Resource Forecasting Research Articles

Предсказание временных рядов солнечной активности с помощью искусственной нейронной сети LSTM

A numerical model for predicting the parameters of solar activity — the number of sunspots R and the radioflux at a wave of 10.7 cm F10.7 ahead for 27 days — has been built. The numerical model uses an artificial neural network (NN) with LSTM (Long short-term memory) layers. For both the number of sunspots and the radioflux, the model predicts the levels and limits of variation of the values for 27 days. The average absolute prediction error of the model is less than 6 %. The real-time model is implemented on the site http://aurora.pgia.ru and can be an addition to long-term forecasts of other INTERNET resources.

Calibration of GFS Solar Irradiation Forecasts: A Case Study in Romania

Models based on Numerical Weather Prediction (NWP) are widely used for the day-ahead forecast of solar resources. This study is focused on the calibration of the hourly global solar irradiation forecasts provided by the Global Forecast System (GFS), a model from the NWP class. Since the evaluation of GFS raw forecasts sometimes shows a high degree of uncertainty (the relative error exceeding 100%), a procedure for reducing the errors is needed as a prerequisite for engineering applications. In this study, a deep analysis of the error sources in relation to the state of the atmosphere is reported. Of special note is the use of sky imagery in the identification process. Generally, it has been found that the largest errors are determined by the underestimation of cloud coverage. For calibration, a new ensemble forecast is proposed. It combines two machine learning approaches, Support Vector Regression and Multi-Layer Perceptron. In contrast to a typical calibration, the objective function is constructed based on the absolute error instead of the traditional root mean squared error. In terms of normalized root mean squared error, the calibration roughly reduces the uncertainty in hourly global solar irradiation by 16%. The study was conducted with high-quality ground-measured data from the Solar Platform of the West University of Timisoara, Romania. To ensure high accessibility, all the parameters required to run the proposed calibration procedures are provided.

Water resources allocation based on water resources supply-demand forecast and comprehensive values of water resources

Study regionThe Yellow River Basin (YRB) in China. Study focusThe water resources supply-demand imbalance hinders sustainable socioeconomic development, which can be effectively addressed by the water resources allocation (WRA). In this study, a WRA model was established based on supply-demand forecast and comprehensive values of water resources (SDF-CVWR). First, the supply-demand situation was analyzed to determine whether an imbalance existed. Considering the coordinated development of all systems, a comprehensive index, CVWR, was proposed, and its values in the current and planning years were quantified by emergy analysis method. Finally, the model was solved by the genetic algorithm. New hydrological insights for the regionThere were supply-demand imbalances existing in the planning years (2025, 2030), and the water shortages were 0.89 × 1010 m3 and 1.04 × 1010 m3. The CVWR were 3.58 × 1012 yuan and 3.61 × 1012 yuan, showing an upward trend compared with the current year (2020). Compared with 2020, the water allocated decreased in middle and upper reaches of the YRB in 2025, while increased in the lower reaches; in 2030, except Shanxi, water allocated in other provinces (regions) was basically the same as that in 2025. These provide a scheme reference for WRA in the YRB. The model proposed in this study is verified to be applicable. In addition, the model can be flexibly used according to the actual parameters in different regions.

Application of novel binary optimized machine learning models for monthly streamflow prediction

