Design of a microgrid for cold storage in agriculture based on stochastic optimization and AWS IoT analytics

Food poisoning and food spoilage have increased remarkably the last decade due to the lack of food cold chain infrastructure, specially in emerging economies. A microgrid (MG) represents an opportunity for a solid transition to integrate renewable energy generation to our vulnerable and unsustainable traditional power grid. Recent advances in technology allow us to consider capturing massive amounts of data from weather sensors, and other electrical devices. To bridge this gap, this research proposes to use AWS IoT Analytics to enhance the stochastic optimization model for a MG for a cold storage in agriculture, and to reduce the curtailment effect. The decisionmodelisformulatedasatwo-stageoptimizationproblemtoobtainoperationdecisionsforabehind-the-metertopology. Thecomparisonbetweenthecurrentpractice ofusinghistoricaldataandintegratingAWSIoTAnalyticstechnologiesdemonstrates the superiority of the streaming data as energy management strategy. A real-world case is developed in Peru for an agriculture application. Experiments under different settingsshowthatusingbigdatastrategy,themodelcan1)achievemorecostsavings of the total system, 2) increase resiliency to power disturbances, and 3) build a data analytics framework to enhance the decision-making process.