Edge-Based Short-Term Energy Demand Prediction

Abstract

The electrical grid is gradually transitioning towards being an interconnected area of the smart grid, where embedded devices operate in an autonomous manner without any human intervention. An important element for this transition is the energy demand prediction, since the needs for energy have substantially increased due to the introduction of new and heavy consumption sources, such as electric vehicles. Accurate energy demand prediction, especially for short-term durations (i.e., minutes to hours), allows grid operators to produce the substantial amount needed to satisfy the demand–response equilibrium and avoid peak electricity load conditions that may also lead to blackouts in densely populated areas. However, to achieve such an accuracy level, machine learning (ML) models require extensive training with historical measurements, which is usually resource intensive (e.g., in memory and processing power). Hence, deriving accurate predictions for short-term energy demands is challenging due to the absence of external factors such as environmental data from different regions and seasons and categorical values such as bank/bridging holidays in the ML model. Additionally, existing work focuses on ML model execution on Cloud platforms, which usually does not satisfy the real-time requirements of grid operators for short-term energy demand predictions. To address these challenges, this article presents a new method that considers environmental factors and categorical values to build an energy profile for each consumer in a multi-access edge computing (MEC) framework. The method is also based on the Temporal Fusion Transformer (TFT) ML model, which allows it to learn the temporal dependencies of the gathered historical measurements and predict energy demands with satisfying accuracy. The method is applied to a home energy management system testbed containing photovoltaic systems, smart meters, sensors and actuators for detecting environmental factors (i.e., temperature, humidity and radiation) as well as energy storage systems as an additional energy supply source. The MEC framework is deployed in data concentrator devices where the TFT ML model is executed with low resource requirements, ensuring additional security as the data do not leave the location where they are produced.

Energy Cost Optimization for Incorporating Energy Hubs into a Smart Microgrid with RESs, CHP, and EVs

“…In terms of energy demand prediction, the model is able to achieve very good results, especially through edge-based deployment [34]. These results serve as a base for deriving a Short-Term Load Forecast that serves as a base for the EMS system.…”

“…In detail, energy demand is forecasted using historical energy consumption and temperature data to train Machine Learning (ML) models that can be used to derive accurate predictions as the Temporal Fusion Transformer (TFT) model that is detailed in [34]. The TFT includes the Transformer and the Temporal Fusion Decoder (TFD) modules, where the former captures the long-term dependencies in energy consumption data and the latter uses the Long Short-Term Memory Network (LSTM) layers to learn these dependencies.…”

“…The EMS coordinates energy generation, storage, and consumption across the MEC sources of the EH as well as their individual loads. Moreover, it integrates load demand-forecasting modules using ML models trained with historical consumption data for predicting energy demand patterns, enabling proactive adjustments to energy supply and consumption strategies [34]. Additionally, the EMS can also be integrated with an SM, allowing the EH to (1) operate independently from the main grid during outages and (2) have cyber-resilience in the presence of cyber-attacks [38].…”

“…The derived prediction accuracy from the model depends on the timespan of data gathering and a recommended data volume spans over the course of a year for each building or household, in order to allow for the observing of adequate seasonal and temperature variations and for the training of the model. In a typical household or building, the electrical energy consumption data are gathered from smart meter devices and result approximately in a 5,256,000 total entry size, which in turn requires 250 MB of data storage for each one (i.e., given 50 bytes of storage per entry as detailed in [34]).…”

“…Nevertheless, a current model restriction lies in the prediction accuracy of thermal energy demand due to the lack of sufficient data on the thermal load. Specifically, as also denoted in Section 5, the thermal load data that are used are generic based on the existing district heating network installed in northern Greece [34] and not specific to the building/household. Usually, such data are derived in substantially higher quantities using smart meters for gas consumption.…”