Electricity Demand Research Articles

Improving the Economic Feasibility of Small-Scale Biogas-Solid Oxide Fuel Cell Energy Systems through a Local Ugandan Biochar Production Method

A small-scale (up to 5 kWe) biogas-solid oxide fuel cell (SOFC) energy system is an envisioned system, which can be used to meet both electrical and thermal energy demand of off-grid settlements. SOFC systems are reported to be more efficient than alternatives like internal combustion engines (ICE). In addition to energy recovery, implementation of biogas-SOFC systems can enhance sanitation among these settlements. However, the capital investment costs and the operation and maintenance costs of a biogas-SOFC energy system are currently higher than the existing alternatives. From previous works, H2S removal by biochar was proposed as a potential local cost-effective alternative. This research demonstrates the techno-economic potential of locally produced biochars made from cow manure, jackfruit leaves, and jack fruit branches in rural Uganda for purifying the biogas prior to SOFC use. Results revealed that the use of biochar from cow manure and jack fruit leaves can reduce H2S to below the desired 1 ppm and substitute alternative biogas treatments like activated carbon. These experimental results were then translated to demonstrate how this biochar would improve the economic feasibility for the implementation of biogas-SOFC systems. It is likely that the operation and maintenance cost of a biogas-SOFC energy system can in the long run be reduced by over 80%. Also, the use of internal reforming as opposed to external reforming can greatly reduce the system capital cost by over 25% and hence further increase the chances of system economic feasibility. By applying the proposed cost reduction strategies coupled with subsidies such as tax reduction or exemption, the biogas-SOFC energy system could become economically competitive with the already existing technologies for off-grid electricity generation, like solar photovoltaic systems.

Techno-economic Analysis of Hybrid Renewable Energy System for Hydrogen Production in the Demnate Region of Morocco

This paper investigates the techno-economic feasibility of producing electrical energy for three villages in the mountains in the Demnate region. The community needs were determined based on the site visit to identify the electrical load demand in reality. In addition, a site description was done to evaluate the suitable system to produce the electrical energy. Using the Homer software, two systems were selected to produce electricity and hydrogen which are described as follows: The first system is constituted of a PV-Generator with 3759 kW, an Autosize Genset generating 300 kW, a DC/ AC converter supplying 317 kw, 800 kW produced by the electrolyzer, and a hydrogen storage tank with 900 Kg as a capacity. The second system is composed of PV modules with 3743 kw, seven G3 wind turbines with 3kW, an Autosize Genset generating 300 kw, 323 kW of power converters, a generic electrolyzer with an output power of 800 kW, and a hydrogen tank with 900 Kg as capacity. In addition, the financial analysis gives 1.56$/kWh and 1.57$/kWh as the Levelized Cost of Energy and 15.6 M$ and 15.7 M$ as the Net Present Cost for the first and second systems respectively.

Formation to Transportation: En-Route Fission-Facilitated Formation of Spheres in a Phosphorus-Based Porous Organic Polymer for Transportation of Iodine.

Despite its potential as a clean power source to meet rising electricity demands, nuclear energy generates radioactive waste, including isotopes of iodine, that pose significant environmental and health risks. There is a growing demand to capture radioactive iodine and repurpose it effectively. However, achieving this dual functionality with a single material remains a significant challenge. This study explores phosphorus-based porous organic polymers (P-POPs) as probes for these dual functionalities. By employing 4-formyl(triphenyl)phosphine (BB1) and phenyl-1,4-diacetonitrile (BB2) under the Knoevenagel polycondensation method, P-POPs (PKPOPs) have been synthesized that exhibit a smooth spherical morphology, which efficiently captures and release iodine under ambient conditions, facilitating efficient transportation of molecular iodine. This novel approach aims to potentially transform nuclear waste into valuable organic feedstock via an iodination reaction. The innovative application of PKPOP has also been demonstrated for iodination reactions using ball mills and under continuous flow conditions, showcasing its potential for safer waste management and utilization.

Temperature Compensation Model for Monitoring Sensor in Steel Industry Load Management

The iron ore industry faces increasing electricity demand due to industrialization, making effective management of electricity demand crucial. This study proposes a temperature compensation model using Support Vector Regression (SVR), aiming to enhance the accuracy of sensors in monitoring electricity demand. An experiment is conducted to assess the impact of temperature on sensor measurements, and a modified Whale Optimization Algorithm is employed to correct the sensor outputs. The proposed model is compared with both PSO-SVR and unimproved WOA-SVR. Results show that the proposed model significantly improves accuracy, achieving a determination coefficient of 0.7882 and a relative standard deviation of the error square sum of 4.6412%. The results of this study not only enhance power demand management in iron mining but also hold potential applications across various industries.

