Resource Forecasting Research Articles

Assessment of rainwater resources in urban areas of reception basins of south-to-north water diversion project under climate change

The forecasting of future stormwater resources serves a pivotal role in gauging the potential effects of stormwater utilization on natural and societal systems. However, there has been limited research on the effect of climate change on future rainwater resources, particularly for large-scale water diversion projects. Based on global climate model data, future land use data and SCS-CN (soil conservation service curve number) model, this study proposed a calculation method of rainwater resources under different SSP scenarios in the future period, and carried out a case study on the cities in the receiving area of South-to-North Water Diversion Project (SNWDP). The results show that there will be an increase in the amount of rainfall in the future compared to 2020.The most significant increase in rainwater resources occurs in urban reception areas of the Eastern Route Project (ERP). However, according to future projections, the quantity of rainwater resources in the study area decreases from south to north. The spatial distribution of rainwater resources demonstrates a nearly normal distribution in the eastern and western routes and a bimodal distribution in the Central Route Project (CRP). In the context of global climate change, the increase in rainfall resources in the CRP may be beneficial for the establishment and implementation of the SNWDP. This study can provide a reference for analysing the uncertainty of rainwater resources in the future period under climate change. It can also provide guidance for the construction and develop scheduling schemes of the SNWDP, a world-class water diversion project.

Application of RNN-LSTM in Predicting Drought Patterns in Pakistan: A Pathway to Sustainable Water Resource Management

Water is a fundamental and crucial natural resource for human survival. However, the global demand for water is increasing, leading to a subsequent decrease in water availability. This study addresses the critical need for improved water resource forecasting models amidst global water scarcity concerns exacerbated by climate change. This study uses the best weather and water resource forecasting model for sustainable development. Employing a Recurrent Neural Network–Long Short-Term Memory (RNN-LSTM) approach, the research enhances drought prediction capabilities by integrating secondary data of the rainfall, temperature, and ground and surface water supplies. The primary objective is to forecast water resources under changing climatic conditions, facilitating the development of early warning systems for vulnerable regions. The results from the LSTM model show an increased trend in temperature and rainfall patterns. However, a relatively unstable decrease in rainfall is observed. The best statistical analysis result was observed with the LSTM model; the model’s accuracy was 99%, showing that it was quite good at presenting the obtained precipitation, temperature, and water data. Meanwhile, the value of the root mean squared error (RMSE) was about 13, 15, and 20, respectively. Therefore, the study’s results highlight that the LSTM model was the most suitable among the artificial neural networks for forecasting the weather, rainfall, and water resources. This study will help weather forecasting, agriculture, and meteorological departments be effective for water resource forecasting.

Monitoring of spatio-temporal glaciers dynamics in Bhagirathi Basin, Gharhwal Himalayas using remote sensing data

Glacier retreat represents a highly sensitive indicator of climate change and global warming. Therefore, timely mapping and monitoring of glacier dynamics is strategic for water budget forecasting and sustainable management of water resources. In this study, Landsat satellite images of 2000 and 2015 have been used to estimate area extent variations in 29 glaciers of the Bhagirathi basin, Garhwali Himalayas. ASTER DEM has been used for extraction of glacier terrain features, such as elevation, slope, area, etc. It is observed from the analysis that Bhagirathi sub-basin has a maximum glaciated area of ~ 35% and Pilang has the least with ~ 3.2%, whereas Kaldi sub-basin has no glacier. In this region, out of 29 glaciers, 25 glaciers have shown retreat, while only 4 glaciers have shown advancement resulting in a total glacier area loss of ~ 0.5%, while the retreat rate varies from ~ 0.06 m/yr to ~ 19.4 m/yr. Dokarni glacier has maximum retreat rate (~ 19.4 m/yr), whereas Dehigad has maximum advancing rate (~ 10.1 m/yr). Glaciers retreat and advance have also been analyzed based on terrain parameters and observed that northern and southern orientations have shown retreat, whereas the area change is highly correlated with glacier length. The study covers more than 65% of the total glaciated area and based on the existing literature represents one of the most exhaustive studies to cover the highest number of glaciers in all sub-basins of the Bhagirathi basin.

