This paper introduces a new integrated framework for short-term time series forecasting used as decision logic support in Energy Management Systems (EMS). The proposed framework defines data preprocessing, forecast model training, and adaptation techniques. For data preprocessing, Gaussian and Kalman filtering were used in offline learning on historical data and online (real-time) forecasting. Optimal parametrisation for both filters was selected based on the forecast accuracy. Next, a multiple-input, single-output forecast model based on the Long Short-Term Memory (LSTM) neural network was tuned for each device. The forecast horizon is single-step, and chaining of predictions was used for longer horizons. Finally, the best model was adapted to the changes in the time series data. A significant drop was observed in the forecast accuracy on the past data after adapting the model to the new data using a naive approach. Due to this drop, a novel sample rehearsal selection strategy for adaptation of the model is proposed and compared to other different strategies. All the techniques are demonstrated based on the examples of forecasting multivariate time series for different household devices: a water heater, a refrigerator and an HVAC device. The use of data preprocessing improved the forecast accuracy by up to 56% compared to no preprocessing. Moreover, by introducing a sample rehearsal, knowledge retention was improved by up to 76.6% compared to the naive approach, and by up to 62% compared to the random selection of samples.

Clouds moving at a high speed in front of the Sun can cause step changes in the output power of photovoltaic (PV) power plants, which can lead to voltage fluctuations and stability problems in the connected electricity networks. These effects can be reduced effectively by proper short-term cloud passing forecasting and suitable PV power plant output power control. This paper proposes a low-cost Internet of Things (IoT)-based solution for intra-minute cloud passing forecasting. The hardware consists of a Raspberry PI Model B 3 with a WiFi connection and an OmniVision OV5647 sensor with a mounted wide-angle lens, a circular polarizing (CPL) filter and a natural density (ND) filter. The completely new algorithm for cloud passing forecasting uses the green and blue colors in the photo to determine the position of the Sun, to recognize the clouds, and to predict their movement. The image processing is performed in several stages, considering selectively only a small part of the photo relevant to the movement of the clouds in the vicinity of the Sun in the next minute. The proposed algorithm is compact, fast and suitable for implementation on low cost processors with low computation power. The speed of the cloud parts closest to the Sun is used to predict when the clouds will cover the Sun. WiFi communication is used to transmit this data to the PV power plant control system in order to decrease the output power slowly and smoothly.

This paper investigates the economic feasibility of utilising energy flexibility in aluminium production as a viable solution to leverage electricity surpluses arising from the increasing number of photovoltaic (PV) system installations. Future trends suggest that the generation capacity of PV systems will soon surpass consumption, leading to significant electricity surpluses, particularly during the summer. This surplus electricity, which is anticipated to be available at low prices, offers a unique opportunity to evaluate different investment and utilisation scenarios for aluminium production while simultaneously decreasing its environmental impact. The results demonstrate that, despite their high initial investment cost, large-scale PV power plants can potentially deliver maximum economic gains over a ten-year period. Conversely, the direct utilisation of surpluses without substantial investment can yield savings of up to EUR 17 million within the same time frame for Slovenia’s case with an aluminium smelter, which has a maximum power usage of 60 MW. The findings of this study have significant implications in terms of shaping future energy strategies and policies, emphasizing the value of integrating renewable energy sources and industrial processes for enhanced economic and environmental outcomes.

Modern LED light sources have many advantages, as well as some disadvantages. One of the disadvantages is the pulsating luminous flux, which, in some cases, affects people’s health and well-being negatively. The paper describes the design and making process of a measuring system for determining the quality of LED substitutes for conventional light bulbs and gives an overview of LED light bulbs for household use. The measurement system is controlled using the MATLAB software environment, in which data processing and plotting of the results are also performed. We acquired 59 different LED light bulbs from 37 manufacturers, and performed the measurements. The light bulbs are classified based on the percentage of fluctuations in the luminous flux, and the percentage of deviation of the measured luminous flux compared to the value stated on the packaging by the manufacturer.

Voltage supraharmonics present in the electrical grid can trigger chain reactions in grid-connected household and industrial power supplies equipped with Power Factor Correction (PFC). A single source of voltage supraharmonics may significantly increase the current in switching devices with PFC, leading to higher-amplitude disturbances throughout the electrical network. When addressing issues in a real low-voltage (LV) grid, it was observed that activation of a single device emitting supraharmonics caused oscillating currents across all feeders connected to the transformer’s busbars, matching the frequency of the supraharmonic source. To investigate this phenomenon further, the grid voltage containing supraharmonics was replicated in a controlled laboratory environment and used to supply various power electronic devices. The laboratory results closely mirrored those observed in the field. Supraharmonics present in the supply voltage caused current oscillations in the power electronic devices at the same frequency. Moreover, the amplitude of the observed current oscillations increased with the amplitude of the injected supply voltage supraharmonics. In some cases, the root mean square (RMS) value of the current drawn by the power electronic devices doubled, indicating a substantial impact on device behaviour and potential implications for grid stability and energy efficiency.

Diesel generators are indispensable in areas lacking electricity infrastructure or requiring alternative power sources. However, while they offer significant advantages, they also suffer notable drawbacks, particularly in fuel efficiency during lower loads. Typically, generators operate in tandem with load profiles, resulting in inefficient operation during reduced loads. This article proposes a solution by integrating generator operation with a battery system. By combining the generator with batteries during periods of lower efficiency, we aim to enhance overall system efficiency.