Accurate measurements of available water resources play a key role in achieving a sustainable environment of a society. Precise river flow estimation is an essential task for optimal use of hydropower generation, flood forecasting, and best utilization of water resources in river engineering. The current paper presents the development and verification of the prediction abilities of new hybrid extreme learning machine (ELM)-based models coupling with metaheuristic methods, e.g., Particle swarm optimization (PSO), Mayfly optimization algorithm (MOA), Grey wolf optimization (GWO), and simulated annealing (SA) for monthly streamflow prediction. Prediction precision of standalone ELM model was compared with two-phase optimized state-of-the-arts models, e.g., ELM–PSO, ELM–MOA, ELM–PSOGWO, and ELM–SAMOA, respectively. Hydro-meteorological data acquired from Gorai and Padma Hardinge Bridge stations at Padma River Basin, northwestern Bangladesh, were utilized as inputs in this study to employ models in the form of seven different input combinations. The model’s performances are appraised using Nash–Sutcliffe efficiency, root-mean-square-error (RMSE), mean absolute error, mean absolute percentage error and determination coefficient. The tested results of both stations reported that the ELM–SAMOA and ELM–PSOGWO models offered the best accuracy in the prediction of monthly streamflows compared to ELM–PSO, ELM–MOA, and ELM models. Based on the local data, the ELM–SAMOA reduced the RMSE of ELM, ELM–PSO, ELM–MOA, and ELM–PSOGWO by 31%, 27%, 19%, and 14% for the Gorai station and by 29%, 27%, 19%, and 14% for Padma Hardinge bridge station, in the testing stage, respectively. In contrast, based on external data, ELM–PSOGWO improves in RMSE of ELM, ELM–PSO, ELM–MOA, and ELM–SAMOA by 20%, 5.1%, 6.2%, and 4.6% in the testing stage, respectively. The results confirmed the superiority of two-phase optimized ELM–SAMOA and ELM–PSOGWO models over a single ELM model. The overall results suggest that ELM–SAMOA and ELM–PSOGWO models can be successfully applied in modeling monthly streamflow prediction with either local or external hydro-meteorological datasets.

Hydrological bases of water resources management of the rivers of Northern Kazakhstan

It is well known that directional global and regional climatic changes have been taking place in recent decades, in the considered area, where the underground feeding of rivers is insignificant, the river flow has decreased. In this regard, the river flow rate and total water resources of the river basins of Northern Kazakhstan are estimated in several ways: for a multi-year period, for the modern period, as well as for the period preceding it, a significant part of which is characterized by conditionally natural (not significantly transformed) river flow. Flow characteristics necessary for practice have been obtained: distribution parameters and probability values. Territorial peculiarities and regularities of annual flow distribution have been analyzed. The regional dependence of the annual flow on the determining physical and geographical factors has been derived. Appropriate recommendations for calculating the flow of unstudied rivers are given. The obtained results can be used in the development of specific principles of integrated water resources management of the considered territory, and the long-term forecasting of water resources under changing climate and changes in anthropogenic pressure on the water bodies of Northern Kazakhstan.

Satellite-derived solar radiation for intra-hour and intra-day applications: Biases and uncertainties by season and altitude

Regional to European scale intra-day forecasts of solar resources and photovoltaic (PV) power generation are of key relevance for operators of solar plants and power grids, as well as power traders, who seek to optimize revenues and maintain grid stability by matching power supply and demand. Our study addresses a key prerequisite for such forecasts: the accuracy of intra-hour and intra-day surface solar radiation (SSR) estimates of the HelioMont Meteosat product, a state of the art satellite product particularly suited for the Alpine region. A second satellite product, SARAH-2, as well as longer time scales, are also examined for comparison. The satellite SSR estimates are analyzed based on 136 ground stations across altitudes from 200 m to 3570 m in Switzerland in 2018. In peak daytime periods, the instantaneous satellite SSR deviates from the ground-measured SSR by a mean absolute deviation (MAD) of 110.4 and 99.6 W/m2 for SARAH-2 and HelioMont, respectively. For the daytime SSR, the instantaneous, hourly, and daily-mean MADs amount to 91.7, 81.1, 50.8, and 82.5, 66.7, 42.9 W/m2 for SARAH-2 and HelioMont, respectively. SARAH-2 drastically underestimates instantaneous SSR in winter at altitudes above 1000 m, possibly due to snow cover. HelioMont performs better in this respect, but the remaining substantial, spatially and temporally heterogeneous biases we identify pose a challenge with regard to the use of HelioMont for accurate intra-day PV estimates and forecasts.