System of automated monitoring and forecasting of the remaining resource of pipeline transport

This article presents a system of automated monitoring and forecasting of the residual resource of pipeline transport, consisting of a developed and manufactured information and diagnostic complex for monitoring the technical condition of pipeline transport and software. Informative frequency ranges for monitoring the technical condition of pipeline transport are determined. Experimental studies have been conducted to confirm the effectiveness of the developed technical solution. The paper considers the problems of reliability of pipeline transport. The analysis of existing methods for assessing the technical condition of pipelines is carried out. A system of automated monitoring and forecasting of the residual resource of pipeline transport has been developed. Experimental studies have been conducted. The methods of circuit and simulation modeling, the theory of automatic control, experimental planning, decision-making, probabilistic and statistical methods of mathematical processing and the method of finite element analysis were used in the performance of the work. Based on the resultsof the study, a new methodology for assessing the technical condition of pipeline transport has been developed.

Expected credit loss modeling

This article proposes a method for modeling the probability of default, describes the statistical evaluation of the model, and presents a model of the software implementation algorithm. The algorithm automatically selects from the group of regression models where the models are both linear regression and various modifications of semi-logarithmic models and lag models for macro factors Xi,t,Xi,t-1, ...,Xi,t-TStatistical analysis is carried out using the coefficient of determination R-squared, p-value, VIF (variance inflation factor).The relevance of this topic is determined by the need for banking organizations to comply with international standards, such as International Financial Reporting Standards (IFRS 9) and the Agreement on Banking Supervision and Capital (Basel 3). These standards define credit risk assessment requirements and capital requirements. Adherence to these standards is important not only for ensuring the stability and reliability of the financial system, but also for maintaining the trust of clients and investors. Compliance with international standards also makes banks competitive in the global market and promotes investment inflows and the development of the financial sector.IFRS 9 can be presented in various mathematical models. The article proposes an approach to choosing the appropriate model for forecasting the probability of default. The described model selection method allows banks to choose the optimal default forecast assessment model within the framework of the given standard. This contributes to a more accurate and reliable assessment of credit risk, in accordance with regulatory requirements, which will provide banks with the means for better forecasting and management of financial resources, as well as risk reduction.The model selection methodology saves a significant amount of time and resources, since the search for the optimal model occurs automatically. This allows us to react more quickly to changes in the economic environment, improve decision-making strategies and manage credit risks, which is of great importance for financial institutions in a competitive environment.There is currently a war going on in Ukraine, and forecasting using current methods becomes a difficult task due to unpredictable stressful situations for the economy. In such conditions, standard models may not be sufficiently adapted to account for increased risk and volatility. The proposed approach allows finding more conservative forecasting models that can be useful in unstable periods and war.

DeepFore: A Deep Reinforcement Learning Approach for Power Forecasting in Renewable Energy Systems

An open network known as the “energy internet” links every component of the whole energy supply chains, from the generations. Due to their ability to mimic regional flow dynamics that have an impact on wind farm production, regional meteorological models are increasingly being used as a general tool for wind resource forecasting. In this study, higher vertical and horizontal resolutions WRF (weather research and forecasting) paradigm simulation are used to anticipate and validate production for a genuine onshore wind farm. This paper proposed a DeepFore which is a power forecasting system for hybrid renewable energy systems. Initially, the dataset is generated by the hybrid system. This data is preprocessed to improve the quality of the data by incorporating, filtering and outlier detection techniques. Then, this enriched data is fed into K++ means clustering algorithm to separate the normal data from faulty data. With the normal and original data, Teaching-Learning based optimization algorithm attempts to realize the optimal features which are important for forecasting. Finally, Deep SARSA which is deep reinforcement learning algorithm is incorporated to determine the power generated by the hybrid system. Better winds energy prediction estimations enable more efficient utilization of the produced electricity, according to computational models.

