Microgrids (MGs) are sustainable solutions for rural zone electrification that use local renewable resources. However, only careful planning at the start of an MG project can ensure its future optimal operation. In this paper, a novel methodology for MG planning by using the uncertainty characterization of renewable resources and demand is presented. Additionally, a model of electricity consumption is proposed and applied in an isolated rural community. In such communities, consumption patterns typically need to be derived as model inputs because consumption measurements are not available for the planning stage. To obtain these inputs, clustering algorithms based on self-organizing maps (SOMs) and fuzzy c-means are used to classify the families of the community given sociodemographic information obtained via surveys. Subsequently, Markov chains (MCs) are employed to generate consumption patterns based on consumption measurements in some dwellings and surveys applied to the community. The nonlinearities and uncertainties associated with renewable resources and consumption are modeled by using prediction interval (PI) models. These PI models provide the required consumption and generation scenarios for deriving the optimal sizing and topological information to address the MG planning problem. The results of the robust planning approach based on scenarios are useful at the feasibility and design phases of an MG project. The proposed methodology is successfully applied to MG planning for a rural Mapuche community, where a conservative criterion was considered to minimize the investment risk. This criterion corresponds to the worst-case scenario in which the demand increases by 19.9% compared to that of the baseline scenario and a lower energy cost is obtained. However, the net present cost and operational costs increase by 14% and 11.75% compared to those of the baseline scenario, respectively.@en

This paper presents a model comparison of a fixed speed wind turbine (FSWT) operating on a real wind farm. By relying on real data obtained from a wind farm operating in the Chilean Interconnected System, three different models are identified and analyzed. First, a phenomenological model based on physical principles governing the production of electricity from wind power is considered. This model is fine-tuned in accordance with practical considerations, such as wind correction factors. Then, a linear model and a Takagi & Sugeno (T&S) fuzzy model are identified. From the experimental results, the linear model is the simplest one, but also the one that presents the worst performance indexes. The best prediction capability is obtained with the T&S model; however, in terms of interpretability, the phenomenological model outperforms the other two black-box models.@en

This paper presents a two-level hierarchical energy management system (EMS) for microgrid operation that is based on a robust model predictive control (MPC) strategy. This EMS focuses on minimizing the cost of the energy drawn from the main grid and increasing self-consumption of local renewable energy resources, and brings benefits to the users of the microgrid as well as the distribution network operator (DNO). The higher level of the EMS comprises a robust MPC controller which optimizes energy usage and defines a power reference that is tracked by the lower-level real-time controller. The proposed EMS addresses the uncertainty of the predictions of the generation and end-user consumption profiles with the use of the robust MPC controller, which considers the optimization over a control policy where the uncertainty of the power predictions can be compensated either by the battery or main grid power consumption. Simulation results using data from a real urban community showed that when compared with an equivalent (non-robust) deterministic EMS (i.e., an EMS based on the same MPC formulation, but without the uncertainty handling), the proposed EMS based on robust MPC achieved reduced energy costs and obtained a more uniform grid power consumption, safer battery operation, and reduced peak loads.@en

This study presents a novel load estimation method for isolated communities that do not receive energy or only receive it for a limited time each day. These profiles have been used to determine the installed capacity of generating units for microgrid electrification projects. The social characteristics and lifestyles of isolated communities differ from those in urban areas; therefore, the load profiles of microgrids are sensitive to minor variations in generation and/or consumption. The proposed methodology for obtaining the residential profiles is based on clustering algorithms such as k-means, a self-organizing map (SOM) or others. In this work, SOM clustering is considered because it allows a better interpretation of results that can be contrasted with social aspects. The proposed methodology includes the following components. First, the inputs are processed based on surveys of residents that live in each socio-economic level of housing and the community. Second, family types are clustered using an SOM, from which relevant information is derived that distinguishes one family from another. Third, the load profiles of each cluster are selected from a database. Additionally, social aspects and relevant energy supply information from communities with similar characteristics are used to generate the required database. The SOM for the clustering of families of the community with available energy measurements is used as an initial guess for the clustering of the families in the community with unknown energy measurements. The methodology is applied and tested in the community of El Romeral, Chile, where a microgrid will be installed. The SOM technique compares favorably with a benchmark method that uses the average load profile of a community; furthermore, the SOM clustering algorithm for the methodology is favorably compared with the k-means algorithm because the results obtained by SOM are consistent with the social aspects.@en