Allocation of emergency medical resources for epidemic diseases considering the heterogeneity of epidemic areas.

The resources available to fight an epidemic are typically limited, and the time and effort required to control it grow as the start date of the containment effort are delayed. When the population is afflicted in various regions, scheduling a fair and acceptable distribution of limited available resources stored in multiple emergency resource centers to each epidemic area has become a serious problem that requires immediate resolution. This study presents an emergency medical logistics model for rapid response to public health emergencies. The proposed methodology consists of two recursive mechanisms: (1) time-varying forecasting of medical resources and (2) emergency medical resource allocation. Considering the epidemic's features and the heterogeneity of existing medical treatment capabilities in different epidemic areas, we provide the modified susceptible-exposed-infected-recovered (SEIR) model to predict the early stage emergency medical resource demand for epidemics. Then we define emergency indicators for each epidemic area based on this. By maximizing the weighted demand satisfaction rate and minimizing the total vehicle travel distance, we develop a bi-objective optimization model to determine the optimal medical resource allocation plan. Decision-makers should assign appropriate values to parameters at various stages of the emergency process based on the actual situation, to ensure that the results obtained are feasible and effective. It is necessary to set up an appropriate number of supply points in the epidemic emergency medical logistics supply to effectively reduce rescue costs and improve the level of emergency services. Overall, this work provides managerial insights to improve decisions made on medical distribution as per demand forecasting for quick response to public health emergencies.

Seasonal forecasting of snow resources at Alpine sites

Abstract. Climate warming in mountain regions is resulting in glacier shrinking, seasonal snow cover reduction, and changes in the amount and seasonality of meltwater runoff, with consequences on water availability. Droughts are expected to become more severe in the future with economical and environmental losses both locally and downstream. Effective adaptation strategies involve multiple timescales, and seasonal forecasts can help in the optimization of the available snow and water resources with a lead time of several months. We developed a prototype to generate seasonal forecasts of snow depth and snow water equivalent with a starting date of 1 November and a lead time of 7 months, so up to 31 May of the following year. The prototype has been co-designed with end users in the field of water management, hydropower production and mountain ski tourism, meeting their needs in terms of indicators, time resolution of the forecasts and visualization of the forecast outputs. In this paper we present the modelling chain, based on the seasonal forecasts of the ECMWF and Météo-France seasonal prediction systems, made available through the Copernicus Climate Change Service (C3S) Climate Data Store. Seasonal forecasts of precipitation, near-surface air temperature, radiative fluxes, wind and relative humidity are bias-corrected and downscaled to three sites in the Western Italian Alps and finally used as input for the physically based multi-layer snow model SNOWPACK. Precipitation is bias-corrected with a quantile mapping method using ERA5 reanalysis as a reference and then downscaled with the RainFARM stochastic procedure in order to allow an estimate of uncertainties due to the downscaling method. The impacts of precipitation bias adjustment and downscaling on the forecast skill have been investigated. The skill of the prototype in predicting the deviation of monthly snow depth with respect to the normal conditions from November to May in each season of the hindcast period 1995–2015 is demonstrated using both deterministic and probabilistic metrics. Forecast skills are determined with respect to a simple forecasting method based on the climatology, and station measurements are used as reference data. The prototype shows good skills at predicting the tercile category, i.e. snow depth below and above normal, in the winter (lead times: 2–3–4 months) and spring (lead times: 5–6–7 months) ahead: snow depth is predicted with higher accuracy (Brier skill score) and higher discrimination (area under the relative operating characteristics (ROC) curve skill score) with respect to a simple forecasting method based on the climatology. Ensemble mean monthly snow depth forecasts are significantly correlated with observations not only at short lead times of 1 and 2 months (November and December) but also at lead times of 5 and 6 months (March and April) when employing the ECMWFS5 forcing. Moreover the prototype shows skill at predicting extremely dry seasons, i.e. seasons with snow depth below the 10th percentile, while skills at predicting snow depth above the 90th percentile are model-, station- and score-dependent. The bias correction of precipitation forecasts is essential in the case of large biases in the global seasonal forecast system (MFS6) to reconstruct a realistic snow depth climatology; however, no remarkable differences are found among the skill scores when the precipitation input is bias-corrected, downscaled, or bias-corrected and downscaled, compared to the case in which raw data are employed, suggesting that skill scores are weakly sensitive to the treatment of the precipitation input.