Forecast-based stochastic optimization for a load powered by wave energy

Stand-alone renewable energy systems, which harness and use electricity without connection to a distribution grid, can benefit from using resource forecasts when making real-time decisions on how to manage power. An example of this is an ocean observation system that uses a wave energy converter (WEC) and battery bank to produce and store electricity in order to meet electrical load requirements for oceanographic sensors and instrumentation. By using wave forecasts to optimize the power consumption of this system, it is possible to reduce the size of the WEC and battery bank needed, thereby reducing the overall system’s cost and complexity. In this paper, we assess the benefits of forecasting for a generic wave-powered ocean observation system. We model an observation platform powered by a WEC and battery-storage system that can switch between four power states, full power: 600 W, medium power: 450 W, low power: 45 W, and survival mode: 1 W. To determine which power state to enter over time, we present a stochastic optimization method that interprets wave forecasts and system information to select a power state on an hourly basis and simulate over two months of consecutive decisions. Using this simulation framework, we compare 8 power management strategies across a range of WEC sizes (3–5 m) and battery capacities (2.5–35 kWh). We find that it is possible to maintain full (600 W) power consumption over the entire simulation window with a 5 m diameter WEC and 25 kWh battery bank, which is on the upper end of the ranges evaluated. To employ a smaller WEC or battery, load flexibility is required. We find that forecast-based methods for this power management handle tradeoffs in performance (e.g., cumulative power consumption, reducing intermittencies and meeting scheduled load targets) more effectively than power management strategies that do not use forecasting. Overall, our results indicate that forecasting for our stand-alone renewable energy system is most impactful when some loads must be met on or within a defined schedule.

Predicting Biochemical Oxygen Demand at the Inlet of Al-Rustumiya Wastewater Treatment Plant Using Different Mathematical Techniques

Water quality planning relies on Biochemical Oxygen Demand BOD. BOD testing takes five days. The Particle Swarm Optimization (PSO) is increasingly used for water resource forecasting. This work designed a PSO technique for estimating everyday BOD at Al-Rustumiya wastewater treatment facility inlet. Al-Rustumiya wastewater treatment plant provided 702 plant-scale data sets during 2012-2022. The PSO model uses the daily data of the water quality parameters, including chemical oxygen demand (COD), chloride (Cl-), suspended solid (SS), total dissolved solids (TDS), and pH, to determine how each variable affects the daily incoming BOD. PSO and multiple linear regression (MLR) findings are compared, and their performance is evaluated using mean square error, relative absolute mistake, and coefficient of determination. PSO utilised COD, TDS, SS, pH, and Cl- as inputs, generating a mean square error of 1029.10, an average absolute relative error of 9.41%, and a coefficient of determination of 0.89. Comparisons demonstrated that the PSO model could accurately calculate the daily BOD at Al-Rustumiya wastewater treatment plant's inlet.

Prediction of solar energy forecasting by using linear and logistic regression : A review and geographical comparative analysis in Indian context

Power generation from renewable resources is now-a-days recognized as an necessary basic skill to improve the operation of power system. Forecasting of the renewable energy is the important factor. This study on renewable energy forecasting Techniques gives the more knowledge about how the renewable energy is forecasted and how the renewable energy is converted to the electrical power. And it tells various techniques and methods for the forecasting of renewable energy resources. India is geographically diversified due to its different climatic conditions and we have collected data from solar energy sources from 6 different locations. It comprises the data collected over a period of around one year solar plant output, solar irradiations and temperature of the PV plant. The datasets are considered for training to supervised learning algorithms with linear and logistic regressions by considering short term forecasting and predict immediate next day by using last 28 days data.

Modernization of methodological approaches to the organizational-technological and economic-management support of development projects

The article focuses on key aspects of inventory management within the context of the construction industry. It addresses issues related to the implementation of an inventory management system, particularly considering various types of risks that can impact supply chains and developing strategies to minimize them. The article emphasizes the importance of effective management of relationships with suppliers, as they play a crucial role in ensuring the stability and reliability of supplies. A comprehensive approach is proposed, which includes the development and implementation of a mathematical model for optimizing the cost parameters of material flow. The model is based on generalized nomenclature cases and allows enterprises to conduct more efficient planning and control of expenses during the stages of product movement and storage. The importance of a strategic approach to supply chain management is demonstrated, taking into account the specificity and dynamics of the construction industry. Particular attention is given to adapting the model to different market conditions and the needs of specific enterprises, which allows for achieving high flexibility and efficiency in managing material flows. The article highlights the analysis of multi-nomenclature supply, which is an important aspect for the construction industry where the need for a variety of materials and components is high. It also includes a parametric base, encompassing the analysis of storage area, restrictions on the minimum size and cost of delivered products, storage costs, potential order volumes, and the assessment of lost benefits. This analysis enables the identification of key points for optimization and implementation of changes in supply chains. The main contribution of the article lies in the development of a model that can be adapted for different types of enterprises in the construction industry. The presented model allows for effective inventory management, reducing associated costs while simultaneously increasing overall productivity and the quality of supply chain management. The article separately considers methods of analysis and forecasting of material resource needs, which are important for ensuring continuity and efficiency of construction processes. The importance of flexibility in supply chains in response to changes in demand and market conditions is highlighted, as well as the necessity of integrating modern information technologies for more effective data and process management. Specific recommendations and methodologies are proposed, which can be useful for managers involved in planning and optimizing supply chains. These recommendations include strategies for balancing between costs and efficiency, methods for risk assessment and management, and approaches for integrating new technological solutions.