A Study the optimisation of smart grid power flow

Optimal Power Flow (OPF) is a fundamental concept in the management and operation of modern electrical power systems, particularly within the context of smart grids. As the demand for electricity continues to grow and the energy landscape evolves towards greater sustainability, the need for efficient, reliable, and adaptive power systems has become more critical than ever. The primary objective of OPF is to determine the most efficient way to operate the power system while satisfying various technical and operational constraints. This involves the optimization of several variables, including generator outputs, voltage levels, and power flows, to minimize costs, reduce losses, and enhance system reliability. Smart grids can enhance their resilience to disturbances, support the efficient use of renewable energy, and provide reliable electricity to consumers.

Efektivitas Program Same Day Services Pasang Baru dan Perubahan Daya Listrik di PT PLN (Persero) Unit Layanan Pelanggan (ULP) Jatibarang

The increasing need for electricity is part of the public interest. The availability of electricity must continue to be ensured to support all forms of activity, such as the economy. The government, through PT PLN (Persero), is responsible for distributing electrical energy to remote areas of the country quickly, easily and safely for the community. Based on this, PT PLN (Persero) is trying to provide electricity to the community quickly through the Same Day Services (SDS) Program for New Installation and Power Change. This program is expected to be a breakthrough in responding to the increasing demand for electricity needs of the community over time. Therefore, the aim of this research is to find out how effective the Same Day Services (SDS) New Installation and Electric Power Change Program implemented by PT PLN (Persero) on Customer Service Unit (ULP) Jatibarang. The research method used is descriptive qualitative research. The data taken is based on the results of observations, interviews, documentation, as well as reviewing data sourced from PT PLN (Persero) ULP Jatibarang documents, articles and other news that are relevant to the research topic. The results of this research show that the SDS Program at ULP Jatibarang shows positive results from several effectiveness indicators according to Budiani. Thus, the author concludes that this program has been running effectively.

Building energy consumption analysis and measures: a case study from an administration building in Chengdu, China

With the peak of carbon dioxide emissions and carbon neutrality, China is placing greater emphasis on energy expenditure. Office buildings occupy a prominent position in building energy consumption, which is one of the main energy consumption areas. Taking an administration building in Chengdu as an example, this article simulates the building energy consumption based on Design Builder software, examines the variables influencing energy consumption, and suggests energy-saving strategies combined with fresh ideas for sustainable architectural design. The results showed that the modeling building was a high-energy-consuming building, with an energy consumption of 724,857.59 kWh, and a unit area energy consumption of 288.17 kWh/m2 in Chengdu. For energy conservation and emission reduction, this article proposes the following three energy-saving measures. The first is to apply heat recovery technology for air conditioning systems. The second is photovoltaic glass, which provides partial electricity demand for buildings and reduces dependence on traditional energy sources. The third is roof greening, which utilizes the plants to purify the air and beautify the environment. The results showed that the heat recovery technology in air conditioning systems reduced the total energy consumption of buildings from 642144.04 kWh/m2 to 502937.83 kWh/m2, photovoltaic glass reduced 552243.87 kWh/m2, and roof greening reduced to 635947.35 kWh/m2. All of these have good energy-saving and emission reduction effects. The above three strategies not only help reduce building energy consumption, but also provide substantial support for China to achieve carbon neutrality.

A Hybrid Forecasting Model for Electricity Demand in Sustainable Power Systems Based on Support Vector Machine

Renewable energy sources, such as wind and solar power, are increasingly contributing to electricity systems. Participants in the energy market need to understand the future electricity demand in order to plan their purchasing and selling strategies. To forecast the electricity demand, this study proposes a hybrid forecasting model. The method uses Kalman filtering to eliminate noise from the electricity demand series. After decomposing the electricity demand using an empirical model, a support vector machine optimized by a genetic algorithm is employed for prediction. The performance of the proposed forecasting model was evaluated using actual electricity demand data from the Australian energy market. The simulation results indicate that the proposed model has the best forecasting capability, with a mean absolute percentage error of 0.25%. Accuracy improved by 74% compared to the Support Vector Machine (SVM) electricity demand forecasting model, by 73% when compared to the SVM with empirical mode decomposition, and by 51% when compared to the SVM with Kalman filtering for noise reduction. Additionally, compared to existing forecasting methods, this study’s accuracy surpasses LSTM by 63%, Transformer by 47%, and LSTM-Adaboost by 36%. The simulation of and comparison with existing forecasting methods validate the effectiveness of the proposed hybrid forecasting model, demonstrating its superior predictive capabilities.