Вплив експлуатаційних факторів на залишковий ресурс металоконструкцій колісних транспортних засобів

The article is devoted to the problem of researching the influence of operational factors on the residual resource of metal structures of wheeled vehicles. Corrosion of metal structures of wheeled vehicles significantly reduces the resource and reliability of vehicles. Failure due to the combined action of corrosion and operational loads is caused by complex factors that can be divided into internal and external. Internal - traditionally considered as dependent on the chemical composition. External factors include corrosive destruction due to the external environment, which includes: atmospheric exposure, methods of operation and storage. The influence of moisture, mineral fertilizers and their combinations significantly reduces the resource of the structural elements of agricultural machines, especially when the protective coating is damaged. Corrosion damage is formed on such surfaces of load-bearing nodes of metal structures, corrosion-fatigue surface cracks are born, which grow to critical sizes, and there is a danger of machine failure. Classical methods of calculation-experimental assessment of durability at the stage of initiation of fatigue cracks in structural systems are based on the assumption of integrity of materials and the inadmissibility of fatigue damage in the most dangerous intersections of structural elements. These approaches do not provide adequate forecasting of the machine's resource, so it is necessary to apply the provisions of the mechanics of destruction.

Assessment and forecast of water resources use in Uzbekistan

The article examines the assessment of the state and problems of irrigation water use in the republic in the past and in the near future. A comparative analysis of the state of water resources use for the period of the last 30 years from 1989 to 2019 was carried out. According to the estimates, own water withdrawal for 5 years (2014 / 15-2018/19) shows that an average of 53.2 billion m3 were used for irrigation, including 50.5 billion m3 from rivers. At present (2018-2019), an average of 57.06 billion m3 of water is taken for irrigation of 4.289 million hectares of land, against 63.02 billion m3 approved in 1989. At the same time, the actual water consumption amounted to 48.9 billion m3. Specific water consumption (in the years of average water content) in the Amudarya river basin is 12.5 thousand m3/ha, in the Syrdarya basin - 10.4 thousand m3/ha. Forecast calculations show that there is a tendency to reduce water from rivers to agriculture by an average of 0.104 billion m3/year, with an increase in other sectors from 11.53% (communal and household sector) to 100% (fisheries). The volume of discharges into CDS is decreasing due to the use of collector-drainage waters throughout the region, while specific water consumption has increased to 11.50 thousand m3/ha, i.e. by 450 m3/ha or 28.1%. The reasons for the lack of water for irrigating agricultural crops during the period of vegetative irrigation are stated. The issues of water saving and ways of transition to modern technologies for the use of surface and ground waters, redistribution of water and solutions for the interstate use of river resources are touched upon.

A two-stage fuzzy nonlinear combination method for utmost-short-term wind speed prediction based on T-S fuzzy model

Wind speed prediction is a complex task in the field of wind energy resource forecasting. For prediction, highly nonlinear temporal features are required for wind speed time series, which are highly variable data sources. In this paper, a two-stage fuzzy nonlinear fusion model is proposed for the utmost short-term wind speed prediction problem of 5 and 15 min ahead. First, empirical mode decomposition decomposes the wind speed time series, and the resulting intrinsic mode functions (IMFs) are employed as features in the later modeling study. The first stage of modeling follows. Each IMF feature is fed into one of the three sub-models of the T-S fuzzy model based on triangle, fuzzy C-mean clustering, and Gaussian, yielding three prediction outputs. The second stage is then modeled, which takes advantage of the IT2-based nonlinear aggregation mechanism to overcome the inherent flaws of single methods and linear combinations. Finally, two real cases from wind farms in Colorado, USA, are analyzed to demonstrate the validity of the TFG-IT2 model. The prediction effect of various approaches was measured using three assessment indicators and a statistical test. The simulation results reveal that the TFG-IT2 model outperforms the other seven models in terms of prediction accuracy.