Wind Energy Assessment Using Weibull Distribution with Different Numerical Estimation Methods: A Case Study

The demand for electrical energy is increasing every day, which is one of the critical challenges facing the world today. Hence, the necessity of turning to clean renewable energy sources that are not harmful to the environment as an alternative to the traditional generation based on fossil fuels has become more important than ever before. Wind power is one of the renewable sources that provides a clean solution to generate electricity. In this context, the Kingdom of Saudi Arabia announces renewable energy projects to generate 9 GW from wind in 2032. Hence, the aim of this paper is to investigate the most suitable method of Weibull parameter estimation in order to predict wind characteristics and employ it for wind energy assessment in the Qassim region located in the center of the country. In this study, wind data is collected from NASA's forecasts of global energy resources for 2010–2015 based on their availability at altitudes of 10m and 50m and analyzed by using six different methods for Weibull parameter estimation: the graphical method (GM), standard deviation method (SDM), energy pattern factor method (EPF), moment method (MM), alternative maximum likelihood method (AMLM), and novel energy pattern factor method (NEPF). The efficiency of each method is tested by calculating the root mean square error (RMSE) and the relative wind power density error (RPDE). The comparison shows that the most appropriate method for estimating wind power density in the country is the Moment Method (MM), with the lowest RPDE ratio equal to 0.2018%. It has been found that the wind power density in the Qassim region falls into the class 1 category, as it is less than 100 W/m2 at a height of 10m and less than 200 W/m2at an altitude of 50m. The results show the region is only suitable for small off-grid projects. Doi: 10.28991/ESJ-2023-07-06-024 Full Text: PDF

Research on demand forecasting and distribution of emergency medical supplies using an agent-based model

The global health crisis caused by SARS-CoV-2 since 2019 has emphasized the critical significance of effective disease detection and treatment in minimizing infection rates and fatalities, as well as halting the spread of pandemics. During an outbreak, individuals suspected of being infected require a significant amount of testing resources, while those confirmed to be infected demand substantial treatment resources. Hence, this paper is dedicated to presenting a new pandemic model that enables joint forecasting and allocation of resources for testing and treatment. The proposed model in this paper is an innovative agent-based epidemic compartmental model, which also incorporates a mixed integer model. It integrates novel features based on crucial disease characteristics, such as self-healing for asymptomatic or mild-symptomatic cases, varying infection risk levels among different groups, and the inclusion of secondary infections. Moreover, the solutions of the joint allocation model are compared with those of the independent allocation model, which entails considering resource interactions rather than allocating each resource independently. Furthermore, the validity of this model was confirmed through real-world data obtained during the SARS-CoV-2 outbreak in China. The findings offer valuable insights into the impact of intervention levels and duration, joint allocation schemes, as well as optimal allocation of test and treatment resources on cross-regional transmission of the pandemic.

Gaussian Adapted Markov Model with Overhauled Fluctuation Analysis-Based Big Data Streaming Model in Cloud.

An accurate resource usage prediction in the big data streaming applications still remains as one of the complex processes. In the existing works, various resource scaling techniques are developed for forecasting the resource usage in the big data streaming systems. However, the baseline streaming mechanisms limit with the issues of inefficient resource scaling, inaccurate forecasting, high latency, and running time. Therefore, the proposed work motivates to develop a new framework, named as Gaussian adapted Markov model (GAMM)-overhauled fluctuation analysis (OFA), for an efficient big data streaming in the cloud systems. The purpose of this work is to efficiently manage the time-bounded big data streaming applications with reduced error rate. In this study, the gating strategy is also used to extract the set of features for obtaining nonlinear distribution of data and fat convergence solution, used to perform the fluctuation analysis. Moreover, the layered architecture is developed for simplifying the process of resource forecasting in the streaming applications. During experimentation, the results of the proposed stream model GAMM-OFA are validated and compared by using different measures.

