The large thermal capacity of buildings enables heating, ventilating, and air-conditioning (HVAC) systems to be exploited as demand response (DR) resources. Optimal DR of HVAC units is challenging, particularly for multi-zone buildings, because this requires detailed physics-based models of zonal temperature variations for HVAC system operation and building thermal conditions. This paper proposes a new strategy for optimal DR of an HVAC system in a multi-zone building, based on supervised learning (SL). Artificial neural networks (ANNs) are trained with data obtained under normal building operating conditions. The ANNs are replicated using piecewise linear equations, which are explicitly integrated into an optimal scheduling problem for price-based DR. The optimization problem is solved for various electricity prices and building thermal conditions. The solutions are further used to train a deep neural network (DNN) to directly determine the optimal DR schedule, referred to here as supervised-learning-aided meta-prediction (SLAMP). Case studies are performed using three different methods: explicit ANN replication (EAR), SLAMP, and physics-based modeling. The case study results verify the effectiveness of the proposed SL-based strategy, in terms of both practical applicability and computational time, while also ensuring the thermal comfort of occupants and cost-effective operation of the HVAC system.
For South Australia, it was a cruelly ironic one-two punch – a burst of the extreme heat conditions that are so much more likely because of climate change, and a power cut linked to a simultaneous drop in wind that hobbled the renewable energy systems introduced to minimise global warming in the first place. On 8 February, South Australians had their air conditioners on full blast while sweltering through temperatures in excess of 46C in some parts of the state, and wind turbines had stopped turning just when energy demand was at its highest. The Australian Energy Market Operator chose not to bring online a standby gas generator and, thanks to an additional computer glitch at SA Power Networks, three times as many houses had their power cut than necessary – a familiar plunge into darkness for the sweat-laced locals of a state that has had more than its fair share of energy problems in recent times. The persistent power-cuts and price surges have seen the Turnbull government blame the state's heavy reliance on intermittent wind farms and advocate for the building of new coal-fired plants, while renewable energy advocates are looking to battery storage systems, which are coming down in price but remain expensive, as the long-term solution. The head of BuddeComm, Paul Budde, however has another idea: talking to air conditioners.
By integrating Verizon's Managed Connectivity LTE solutions into Honeywell's next-generation smart meters and other electric, gas, and water solutions, the two companies will drive energy savings by more quickly deploying smart electric grid technologies. These technologies allow consumers to use energy at the optimum time and help utilities manage and plan for peak demand. Combining Managed Connectivity, which will be offered as a service on Verizon's LTE network, with Honeywell Smart Energy software, hardware and services, the collaboration will provide utility companies with a highly scalable, fully managed, open computing and communications platform to help them manage operations efficiently and safely deliver new services to their customers. "Working with Honeywell on these next-generation solutions will enable the reliability and scalability of the communications needed to deliver smart metering, manage distributed energy resources, conserve water, and make the digital world work better for utilities and consumers," said Jay Olearain, director, Enterprise Products and IoT at Verizon. "Our Connected Utilities solutions bring connectivity and computing capabilities to all kinds of IoT devices, helping companies like Honeywell grow their leadership positions in the utilities space and expand their business models into new market opportunities."
TP-Link sells smart plugs and light switches that add convenience and cost savings. Did you know more than a quarter of your income is gobbled up by your home? Mortgage or rent payments make up the bulk of it, says the Bureau of Labor Statistics, but 11 percent of your annual income goes towards utilities and other household operating costs. Don't be surprised: from energy-sucking appliances to leaving the lights on in rooms to blasting your air conditioner all day (when you're at work), it can all really add up. My wife and I bit the bullet last year and replaced every single light in and outside our home, more than 400, with LEDs – from pot lights and regular (A19) bulbs to tiny chandelier lights and large front yard flood lights.