Modulated model predictive control (M 2 PC) allows fixed switching frequency operation of power converters, producing lower ripple and lower total harmonic distortion (THD) in the output signals than those obtained using regular model predictive control (MPC) algorithms. However, the design of the M 2 PC algorithm and its performance depend on, among other factors, the tuning of weighting factors, which are required by the cost functions typically used in predictive control algorithms. In this paper, a novel Pareto-based multi-objective M 2 PC (MO-M 2 PC) strategy is proposed. In this case, the use of weighting factors is not required, and the optimization problem is solved using a multi-objective approach. The aim of the proposed MO-M 2 PC strategy is to consider practical rules, such as satisfaction of soft constraints, to calculate the control actions. The proposed Pareto-based MO-M 2 PC strategy can be applied to any power converter topology. In this paper, experimental validation of the proposed methodology is pursued using a 3-phase 3 kW power converter operating as a shunt active power filter (SAPF). The proposed control is implemented in a control platform based on the dSPACE ds1103 system. The simulation and experimental results demonstrate the advantages and flexibility achieved by the proposed Pareto-based MO-M 2 PC. @en

Prediction interval modelling has been proposed in the literature to characterize uncertain phenomena and provide useful information from a decision-making point of view. In most of the reported studies, assumptions about the data distribution are made and/or the models are trained at one step ahead, which can decrease the quality of the interval in terms of the information about the uncertainty modelled for a higher prediction horizon. In this paper, a new prediction interval modelling methodology based on fuzzy numbers is proposed to solve the abovementioned drawbacks. Fuzzy and neural network prediction interval models are developed based on this proposed methodology by minimizing a novel criterion that includes the coverage probability and normalized average width. The fuzzy number concept is considered because the affine combination of fuzzy numbers generates, by definition, prediction intervals that can handle uncertainty without requiring assumptions about the data distribution. The developed models are compared with a covariance-based prediction interval method, and high-quality intervals are obtained, as determined by the narrower interval width of the proposed method. Additionally, the proposed prediction intervals are tested by forecasting up to two days ahead of the load of the Huatacondo microgrid in the north of Chile and the consumption of the residential dwellings in the town of Loughborough, UK. The results show that the proposed models are suitable alternatives to electrical consumption forecasting because they obtain the minimum interval widths that characterize the uncertainty of this type of stochastic process. Furthermore, the information provided by the obtained prediction interval could be used to develop robust energy management systems that, for example, consider the worst-case scenario.@en

Microgrids are suitable electrical solutions for providing energy in rural zones. However, it is challenging to propose in advance a good design of the microgrid because the electrical load is difficult to estimate due to its highly dependence of the residential consumption. In this paper, a novel estimation methodology for the residential load profiles is proposed. Socio-demographic data and electrical power consumption are used to generate significant knowledge about the load behavior. Socio-demographic data are used as input for a neural network called Self-Organizing Maps (SOM). The SOM proposes a way to group dwelling according to their different features. Moreover, a probabilistic model based on Bayesian networks incorporates daily variations of the electrical load, simulating the behavior of the electrical appliances. The methodology, as a whole, is applied to a case study in a rural community located in Chile. The methodology is easily adaptable to other rural communities. @en