Research on the Influence of Electric Vehicle Integration in Island Microgrid, Vietnam

Vietnam's economy is developing strongly, and the demand for energy use will increase rapidly. The development of smart grids contributes significantly to the transition and sustainable development of energy from renewable energy sources to improve the quality of the national power supply and promote the sustainable use of electricity economically and efficiently. Thus, this is highly beneficial in reducing carbon emissions and other types of pollution. Besides, electrification in the transportation industry is developing rapidly, such as Electric Vehicles (EVs) and Metros in recent years. Integrating electric vehicles into the grid will enable two-way energy exchange, reactive power compensation and load balancing. However, the number of EVs participating in charging at a time will cause some conflicts, such as voltage and power loss at the nodes. Therefore, the balancing problem between load demand and generation source is a difficult task in planning operations. This paper presents a method to optimize island Microgrid (MG) operation with the participation of electric vehicles based on renewable energy sources. Optimization techniques in intelligent resource forecasting and management algorithms are built in MATLAB to achieve different requirements. The proposed Microgrid manages energy efficiency that adapts to the variability of Renewable Energy with improved efficiency.

Eagle arithmetic optimization algorithm for renewable energy-based load frequency stabilization of power systems

Power systems' efficient management and planning are crucial in renewable energy-based systems. As the global electricity demand continues to rise, there is a growing need for alternative energy sources such as solar, wind, and hydropower. Consequently, numerous research studies have focused on maintaining load balancing within the renewable energy system and improving the forecasting of renewable energy resources. This paper presents the Eagle Arithmetic Optimization Algorithm (EAOA) as a novel approach to address these challenges. By utilizing a fuzzy-based dragonfly optimization algorithm (fuzzy-DFOA), the proposed method enhances the accuracy of load-balancing analysis in renewable energy resources. Through its innovative techniques, the EAOA demonstrates its potential to significantly improve the efficiency and effectiveness of managing renewable energy systems, paving the way for a more sustainable and reliable power grid. The accuracy rate of both wind and solar datasets is given. For the wind dataset, our proposed work got 92.63%, SVR got 75.89%, CNN got 87.54%, and QODA got 83.16%. For the solar dataset presented work of fuzzy-based DFOA got 92.59%, SVR got 69.16%, CNN got 86.25%, and QODA got 82.37%.

An intuitive unified hybrid approach for medium to long-term forecasting of different renewable energy sources

Forecasting of stochastic renewable energy resources is quintessential for effective planning, operations and management of the power systems. Existing literature contains ample studies on very short and short-term forecasting of renewables. But it’s still challenging to obtain high accuracy for medium-term and long-term forecasting. Therefore, an intuitive unified hybrid approach is proposed in this paper for medium to long-term forecasting of power generation from different weather-dependent renewables single-handedly by utilising their inherited periodic seasonal patterns iteratively year-on-year basis. Bi-LSTM (Bidirectional Long Short Term Memory) and ARIMA (Auto Regressive Integrated Moving Average) are utilised to construct the proposed approach with the aid of STL (Seasonal-Trend decomposition using Loess) decomposition and data pre-processing. The performance of proposed approach (STL-ARIMA-BiLSTM) is validated using seven recent datasets of wind, solar and hydro power. It yields accurate forecasts for a week-ahead to a year-ahead forecasting horizons. MAE (Mean Absolute Error) lying in range from 6.3% to 6.6%, 5.6% to 6.7% and 4.72% for a year-ahead forecast of wind, hydro and solar power, respectively, is obtained. It is established that these long-term forecast errors are even less than the short-term forecast errors of some of the existing studies demonstrating novelty and practicality of the proposed approach.

The Application of Information Systems to Improve Ambulance Response Times in the UK

Emergency ambulance services in the UK are tasked with providing pre-hospital patient care and clinical services with a target response time between call connect to on-scene attendance. In 2017, NHS England introduced four new response time categories based on patient needs. The most challenging is to be on-scene for a life-threatening situation within seven minutes of the call being connected when such calls are random in terms of time and place throughout a large territory. Recent evidence indicates emergency ambulance services regularly fall short of achieving the target ambulance response times set by the National Health Service (NHS). To achieve these targets, they need to undertake transformational change and apply statistical, operations research and artificial intelligence techniques in the form of five separate modules covering demand forecasting, plus locate, allocate, dispatch, monitoring and re-deployment of resources. These modules should be linked in real-time employing a data warehouse to minimise computational data and generate accurate, meaningful and timely decisions ensuring patients receive an appropriate and timely response. A simulation covering a limited geographical area, time and operational data concluded that this form of integration of the five modules provides accurate and timely data upon which to make decisions that effectively improve ambulance response times.

