No abstract

No abstract

Nowadays, the energy sharing of RES production within Renewable Energy Communities (REC) is promoting the diffusion of a more decentralized energy system, where dispersed renewable generation can be locally self-consumed by REC members. The maximization of self-consumption through the matching between generation and demand is thus fundamental to ensure higher economic and environmental benefits for residential end-users joining REC configurations. However residential electricity demand and the corresponding load profile are generally influenced by end-users' behavior. In fact, even if most of the household appliances can be assumed as fixed loads, the usage of some appliances depends basically on the residents' habits. The engagement of customers in changing their energy consumption patterns is then challenging to promote flexibility in electricity demand to further increase the benefits of adopting and joining renewable energy communities. In this view, a MILP approach is proposed to model end-users' flexibility for investigating how the changing in consumption habits can potentially improve the energy sharing by maximizing the match between RES production and demand. User's discomfort is evaluated consequently as the distance between the desired or usual consumption pattern and the optimized one. An Italian multifamily residential building case study, where end-users adopt a collective self-consumption scheme, is considered to highlight energy and economic results assuming different level of end-users' flexibility. Finally, a comparison between the maximization of energy sharing and the minimization of discomfort rate is pointed out through weighted sum method to identify solutions with different relevance of the end-users' flexibility.

Purpose This paper aims to compare stochastic gradient method used for neural network training with global optimizer without use of gradient information, in particular differential evolution. Design/methodology/approach This contribute shows the application of heuristic optimization algorithms to the training phase of artificial neural network whose aim is to predict renewable power production as function of environmental variables such as solar irradiance and temperature. The training problem is cast as the minimization of a cost function whose degrees of freedom are the parameters of the neural network. A differential evolution algorithm is substituted to the more usual gradient-based minimization procedure, and the comparison of their performances is presented. Findings The two procedures based on stochastic gradient and differential evolution reach the same results being the gradient based moderately quicker in convergence but with a lower value of reliability, as a significant number of runs do not reach convergence. Research limitations/implications The approach has been applied to two forecasting problems and, even if results are encouraging, the need for extend the approach to other problems is needed. Practical implications The new approach could open the training of neural network to more stable and general methods, exploiting the potentialities of parallel computing. Originality/value To the best of the authors’ knowledge, the research presented is fully original for the part regarding the neural network training with differential evolution.

Renewable energy communities (RECs) are legal entities where citizens, small-to-medium en- terprises (SMEs) and local authorities join to manage cooperatively energy from renewable sources. Since the regulation requires to evaluate energy fluxes on the hour base, the operative control and performance assessment of these new energy hubs become complex and require the handling of data such as production from renewable energy sources (RES) and end user con- sumption, that are intrinsically affected by uncertainties. In this contribution, an optimization tool for the operational management of a REC is proposed. RECs can contain renewable energy technologies (photovoltaic or solar thermal panels, biofuel burners), electric, heating and cooling end users and coupling components (e.g., heat pumps). The tool can be used at the planning level to compare different REC configurations based on their performances, assuming optimal man- agement of the available technologies. In this paper, the tool is tested in the simulation of three case studies of collective self-consumption (that in Italy is a REC where all end users are in the same building), located at different latitudes of the Italian country.