Rock point load test (PLT index) and its correlation with rock coring rate of bored pile machine

Rock socketed cast in-situ bored pile has getting more common in the local foundation industry due to high load carrying capacity to support the increasingly large superstructure load. The estimation of bored pile production rate based on rock strength is vital for piling contractor in terms of project planning, site work done forecasting and management of resources. Uniaxial compressive strength (UCS) of rocks is a useful parameter needed for analytical and designing purpose for rock structure, as well as classification of rock strength. Owing to the time-consuming, tedious and expensive testing procedure of UCS, point load test (PLT) on irregular lump samples has appeared to be the best alternative test to ascertain rock strength, which can be performed on-site or off-site. This research was conducted to establish the correlation between rock PLT index and rock coring rate of bored pile machine, where the PLT results and rock coring data were collected from manual recording at respective project site. Graphical relationship was derived for PLT index against rock coring rate for several pile size categories. As rock UCS is typically adopted for foundation design purpose, the conversion factor between PLT index and UCS was derived for the typical bedrock formation encountered in Kuala Lumpur, namely Granitic rock and Limestone. This study also depicts the estimation of mobilized rock unit shaft friction with respect to the corresponding UCS value, using a recommended empirical formula. From this research study, it was justified that PLT could serve as a cost-effective and straightforward field test which provides invaluable guidance for piling production rate estimation as well as better engineering judgement in foundation design.

Analysis and Forecast of Water Resources and Optimization of Water Transfer Plan

Analysis and Forecast of Water Resources and Optimization of Water Transfer Plan

The hourly wind-bias-adjusted precipitation data set from the Environment and Climate Change Canada automated surface observation network (2001–2019)

Abstract. The measurement of precipitation in the Environment and Climate Change Canada (ECCC) surface network is a crucial component for climate and weather monitoring, flood and water resource forecasting, numerical weather prediction, and many other applications that impact the health and safety of Canadians. Through the late 1990s and early 2000s, the ECCC surface network modernization resulted in a shift from manual to automated precipitation measurements. Although many advantages to automation are realized, such as enhanced capabilities for monitoring in remote locations and a higher frequency of observations at lower cost, the increased reliance on automated precipitation gauges has also resulted in additional challenges, especially with data quality and homogenization. The automated weighing precipitation gauges used in the ECCC operational network have an increased propensity for wind-induced undercatch of solid precipitation. One outcome of the World Meteorological Organization (WMO) Solid Precipitation Intercomparison Experiment (SPICE) was the development of transfer functions for the adjustment of high-frequency solid precipitation measurements made with gauge/wind shield configurations used in the ECCC surface network. Using the SPICE universal transfer function (UTF), hourly precipitation measurements from 397 ECCC automated climate stations were retroactively adjusted for wind undercatch. The data format, quality control, and adjustment procedures are described here. The hourly adjusted data set (2001–2019; version v2019UTF) is available via the ECCC data catalogue at https://doi.org/10.18164/6b90d130-4e73-422a-9374-07a2437d7e52 (ECCC, 2021). A basic spatial impact assessment shows that the highest relative total precipitation adjustments occur in the Arctic, where solid precipitation has an overall higher annual occurrence ratio. The highest adjustments for solid precipitation are shared by the Arctic, Southern Prairies, and the coastal Maritimes, where stations tend to be more exposed and snowfall events occur at higher wind speeds.