Intraday probabilistic forecasts of surface solar radiation with cloud scale-dependent autoregressive advection

Solar energy supply is usually highly volatile, limiting its integration into the power grid. Accurate probabilistic intraday forecasts of solar resources are essential to increase the share of photovoltaic (PV) energy in the grid and enable cost-efficient balancing of power demand and supply. Solar PV production mainly depends on downwelling surface solar radiation (SSR). By estimating SSR from geostationary satellites, we can cover large areas with high spatial and temporal resolutions, allowing us to track cloud motion. State-of-the-art probabilistic forecasts of solar resources from satellite imagery account only for the advective motion of clouds. They do not consider the evolution of clouds over time, their growth, and dissipation, even though these are major sources of forecast uncertainty. To address the uncertainty of cloudiness evolution, we present SolarSTEPS, the first optical-flow probabilistic model able to simulate the temporal variability of cloudiness. We demonstrate that forecasting the autocorrelated scale-dependent evolution of cloudiness outperforms state-of-the-art probabilistic advection-based forecasts by 9% in continuous ranked probability score (CRPS). This corresponds to an extension of the forecast lead time by about 45 min at constant CRPS. Our work is motivated by the scale-dependent predictability of cloud growth and decay. We demonstrate that cloudiness is more variable in time at smaller spatial scales than at larger ones. Specifically, we show that the temporal autocorrelation of cloudiness is related to its spatial scale by an inverse power law. We also demonstrate that decomposing cloudiness into multiple spatial scales in the forecasts further improves the forecast skill, reducing the CRPS by 10% and the RMSE by 9%.

An Ensemble Approach for Intra-Hour Forecasting of Solar Resource

Solar resource forecasting is an essential step towards smart management of power grids. This study aims to increase the performance of intra-hour forecasts. For this, a novel ensemble model, combining statistical extrapolation of time-series measurements with models based on machine learning and all-sky imagery, is proposed. This study is conducted with high-quality data and high-resolution sky images recorded on the Solar Platform of the West University of Timisoara, Romania. Atmospheric factors that contribute to improving or reducing the quality of forecasts are discussed. Generally, the statistical models gain a small skill score across all forecast horizons (5 to 30 min). The machine-learning-based methods perform best at smaller forecast horizons (less than 15 min), while the all-sky-imagery-based model performs best at larger forecast horizons. Overall, for forecast horizons between 10 and 30 min, the weighted forecast ensemble with frozen coefficients achieves a skill score between 15 and 20%.

Coupled thermo-electrical dispatch strategy with AI forecasting for optimal sizing of grid-connected hybrid renewable energy systems

In multi-energy systems the full utilisation of the generated energy is a challenge. Integrating heat and electricity supply at the system level design could provide an opportunity to address this challenge. In this paper we introduce and examine two coupled thermal-electrical dispatch strategies for grid-connected hybrid multi-energy systems supplying electrical and thermal demand loads. The dispatch strategy employs forecasting of energy resources and demand loads to prioritise supplying the thermal load in times of renewable surplus. Four forecasting algorithms, namely, baseline forecast, Facebook Prophet (FBP), Neural Prophet (NP), and Long Short-Term Memory model (LSTM) are implemented and used to generate annual forecast data for solar irradiance, wind speed, and thermal and electrical demand loads. To integrate forecast data within the dispatch strategy, new parameters are proposed to quantify the expected available energy within the forecast time horizon. A building complex for the Department of Education in the UK is used for conducting a system design case study. A genetic algorithm-based multi-objective optimisation with the levelised costs of electricity and heat as two objectives is conducted. The results show that the proposed dispatch algorithm produces systems with reduced levelised costs compared to the base case of using utility gas and electricity. Forecasting is particularly useful in reducing cost of heat, as it can prioritise supplying the thermal load in times of renewable surplus. LSTM proved to be the most accurate forecasting algorithm for this case, where the data has strong seasonality and trends. The main contribution of this work is to propose and demonstrate the effectiveness of tightly coupling thermo-electrical dispatch algorithms of HRES from the design stage, and how to effectively integrate forecast data within such algorithms.