Flexible emulation of the climate warming cooling feedback to globally assess the maladaptation implications of future air conditioning use

Abstract Rising affluence and a warming climate mean that the demand for air conditioning (AC) is rising rapidly, as society adapts to climate extremes. Here we present findings from a new methodological framework to flexibly couple and emulate these growing demands into a global integrated assessment model (IAM), subsequently representing the positive feedbacks between rising temperatures, growth in cooling demand, and carbon emissions. In assessing global and regional climate change impacts on cooling energy demand, the emulator incorporates climate model uncertainties and can explore behavioural and adaptation-related assumptions on setpoint temperature and access to cooling. It is also agnostic to the emissions and climate warming trajectory, enabling the IAM to run new policy-relevant scenarios (Current Policies, 2 °C and 1.5 °C) with climate impacts that do not follow Representative Concentration Pathways. We find that climate model uncertainty has a significant effect, more than doubling the increase in electricity demand, when comparing the 95th percentile cases to the median of the climate model ensemble. Residential AC cooling energy demands are expected to increase by 150% by 2050 whilst providing universal access to AC would result in the order of a 400% increase. Depending on the region, under current policies and limited mitigation, climate change could bring in the order of 10%–20% higher cooling-related electricity demands by 2050, and approximately 50% by 2100. Set point temperature has an important moderating role—increasing internal set-point from 23 °C to 26 °C, approximately halves the growth in electricity demand, for the majority of scenarios and regions. This effect is so strong that the change in set point temperature to both residential and commercial sectors outweighs the growth in demand that would occur by providing universal access to AC by 2050 to the 40% of the global population who would otherwise not afford it.

Rule-based energy management strategies for PEMFC-based micro-CHP systems: A comparative analysis

Commercial PEMFC-based micro-CHP systems are operated by rule-based energy management strategies. Each of these strategies constitutes a different way to meet the household energy demand (following the heat demand, following the electricity demand, the maximum of the two, etc.). Previous studies demonstrate that which of them is the best —i.e. the one that manages to meet the demand at the lowest operating cost— depends on the particular scenario in which the micro-CHP system works (gas and electricity prices, annual energy demands, ability to export electricity to the grid, etc.). This paper aims to explore this dependence relationship and to deepen our understanding of it. To this end, a parametric analysis is conducted and the performances achieved by four rule-based operating strategies are compared. The parameters whose influence is studied, and through which the scenario is jointly characterized, are: (1) energy prices (electricity and natural gas), (2) feed-in tariff, (3) stack degradation, (4) climate and (5) heat to power ratio of the demand. The results show this dependence relationship in a clear and more comprehensive way, and offer a better understanding of its nature. From this improved understanding it can be inferred, among other things, that adapting the strategy to the scenario can generate annual savings of up to 14.5 percentage points. Moreover, this enhanced characterization of that dependence relationship can be useful for the design of a new operating strategy, a strategy that, without falling into the complexity that an optimal energy management approach (based on linear programming) involves, manages to exploit the savings potential of micro-CHP systems, thus facilitating their future mass commercialization.

Plug-in charging or electric roads? Powering U.S. long-haul heavy-duty trucks in 2050

Abstract Pervasive plug-in fast chargers and/or electrified roadways (eRoads) might address the limited range, long recharging times, and reliance on greenhouse gas (GHG)-intensive, costly, and heavy batteries associated with electrifying long-haul heavy-duty trucks (HDTs). While these large-scale interventions shift environmental and cost burdens onto infrastructure, there is a lack of studies investigating how eRoads affect system-level GHG emissions, costs, material use, and peak electric grid power demands. We compare these aspects for the case of electrifying U.S long-haul HDTs (Class 8) in 2050 powered by combinations of plug-in fast chargers and eRoads. Our model accounts for battery downsizing, energy consumption, and truck operation patterns in quantifying life cycle impacts of batteries, plug-in chargers, eRoads, and hourly truck electricity demand. We find that plug-in fast chargers and eRoads reduce annualized 2050 HDT life cycle GHG emissions by 8% to 14% compared to using long-range batteries, which in turn have at least 50% lower emissions than diesel trucks. Conductive rails, overhead lines, and wireless eRoads (amortized across light- and heavy-duty vehicles) have lower system-wide costs than long-range batteries, plug-in fast chargers, or diesel trucks. Cost savings from smaller batteries, lower energy use and avoided recharging time offset high eRoads capital costs. While eRoads can reduce both system-level GHG and costs compared to diesel trucks, these reductions are sensitive to eRoads capital costs and losses from wireless power transfer and air resistance. eRoads require less lithium (87%) and copper (67%) than long-range batteries but increase regional peak power demands by up to 32%. Efficient wireless power transfer and aerodynamic pantographs enhance eRoads’ GHG and cost advantages, which may diminish if future batteries are more energy-dense, cheaper, or less GHG intensive. If successfully deployed, eRoads present opportunities for tighter integration between the transportation and electricity infrastructure systems, enabling optimized charging strategies to lower GHG emissions and costs.