The application of specialised management assistants in demand forecasting of human resources

ObjectiveBased on a theoretical analysis and through working practice, this paper presents the experience of the scientific use of the manpower demand prediction method and practical process of specialised business assistants in clinical departments. MethodsA spot observation, interview and public information inquiry were conducted, and SPSS20.0 Chinese software was used to make a statistical prediction of the business growth (P & LT; 0.05). ResultsThe specialist management assistant prepared the manpower needs assessment report for the department, and the hospital organization personnel department adopted the recommendation in the manpower needs assessment report and put it into the hospital's recruitment plan for the following year. ConclusionThe blood purification centre of specialised business assistants in patients in the medical market, service people, workload and equipment operation efficiency analysis data analysis. It was found that an effective prediction model that supports decisions regarding the hospital's scientific allocation of human resources is advantageous to the hospital's human resource optimisation, improves both operation equipment efficiency and patient satisfaction and is worthy of application and popularisation.

Implementation of an Adaptable COVID-19 Utilization and Resource Visualization Engine (CURVE) to Depict In-Hospital Resource Forecasts Over Time

We developed an interactive web-based, decision support application that can adapt to the rapid pace of change in region-specific pandemic related variables and knowledge, thereby providing timely, accurate insights to inform a large healthcare system’s proactive response to COVID-19 hospital resource planning. We designed the COVID-19 Utilization and Resource Visualization Engine (CURVE) app to be adaptable to real-time changes as the pandemic evolved, enabling decisions to be supported by contemporary local data and accurate predictive models. To demonstrate this flexibility, we sequentially implemented a Susceptible-Infected-Removed (SIR) model that incorporates social-distancing and imperfect detection (SIR-D2), an extended-state-space Bayesian SIR model (eSIR), and a time-series model (ARIMA). CURVE improves upon other pandemic forecasting solutions by providing adaptable decision support that generates locally calibrated forecasts aligned to health system specific data to guide COVID-19 pandemic planning. The app additionally enables systematic monitoring of forecast model performance and realignment that keeps pace with the pandemic’s volatile spread and behavior. CURVE provides a flexible pandemic decision support framework that places the most accurate, locally relevant information in front of decision makers to enable health systems to be proactive and prepared.

Insights into methodologies and operational details of resource adequacy assessment: A case study with application to a broader flexibility framework

Assessing and maintaining resource adequacy (RA) is a core pillar of power systems. However, recent changes in the physical makeup of these systems and the conditions under which these systems must operate have yielded a renewed interest in the methods, metrics, and assumptions that underpin RA assessments. In this paper, we systematically explore a wide range of RA modeling dimensions, including: the objective function and level of operational detail in the underlying model formulation; the quantity (look-ahead) and quality (accuracy) of data that is available for making operational decisions within those models; and the physical configuration of solar photovoltaics (PV) with battery storage hybrid resources. We apply a set of probabilistic RA tools and production cost modeling tools to a realistic test system based loosely on a future Electric Reliability Council of Texas power system dominated by solar PV resources. Under the assumptions of our system and models, we find that multi-stage probabilistic assessments may provide a more robust evaluation of RA by capturing a wider range of operational and system interactions, but this comes at a computational cost of 1–2 orders of magnitude longer run time depending on the specific configuration. In addition, the information on thermal generator availability impacts RA performance by an order of magnitude more than solar resource forecasts, which is driven by the comparatively larger magnitude of thermal outages than solar forecast errors within our test system. Lastly, the flexibility provided by hybrid and other resources can help reduce system load-shedding event frequencies and enable the system to be more robust to inaccurate forecast information, and alternative hybrid inverter sizes can impact RA levels by 1–2 orders of magnitude. Our results point to the importance of a broader flexibility framework to describe the interaction between (1) flexibility “supply” from both physical resource capabilities and operational constraints considered in the modeling, and (2) flexibility “demand” from forecast errors, thermal generator outages, and other sources of uncertainty, as well as their RA impacts. Results are likely sensitive to the system buildout explored; future work could consider additional system configurations and conditions.