In this paper we describe the design of hybrid fuzzy predictive control based on a genetic algorithm (GA). We also present a simulation test of the proposed algorithm and a comparison with two hybrid predictive control methods: Explicit Enumeration and Branch and Bound (BB). The experiments involved controlling the temperature of a batch reactor by using two on/off input valves and a discrete-position mixing valve. The GA-hybrid predictive control strategy proved to be a suitable method for the control of hybrid systems, giving similar performance to that of typical hybrid predictive control strategies and a significant saving with respect to the computation time.@en

A hybrid predictive control formulation based on evolutionary multi-objective optimization to optimize real-time operations of public transport systems is presented. The state space model includes bus position, expected load and arrival time at stops. The system is based on discrete events, and the possible operator control actions are: holding vehicles at stations and skipping some stations. The controller (operator) pursues the minimization of a dynamic objective function to generate better operational decisions under uncertain demand at bus stops. In this work, a multi-objective approach is conducted to include different goals in the optimization process that could be opposite. In this case, the optimization was defined in terms of two objectives: waiting time minimization on one side, and impact of the strategies on the other. A genetic algorithm method is proposed to solve the multi-objective dynamic problem. From the conducted experiments considering a single bus line corridor, we found that the two objectives are opposite but with a certain degree of overlapping, in the sense that in all cases both objectives significantly improve the level of service with respect to the open-loop scenario by regularizing the headways. On average, the observed trade-off validates the proposed multi-objective methodology for the studied system, allowing dynamically finding the pseudo-optimal Pareto front and making real-time decisions based on different optimization criteria reflected in the proposed objective function compounds.@en

A hybrid predictive control formulation based on evolutionary multi-objective optimization to optimize real-time operations of public transport systems is presented. The state space model includes bus position, expected load and arrival time at stops. The system is based on discrete events, and the possible operator control actions are: holding vehicles at stations and skipping some stations. The controller (operator) pursues the minimization of a dynamic objective function to generate better operational decisions under uncertain demand at bus stops. In this work, a multi-objective approach is conducted to include different goals in the optimization process that could be opposite. In this case, the optimization was defined in terms of two objectives: waiting time minimization on one side, and impact of the strategies on the other. A genetic algorithm method is proposed to solve the multi-objective dynamic problem. From the conducted experiments considering a single bus line corridor, we found that the two objectives are opposite but with a certain degree of overlapping, in the sense that in all cases both objectives significantly improve the level of service with respect to the open-loop scenario by regularizing the headways. On average, the observed trade-off validates the proposed multi-objective methodology for the studied system, allowing dynamically finding the pseudo-optimal Pareto front and making real-time decisions based on different optimization criteria reflected in the proposed objective function compounds.@en

In this article, a hybrid predictive control (HPC) strategy is formulated for the real-time optimisation of a public transport system operation run using buses. For this problem, the hybrid predictive controller corresponds to the bus dispatcher, who dynamically provides the optimal control actions to the bus system to minimise users' total travel time (on-vehicle ride time plus waiting time at stops). The HPC framework includes a dynamic objective function and a predictive model of the bus system, written in discrete time, where events are triggered when a bus arrives at a bus stop. Upon these events, the HPC controller makes decisions based on two well-known real-time transit control actions, holding and expressing. Additionally, the uncertain passenger demand is included in the model as a disturbance and then predicted based on both offline and online information of passenger behaviour. The resulting optimisation problem of the HPC strategy at every event is Np-hard and needs an efficient algorithm to solve it in terms of computation time and accuracy. We chose an ad hoc implementation of a Genetic Algorithm that permits the proper management of the trade-off between these two aspects. For real-time implementation, the design of this HPC strategy considers newly available transport technology such as the availability of automatic passenger counters (APCs) and automatic vehicle location (AVL) devices. Illustrative simulations at 2, 5 and 10 steps ahead are conducted, and promising results showing the advantages of the real-time control schemes are reported and discussed.@en