A hybrid optimization for distributed generation and D-STATCOM placement in radial distribution network: a multi-faceted evaluation

The deregulation of the power system, upward growth in electrical energy demand and network expansion have resulted in an increasing integration of distributed generation (DG) and distribution static synchronous compensator (D-STATCOM) into radial distribution systems (RDS). Nonetheless, the optimal allocation of these devices is highly important to derive immense benefits. This investigation narrows down on optimizing DG and D-STATCOM placement in IEEE 33-bus RDS with a view to increase bus voltages, decrease power losses as well as maximize economic gains. The study undertakes a comprehensive analysis comparing the technical, economic and environmental performance of DG and D-STATCOM; thereby enabling power engineers to make informed choices concerning which device will be most advantageous when it comes to delivering power in RDS. A fuzzy enhanced firefly optimization (FEFO) approach is proposed for the optimization and a multifaceted evaluation in terms of technical, financial and environmental is presented for effective decision-making on distributed energy resource deployment. D-STATCOM and wind DG integrations led to notable reductions in power loss and pollutant emissions, highlighting their effectiveness in improving power quality and reducing reliance on fossil fuels. While wind DG incurred a higher installation cost ($3,100,749.2) compared to D-STATCOM ($90,566.6), it achieved greater yearly power loss cost savings ($69,198 versus $47,619). FEFO’s efficiency in optimization stands out, aiding engineers in making informed decisions for optimizing D-STATCOM and wind-DG integration in the IEEE-33 RDS, ultimately enhancing system performance and cost-effectiveness through proactive planning. The integration of D-STATCOM and wind DG led to a significant improvement in distribution system efficiency, with D-STATCOM reducing real power loss by 28.7% and reactive power loss by 27.8%, while wind DG achieved greater reductions of 41.8% in real power loss and 37.5% in reactive power loss, alongside reductions in pollutant emissions of 1.5% and 2.2%, respectively.

Potential Utilization of Tamblang Dam for Micro Hydro Power Plant to Increase Renewable Energy Mix for Indonesia

Abstract Bali, a prominent tourist destination in Indonesia, faces an increasing demand for electricity, primarily supplied by non-renewable sources. With a target to increase renewable energy mix, Bali focuses on leveraging its water resources, notably Tamblang Dam, for hydroelectric power generation. This research aims to determine the potential utilization of Tamblang Dam as a micro hydro power plant, highlighting its capacity to significantly contribute to renewable energy mix in Indonesia generally and Bali particularly. Analysis reveals a potential electricity generation of 0.52 MW, with an annual hydro power production estimate of 4.57 GWh. Considering discharge availability, height of falling water and efficiency of hydro power system. The research also underscores the project’s economic viability and profitability, emphasizing its role in fostering sustainable energy practices in the region.

Energy management in a grid-connected microgrid using hybrid Golden Jackal optimization and gradient descent optimization and the concept of loadability

