Optimized Charge Controller Schedule in Hybrid Solar-Battery Farms for Peak Load Reduction

The goal of this paper is to optimally combine day-ahead solar and demand forecasts for the optimal battery schedule of a hybrid solar and battery farm connected to a distribution station. The objective is to achieve the maximum daily peak load reduction and charge battery with maximum solar photovoltaic energy. The innovative part of the paper lies in the treatment for the errors in solar and demand forecasts to then optimize the battery scheduler. To test the effectiveness of the proposed methodology, it was applied in the data science challenge Presumed Open Data 2021. With the historical Numerical Weather Prediction (NWP) data, solar power plant generation and distribution-level demand data provided, the proposed methodology was tested for four different seasons. The evaluation metric used is the peak reduction score (defined in the paper), and our approach has improved this KPI from 82.84 to 89.83. The solution developed achieved a final place of 5th (out of 55 teams) in the challenge.

Electrical Load Demand Forecasting Using Feed-Forward Neural Networks

The higher share of renewable energy sources in the electrical grid and the electrification of significant sectors, such as transport and heating, are imposing a tremendous challenge on the operation of the energy system due to the increase in the complexity, variability and uncertainties associated with these changes. The recent advances of computational technologies and the ever-growing data availability allowed the development of sophisticated and efficient algorithms that can process information at a very fast pace. In this sense, the use of machine learning models has been gaining increased attention from the electricity sector as it can provide accurate forecasts of system behaviour from energy generation to consumption, helping all the stakeholders to optimize their activities. This work develops and proposes a methodology to enhance load demand forecasts using a machine learning model, namely a feed-forward neural network (FFNN), by incorporating an error correction step that involves the prediction of the initial forecast errors by another FFNN. The results showed that the proposed methodology was able to significantly improve the quality of load demand forecasts, demonstrating a better performance than the benchmark models.

The Role of Temperature Variability on Seasonal Electricity Demand in the Southern US

The reliable and affordable supply of energy through interconnected systems represent a critical infrastructure challenge. Seasonal and interannual variability in climate variables—primarily precipitation and temperature—can increase the vulnerability of such systems during climate extremes. The objective of this study is to understand and quantify the role of temperature variability on electricity consumption over representative areas of the Southern United States. We consider two states, Tennessee and Texas, which represent different climate regimes and have limited electricity trade with adjacent regions. Results from regression tests indicate that regional population growth explains most of the variability in electricity demand at decadal time scales, whereas temperature explains 44–67% of the electricity demand variability at seasonal time scales. Seasonal temperature forecasts from general circulation models are also used to develop season-ahead power demand forecasts. Results suggest that the use of climate forecasts can potentially help to project future residential electricity demand at the monthly time scale.Capsule Summary: Seasonal temperature forecasts from GCMs can potentially help in predicting season-ahead residential power demand forecasts for states in the Southern US.

Optimization of small hydropower systems in water distribution networks through evolutionary algorithms and water demand forecasting

<p>The transition from fossil fuel to renewable energies represents the central challenge of the early 21st century. In this context, small hydro power systems (SHPS) can be implemented in water distribution networks (WDNs) to use pressure and drinking water surplus for hydropower production. However, inflow to SHPS is normally controlled based on the available water volume after ensuring a reliable drinking water supply and considering a fire-fighting reserve. Hence, the hydropower generation in WDNs has to be in accordance with its primary tasks. The challenge now is to optimally use the available pressure and water surplus for hydropower production while at the same time reliably fulfilling drinking water constraints.</p><p>In this work, future predictions of daily water demand are added into the control strategy of SHPS to optimize the operation. The control procedure of a SHPS is optimized by means of an evolutionary algorithm in combination with Monte-Carlo sampling. This is done for different categorized water demand and water source data in order to maximize profit while ensuring the WDNs reliable operation. Further, water demand forecasts of varying quality are evaluated in combination with previously optimized and categorized SHPS control-sets. For case study, a real WDN of an Alpine municipality is hypothetically retrofitted with a controllable SHPS. Different types of SHPS and turbine characterises are investigated using amount of hydropower production, more specifically profitability, as performance indicator.</p><p>While in literature, optimization is usually performed based on representative days (e.g., average day demand), long-term simulations over 10 years are used in this work. Therefore, a sufficient supply pressure in all water demand nodes in the WDN is ensured during this period. This results in a significant lower but more realistic estimation of potential benefits. The results also show, that after optimizing the SHPS location and device size, an additional potential increase of yearly profit of 1.1% can be achieved in the long-term operation of a Pelton turbine by considering water demand forecasts.</p>