This paper presents a hybrid adaptive predictive control approach to incorporate future information regarding unknown demand and expected traffic conditions, in the context of a dynamic pickup and delivery problem with fixed fleet size. As the routing problem is dynamic, several stochastic effects have to be considered within the analytical expression of the dispatcher assignment decision objective function. This paper is focused on two issues: one is the extra cost associated with potential rerouting arising from unknown requests in the future, and the other is the potential uncertainty in travel time coming from non-recurrent traffic congestion from unexpected incidents. These effects are incorporated explicitly in the objective function of the hybrid predictive controller. In fact, the proposed predictive control strategy is based on a multivariable model that includes both discrete/integer and continuous variables. The vehicle load and the sequence of stops correspond to the discrete/integer variable, adding the vehicle position as an indicator of the traffic congestion conditions. The strategy is analyzed under two scenarios. The first one considers a predictable congestion obtained using historical data (off-line method) requiring a predictive model of velocities distributed over zones. The second scenario that accepts unpredictable congestion events generates a more complex problem that is managed by using both fault detection and isolation and fuzzy fault-tolerant control approaches. Results validating these approaches are presented through a simulated numerical example.@en

This paper presents a hybrid adaptive predictive control approach to incorporate future information regarding unknown demand and expected traffic conditions, in the context of a dynamic pickup and delivery problem with fixed fleet size. As the routing problem is dynamic, several stochastic effects have to be considered within the analytical expression of the dispatcher assignment decision objective function. This paper is focused on two issues: one is the extra cost associated with potential rerouting arising from unknown requests in the future, and the other is the potential uncertainty in travel time coming from non-recurrent traffic congestion from unexpected incidents. These effects are incorporated explicitly in the objective function of the hybrid predictive controller. In fact, the proposed predictive control strategy is based on a multivariable model that includes both discrete/integer and continuous variables. The vehicle load and the sequence of stops correspond to the discrete/integer variable, adding the vehicle position as an indicator of the traffic congestion conditions. The strategy is analyzed under two scenarios. The first one considers a predictable congestion obtained using historical data (off-line method) requiring a predictive model of velocities distributed over zones. The second scenario that accepts unpredictable congestion events generates a more complex problem that is managed by using both fault detection and isolation and fuzzy fault-tolerant control approaches. Results validating these approaches are presented through a simulated numerical example.@en

In this paper we present a method of hybrid predictive control (HPC) based on a fuzzy model. The identification methodology for a nonlinear system with discrete state-space variables based on combining fuzzy clustering and principal component analysis is proposed. The fuzzy model is used for HPC design, where the optimization problem is solved by the use of genetic algorithms (GAs). An illustrative experiment on a hybrid tank system is conducted to demonstrate the benefits of the proposed approach.@en

The paper deals with model predictive control (MPC) of nonlinear hybrid systems with discrete inputs. It is often required to take into account the hybrid and/or nonlinear nature of real systems, therefore, a hybrid fuzzy model is used for MPC in the paper. Two approaches that are suitable for MPC of nonlinear hybrid systems with discrete inputs are compared on a batch reactor example: a branch & bound and a genetic algorithm. We have established that both algorithms are suitable for controlling such systems. The main advantages of the genetic algorithm are boundedness of computational time in one step and whole computation-e±ciency, whereas the main drawbacks are its inherent sub-optimality and the need for suitably tuned parameters. On the other hand, the branch & bound approach does not require parameter tuning and using a suitable cost function provides optimal results in considerably less time than an explicit enumeration method.@en