Efficacy and application of the window-sliding ARIMA for daily and weekly wind speed forecasting

Accurate forecasting of renewable energy resources has a deep societal and environmental impact. In this work, we investigate the efficacy and applicability of the Window-Sliding ARIMA (WS-ARIMA) method for daily and weekly forecasting of wind speed. The WS-ARIMA technique with a fixed or variable window length belongs to the class of adaptive models. Particularly, the sliding windows of fixed length are popular in the areas of finance, energy, and traffic management, where the dataset of necessity exhibits a seasonal pattern. To carry out the proposed analysis, the following processes were done: (1) we first perform a stationarity test on the wind speed data and observe weak stationarity; (2) we then apply a grid search method to obtain the optimal parameters of the ARIMA model; (3) we implement the WS-ARIMA method for both daily and weekly wind speed data and compare the results with the conventional ARIMA model, and (4) finally, we perform a residual analysis as a post processing step to examine any systematic bias in the implemented models. The experimental results based on 15 years (2000–2014) of daily and weekly wind speed data collected at four different locations in India reveal that the WS-ARIMA method consistently outperforms the conventional ARIMA method. The inclusion of window sliding in ARIMA has resulted in the overall RMSE reduction up to 75% in daily wind speed data and 50% in the weekly data. Therefore, we recommend the WS-ARIMA model as one of the potential techniques in wind speed forecasting at daily and weekly time horizons.

Ultra-Short-Term Spatiotemporal Forecasting of Renewable Resources: An Attention Temporal Convolutional Network-Based Approach

The rapid increase in the penetration of renewable energy resources characterized by high variability and uncertainty is bringing new challenges to the power system operation. To ensure the efficient and reliable operation of electric grid, an accurate and general short-term forecasting algorithm with interpretability is desired. Moreover, the extensive off-site information provided by the proliferation of new renewable plants stimulates the interests in the spatiotemporal forecasting. In this paper, an attention temporal convolutional network, which is built on stacked dilated causal convolutional networks and attention mechanisms, is proposed to perform the ultra-short-term spatiotemporal forecasting of renewable resources. Compared with the existing spatiotemporal forecasting methods, the presented model needs no domain knowledge and can be applied to different forecasting tasks such as solar generation and wind speed forecasting. The attention mechanism improves the interpretability. The algorithm can be used to produce both point and probabilistic forecasts. Numerical results on the data sets from National Renewable Energy Laboratory show superior performance over five baselines, in terms of skill scores. Compared with the baselines, the average improvements of accuracy introduced by the proposed method for the point and probabilistic forecasting are 15.08% and 15.85%, respectively.

Forecast-planning system of financial support for the development of industrial enterprises

The aim of the article is to develop a forecast-planned system of financial support for enterprise development based on approaches to forecasting factors influencing the need for financial resources to ensure enterprise development and planning financial support for enterprise development. In order to ensure high-quality and accurate forecasting of external and internal environmental factors necessary for further planning and the possibility of sound planning, the system has formed forecasting and planning modules. Based on the structure of the forecasting module with the identification of key factors influencing the financial security of the enterprise and comparing the most effective forecasting methods, an approach to forecasting factors influencing the need for financial resources in ensuring the development of agricultural machinery. The forecasting module is built by combining quantitative forecasting methods based on the approximation of existing trends with quantitative and qualitative approaches based on expert assessments. Based on a combination of balance, calculation-analytical and program-target planning and formalization of the choice of the date of the beginning of measures to manage financial security depending on the importance of the event, an approach to planning financial support for enterprise development. In the planning module, the external element in relation to the financial management system is the goal-setting system of the enterprise, which determines the mission and its goals in the areas of development. Approbation of the forecast-planning system at PJSC "Harvesters" was carried out. The results would be useful for practitioners, for the effective implementation of sustainable planning and forecasting of enterprise resources in accordance with the objectives of its development.