Mathematical Modelling and Operation Simulation of the Indirect Connection Scheme of the Heating Installation and of the Consumption Hot Water Preparation in an Accumulating Stage

This paper presents the mathematical model and simulation of a thermal system for heating and supplying hot water to industrial or residential consumers consisting of a heat exchanger on the heating circuit and a heat exchanger provided with an accumulation tank on the domestic hot water circuit, this scheme is generally adopted in the industrial thermal points and increasingly in module-type thermal points for residential consumers. The mathematical model is based on the mathematical equations describing this system and developed using the MATLAB - Simulink program. Thus, as a result of the simulations, we can see the evolutions in time of the water temperatures on the heating circuit and the domestic hot water circuit, as well as the quantity of heat delivered by them.

Analysis for Non-Residential Short-Term Load Forecasting Using Machine Learning and Statistical Methods with Financial Impact on the Power Market

Short-term load forecasting predetermines how power systems operate because electricity production needs to sustain demand at all times and costs. Most load forecasts for the non-residential consumers are empirically done either by a customer’s employee or supplier personnel based on experience and historical data, which is frequently not consistent. Our objective is to develop viable and market-oriented machine learning models for short-term forecasting for non-residential consumers. Multiple algorithms were implemented and compared to identify the best model for a cluster of industrial and commercial consumers. The article concludes that the sliding window approach for supervised learning with recurrent neural networks can learn short and long-term dependencies in time series. The best method implemented for the 24 h forecast is a Gated Recurrent Unit (GRU) applied for aggregated loads over three months of testing data resulted in 5.28% MAPE and minimized the cost with 5326.17 € compared with the second-best method LSTM. We propose a new model to evaluate the gap between evaluation metrics and the financial impact of forecast errors in the power market environment. The model simulates bidding on the power market based on the 24 h forecast and using the Romanian day-ahead market and balancing prices through the testing dataset.

Price-Based Demand Side Response Programs and Their Effectiveness on the Example of TOU Electricity Tariff for Residential Consumers

Demand side response is becoming an increasingly significant issue for reliable power systems’ operation. Therefore, it is desirable to ensure high effectiveness of such programs, including electricity tariffs. The purpose of the study is developing a method for analysing electricity tariff’s effectiveness in terms of demand side response purposes based on statistical data concerning tariffs’ use by the consumers and price elasticity of their electricity demand. A case-study analysis is presented for residential electricity consumers, shifting the settlement and consequently the profile of electricity use from a flat to a time-of-use tariff, based on the comparison of the considered tariff groups. Additionally, a correlation analysis is suggested to verify tariffs’ influence of the power system’s peak load based on residential electricity tariffs in Poland. The presented analysis proves that large residential consumers aggregated by tariff incentives may have a significant impact on the power system’s load and this impact changes substantially for particular hours of a day or season. Such efficiency assessment may be used by both energy suppliers to optimize their market purchases and by distribution system operators in order to ensure adequate generation during peak load periods.