In this paper, we develop a family of solution algorithms based upon computational intelligence for solving the dynamic multi-vehicle pick-up and delivery problem formulated under a hybrid predictive adaptive control scheme. The scheme considers future demand and prediction of expected waiting and travel times experienced by customers. In addition, this work includes an analytical formulation of the proposed prediction models that allow us to search over a reduced feasible space. Predictive models consider relevant state space variables as vehicle load and departure time at stops. A generic expression of the system cost function is used to measure the benefits in dispatching decisions of the proposed scheme when solving for more than two-step ahead under unknown demand. The demand prediction is based on a systematic fuzzy clustering methodology, resulting in appropriate call probabilities for uncertain future. As the dynamic multi-vehicle routing problem considered is NP-hard, we propose the use of genetic algorithms (GA) that provide near-optimal solutions for the three, two and one-step ahead problems. Promising results in terms of computation time and accuracy are presented through a simulated numerical example that includes the analysis of the proposed fuzzy clustering, and the comparison of myopic and new predictive approaches solved with GA.@en

In this paper, we develop a family of solution algorithms based upon computational intelligence for solving the dynamic multi-vehicle pick-up and delivery problem formulated under a hybrid predictive adaptive control scheme. The scheme considers future demand and prediction of expected waiting and travel times experienced by customers. In addition, this work includes an analytical formulation of the proposed prediction models that allow us to search over a reduced feasible space. Predictive models consider relevant state space variables as vehicle load and departure time at stops. A generic expression of the system cost function is used to measure the benefits in dispatching decisions of the proposed scheme when solving for more than two-step ahead under unknown demand. The demand prediction is based on a systematic fuzzy clustering methodology, resulting in appropriate call probabilities for uncertain future. As the dynamic multi-vehicle routing problem considered is NP-hard, we propose the use of genetic algorithms (GA) that provide near-optimal solutions for the three, two and one-step ahead problems. Promising results in terms of computation time and accuracy are presented through a simulated numerical example that includes the analysis of the proposed fuzzy clustering, and the comparison of myopic and new predictive approaches solved with GA.@en

In this paper, two methods for generating the daily load profile and forecasting in isolated small communities are proposed. In these communities, the energy supply is difficult to predict because it is not always available, is limited according to some schedules and is highly dependent on the consumption behavior of each community member. The first method is proposed to be used before the implementation of the microgrid in the design state, and it includes a household classifier based on a Self Organizing Map (SOM) that provides load patterns by the use of the socio-economic characteristics of the community obtained in a survey. The second method is used after the implementation of the microgrid, in the operation state, and consists of a neural network with on-line learning for the load forecasting. The neural network model is trained with real-data of load and it is designed to stay adapted according to the availability of measured data. Both proposals are tested in a real-life microgrid located in Huatacondo, in northern Chile (project ESUSCON). The results show that the estimated daily load profile of the community can be very well approximated with the SOM classifier. On the other hand, the neural network can forecast the load of the community reasonably well two-days ahead. Both proposals are currently being used in a key module of the energy management system (EMS) in the real microgrid to optimize the real uninterrupted load for 24-hour energy supply service.@en

This paper presents a hybrid adaptive predictive control approach that includes future information in realtime routing decisions in the context of a dynamic pickup and delivery problem (DPDP). We recognize in this research that when the problem is dynamic, an additional stochastic effect has to be considered within the analytical expression of the objective function for vehicle scheduling and routing, which is the extra cost associated with potential rerouting arising from unknown requests in the future. The major contributions of this paper are: first, the development of a formal adaptive predictive control framework to model the DPDP, and second, the development and coding of an ad hoc particle swarm optimization (PSO) algorithm to efficiently solve it. Predictive state-space formulations are written on the relevant variables (vehicle load and departure time at stops) for the DPDP. Next, an objective function is stated to solve the real-time system when predicting one and two steps ahead in time. A problem-specific PSO algorithm is proposed and coded according to the dynamic formulation. Then, the PSO method is used to validate this approach through a simulated numerical example.@en

In the paper, the hybrid predictive control based on a fuzzy model is presented. The identification methodology for a nonlinear system with discrete state-space variables by combining fuzzy clustering and principal component analysis is proposed. The fuzzy model is used for hybrid predictive control design where the optimization problem is solved by the use of genetic algorithms. An illustrative experiment on a hybrid tank system is conducted to present the benefits of the proposed approach.@en