Golden Jackal optimization (GJO) maintains diversity and can simultaneously explore multiple regions of the search space since it operates on a population of solutions. However, the GJO has the demerit of deprived exploitation capability and it struck in local optima easily. For enhanced optimization efficacy, the suggested approach integrates a hybrid optimization algorithm that combines gradient descent and the GJO algorithm. The goal of this hybrid strategy is to influence the complimentary advantages of both algorithms: the local exploitation potential of gradient descent and the global exploration capabilities of GJO. The suggested hybrid method uses GJO to initialize a population of possible results. Then, iteratively exploring the search space, it notifies solutions based on GJO's mechanisms for exploration and exploitation. Furthermore, a portion of the population undergoes refinement using gradient descent in order to effectively converge towards local minima by utilizing local knowledge. The hybrid algorithm demonstrates improved convergence speed, robustness to diverse search space characteristics, and effectiveness in handling large-scale optimization problems compared to various optimization techniques including particle swarm optimization, pelican optimization, artificial bee colony, whale optimization algorithm and grey wolf optimization, standalone GJO and gradient descent algorithms. The total cost of the MG with the proposed methodology has reduced to 12017 rupees from 12350 by gradient descent and 12332 using GJO. Detailed comparison of various optimization techniques has been presented in the results section. Further, this paper also addressed the concept of loadability, which refers to the MG's ability to meet electricity demand under varying conditions, relying solely on its internal resources. Achieving optimal loadability in isolated MGs involves diversifying generation sources, leveraging energy storage systems, implementing demand-side management measures, utilizing predictive analytics, and designing resilient grid infrastructure. By implementing Bayesian sparse polynomial chaos expansion, the concept of loadability has been assessed. Due to which the MG operators can enhance energy management capabilities and maximize loadability, ensuring reliable and sustainable electricity supply to connected loads.

Techno-Economic Analysis of Solar, Wind, and Biomass Hybrid Renewable Energy Systems to Meet Electricity Demand of a Small Village in Bihar State of India

This study examines the potential use of Hybrid Renewable Energy Systems (consisting of photovoltaic, wind, bio, and diesel sources) both with and without the inclusion of battery storage in the eastern region of India. An evaluation is conducted to determine the economic viability of several system configurations, and the most efficient system is selected using HOMER software. The investigation focused on six distinct scenarios to meet the energy needs of a village community. The goal was to satisfy a daily load need of 1093.7 kWh, with a peak demand of 153.63 kW. The study examined many factors, such as system efficiency, financial viability, and ecological consequences. The primary aim of the research was to compare the power costs associated with different designs of HRES. Detailed techno-commercial assessments were carried out to examine the energy production, consumption, and financial impacts of each scenario. This research provides valuable insights for individuals and organizations seeking reliable and long-lasting energy solutions by analyzing the potential benefits and drawbacks of implementing HRES in rural areas. An evaluation is conducted to determine the energy contribution of each element within an RES, as well as the influence of HRES on energy expenses and net present value. The findings of this study reveal that the optimized hybrid system comprises 133 kW photovoltaic arrays, a 130-kW wind turbine, a 0.2 kW biogas generator, a 100-kW diesel generator, a 540-kWh battery bank with nominal capacity, and a 58-kW converter. This system has a minimum COE of 0.347$/kWh and NPC of $1.71M. The research offers useful insights for designers, scholars, and policymakers on the existing design constraints and policies of biomass-based hybrid systems.

Parametric Based Techno‐Economic Evaluation for a Solar Thermal‐PV Integrated Multi‐Commodity Storage Facility

ABSTRACTPostharvest losses and spoilage of agricultural products are a major problem for tropical countries, and it is even more challenging for countries encountering fluctuating power shortages, such as Pakistan. Therefore, this study focused on the energy and economic analysis of cold storage to store three products (potatoes, pomegranates, and potatoes) according to the season and storage span throughout the year. The cooling load of the cold store was supported by a LiBr‐H2O vapor absorption and vapor compression refrigeration system to maintain the desired temperature for each product during cold storage. A solar thermal PV system is installed to operate cold storage refrigeration systems. Cold storage performance was analyzed by developing thermal models of integrated systems using the ambient conditions of Lahore, Pakistan. A parametric study was also conducted to analyze the impact of various working parameters on integrated system performance, and it was found that the maximum peak cooling load of 91 kW inside cold storage is attributed to pomegranates owing to high ambient conditions during its loading month. The product loading rate significantly affects the cooling load of cold storage and varies directly with it, as observed for an increase in the product loading rate from 0 to 50 000 kg/day cooling load also increases from 34 to 87 kW. To meet the thermal demand of the generator of the vapor absorption system, parabolic troughs were installed to operate cold storage, and it was found that a minimum of four PTC were needed to support the peak cooling load at the maximum product loading rate and minimum DNI value. To meet the electrical demand of cold storage electrical equipment and the compressor of the vapor compression system, solar photovoltaic panels were installed, and it was found that a minimum of 618 panels was required at a minimum tilted radiation value. To validate the viability of proposed design system economic analysis was also conducted which revealed a payback period of 12 years for Kinnow and potatoes and 16 years for pomegranates.

