Deep convolutional neural networks for short-term multi-energy demand prediction of integrated energy systems

Abstract

• In the context of the Deep Convolutional Neural Networks (CNNs), there are developed and evaluated six novel CNN models for short-term prediction of multi-energy vectors of a novel integrated energy system consisting of three different electric, heat and gas networks and a total of 39 interconnected buildings. • The novel prediction CNN models can be classified function of the type and the number of input and output variables, and type of learning (centralized or distributed). • High correlations between the next and the previous 24 hours building power consumptions are envisaged, and higher correlations than the ones calculated with regard to the weather temperature data (°C) or the solar radiance. • The numerical results obtained for the testing datasets and evaluated in terms of Signal-to-Noise Ratio (SNR) and Normalized Root Mean Square Error (NRMSE), show that the single input variable/single output variable CNN models (CNN_1 and CNN_3), which input/output variables are corresponding to each building and each type of energy consumption, predict the best in comparison to the other models. • For the novel integrated energy system comprising the three distinct networks (electric, heat and gas), it is shown that as the input data is more non-linear and scarce, then it becomes more difficult to predict, and this is to be expected also for any other single or integrated energy system. Forecasting power consumptions of integrated electrical, heat and gas network systems is essential in order to operate more efficiently the multi-energy network system. Multi-energy systems are increasingly seen as a key component of future energy systems, and a valuable source of flexibility, which can significantly contribute to a cleaner and more sustainable integrated energy system. Therefore, there is a stringent need for developing novel and performant models for forecasting multi-energy demands of integrated energy systems, which to account for the different types of interacting energy vectors and of the coupling between them. Previous efforts in demand forecasting focused only on electrical power consumptions or, more recently, on the single heat or gas power consumptions. Therefore, in order to address the multi-energy demand forecasting problem, in this paper six novel prediction models based on Convolutional Neural Networks (CNNs) are developed, for either individual or joint prediction of multi-energy power consumptions: the single input/single output variable CNN model with determining the optimum number of epochs (CNN_1), the multiple input/single output variable CNN model (CNN_2), the single input/single output CNN model with training/validation/testing datasets (CNN_3), the joint prediction CNN model (CNN_4), the multiple-building input/output CNN model (CNN_5) and the federated learning CNN model (CNN_6). All six models are applied in a comprehensive manner on a novel integrated electrical, heat and gas network system, which only recently has started to be used for forecasting. The forecast horizon is short-term (i.e. next half an hour) and all the prediction results are evaluated in terms of the Signal to Noise Ratio (SNR) and the Normalized Root Mean Square Error (NRMSE), while the Mean Absolute Percentage Error (MAPE) is used for comparison purposes with other existent results from literature. The numerical results show that the single input/single output variable CNN model with training/validation/testing datasets (CNN_3) is able to equal the performances of the single input/single output variable CNN model with determining the optimum number of epochs (CNN_1), and to outperform the other four prediction models. The prediction accuracy of the multi-energy networks loads is shown to significantly depend on the level of non-linearity and scarcity existent in the input training dataset(s). Furthermore, this extensive multi-model study reveals that the characteristics (i.e. connections between the different networks, correlations between the different energy vectors) of the considered integrated energy system need to be explored when designing the CNNs prediction models.

Topics & Concepts