view of the transmission mechanism of the seasonal fluctuations in electricity demand from the demand side, to improve energy efficiency, electricity companies can adopt the strategy of price discrimination to smooth the seasonal fluctuations in demand.