On the value of orderly electric vehicle charging in carbon emission reduction

In this study, a bi-level model is developed to quantify the value of orderly electric vehicle (EV) charging in carbon reduction. Specifically, the upper-level model optimizes each EV driver’s charging schedule to diminish the total carbon emissions without impacting their travel plans, and the lower-level problem aims to fulfill electricity demands with minimal electricity dispatch cost. Based on real-world operation data obtained from 3,777 battery EVs (BEVs) in Shanghai over 11 months and local power plant data, the total carbon emissions generated by BEVs in Shanghai is calculated as 1,176,637 tons over this period, averaging 73 gCO2/km per BEV. By administering charging control to all BEVs in Shanghai, the above emission could be curtailed by 39%. Sensitivity analyses uncover that augmenting battery capacity and integrating wind power can significantly enhance emission reductions, while increasing the flexibility of the power plant might diminish the effectiveness of orderly EV charging.

Economy and energy flexibility optimization of the photovoltaic heat pump system with thermal energy storage

Photovoltaic systems have been widely applied in building energy systems. However, with the sharp increase in demand of electricity in buildings during heating and cooling seasons, the uncertainty of photovoltaic generation further exacerbates the peak-valley difference in electricity use. To improve the economy and energy flexibility of buildings in hot summer and cold winter zones of China, a rule-based operation strategy was proposed for the photovoltaic heat pump with thermal energy storage system to optimize the size of the thermal energy storage system and system operation, with aims of minimizing the total annual cost of the system and maximizing the self-consumption rate of the photovoltaic generation. The effects of grid export power limits, grid import power limits, feed-in tariffs, and PV generation on the system operation optimization results were also investigated. The results indicated that by integrating the thermal energy storage system into the photovoltaic heat pump system, the self-consumption rate of the photovoltaic generation was reduced by 2.39 %, the total annual cost of the system was decreased by 6.61 %, and the payback period of the thermal energy storage system was 1.31 years. The optimum size of the thermal energy storage system and the self-consumption rate of the photovoltaic generation decreased with the increasing grid export power limits and grid import power limits. In contrast, higher grid export power limits, grid import power limits, feed-in tariffs, and PV generation all resulted in a lower total annual cost. This study provided a systematic design and operation optimization method for building energy systems.

Subsidies for close substitutes: Aggregate demand for residential solar electricity

Subsidies promoting residential solar systems are intended to reduce carbon emissions by lowering demand for electricity from the grid. The ability of these subsidies to reduce grid demand hinges on how close, on aggregate, the two sources of electricity are to perfect substitutes. To test the efficacy of these policies, we form a tractable model of national residential electricity demand that identifies the aggregate substitutability between residential systems and electricity drawn from the grid. When estimated on the United States, we find that while the two are close to perfect substitutes, the degree to which substitutability is imperfect has material implications for policy. Subsidies inducing one kWh of residential solar electricity demand displace only 0.5 kWh of grid consumption. As an emissions reduction policy, subsidies had national abatement costs of $332 per MTCO2 in 2018.

Applying neural networks for short and long-term hourly electricity consumption forecasting in universities: A simultaneous approach for energy management

Predictive models for energy consumption are increasingly relevant for buildings with medium-high demands, such as public buildings. These models enable effective energy management, especially in contexts of budget constraints, maximizing resource efficiency. Thus, university buildings are interesting cases because they meet the above-mentioned conditions, they can be managed by the public or private sector and have high societal impact. This work aims to simultaneously develop two predictive models for hourly electricity demand in a university building: one for the short-term (next hour) and one for the long-term (all hours of the year). The methodology consists in: analyzing the data using descriptive statistics to identify relevant variables; building the neural network models in Python; and evaluating them with performance indicators. The short-term model, which includes the previous hour's energy as independent variable, achieved a relative error of 16.0 %, an R2 = 91.17, RMSE = 0.512 kWh, and MAE = 0.325 kWh. The long-term model, which omits this variable, showed a relative error of 31.7 %, R2 = 74.69, RMSE = 0.864 kWh, and MAE = 0.566 kWh. The study highlights the effectiveness of neural networks in energy forecasting. It also emphasizes the importance of using the previous hour's energy as a variable to obtain short-term accuracy; but also the possibility of building models without it, allowing for long-term approaches. The novelty lies in the simultaneous approach of two predictive horizons in a university building. This approach can contribute by providing accurate information to energy control algorithms that integrate renewable energy, storage, grid power, etc., to optimize the use of resources and improving environmental sustainability.